HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Ding, Lingde
Abrégé
A traffic state determination method and apparatus, and a device. The traffic state determination method comprises: on the basis of vehicle passage data corresponding to a first position point and vehicle passage data corresponding to a second position point, determining a first average passage time corresponding to a target road section in the current statistical period (S101), wherein the target road section is a road section from the first position point to the second position point; and on the basis of K threshold intervals corresponding to the target road section, determining a target threshold interval within which the first average passage time is, and on the basis of a traffic state corresponding to the target threshold interval, determining a target traffic state corresponding to the target road section in the current statistical period (S102), wherein the K threshold intervals have one-to-one correspondence to K configured traffic states, and K is a positive integer greater than 1. By means of the traffic state determination method, the traffic state of the target road section can be accurately learned about.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Huan
Abrégé
Embodiments of the present application relate to the technical field of communications, and provide a device communication method and apparatus, and an electronic device. The method is applied to a client in a device communication system, and the device communication system further comprises a communication platform and at least one communication device. The method comprises: the client displaying a platform page of the communication platform, and when detecting a click operation on a target device, sending a page request about the target device to the communication platform, so that the communication platform feeds back to the client a page file sent by the target device; receiving the page file and executing the page file to obtain a device page of the target device; calling an authentication function of the platform page by means of the device page; sending, to the communication platform by means of the device page, a parameter request about the target device and carrying first authentication data; and receiving device parameters and jumping to a device page displaying the device parameters. Compared with the related art, the solution provided by the embodiments of the present application can implement communication between a client and a device without a fixed IP.
H04L 67/54 - Gestion de la présence, p.ex. surveillance ou enregistrement pour la réception des informations de connexion des utilisateurs ou état de connexion des utilisateurs
H04L 41/22 - Dispositions pour la maintenance, l’administration ou la gestion des réseaux de commutation de données, p.ex. des réseaux de commutation de paquets comprenant des interfaces utilisateur graphiques spécialement adaptées [GUI]
3.
TASK PROCESSING METHOD AND APPARATUS BASED ON MODEL QUANTIZATION, AND DEVICE AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Lan, Chaoxiang
Li, Zheyang
Zhang, Kai
Abrégé
Provided in the present disclosure are a task processing method and apparatus based on model quantization, and a device and a storage medium. The task processing method comprises: according to a first difference between a first quantization output of an optimization unit in a transformer model and a first floating-point output of same, updating a weight quantization coefficient of the optimization unit and an activation quantization coefficient of same; according to a second difference between a second quantization output of the optimization unit and a second floating-point output of same, updating a weight quantization increment of the optimization unit; determining a weight quantization rounding direction for the optimization unit according to a target weight quantization increment, and performing quantization on a weight parameter of the optimization unit according to a target weight quantization coefficient and the weight quantization rounding direction; and performing forward reasoning calculation on input data of the optimization unit according to a target quantized weight parameter corresponding to the optimization unit, and performing quantization on inputs and outputs of the optimization unit according to a target activation quantization coefficient of the optimization unit. The method can improve the accuracy of task processing.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pan, Yadong
Abrégé
The present application provides an information synchronization method and apparatus in a distributed remote classroom system and the system. The method comprises: a master whiteboard device sends address information thereof to a slave video device; a slave whiteboard device obtains the address information of the master whiteboard device from the slave video device; after receiving the address information of the master whiteboard device, the slave whiteboard device establishes a communication connection with the master whiteboard device on the basis of the address information of the master whiteboard device; and the master whiteboard device sends picture content of the master whiteboard device to the slave whiteboard device on the basis of the communication connection, so that the slave whiteboard device displays the picture content of the master whiteboard device.
H04L 65/401 - Prise en charge des services ou des applications dans laquelle les services impliquent une session principale en temps réel et une ou plusieurs sessions parallèles additionnelles en temps réel ou sensibles au temps, p.ex. accès partagé à un tableau blanc ou mise en place d’une sous-conférence
H04L 65/1069 - Gestion de session Établissement ou terminaison d'une session
G09B 5/08 - Matériel à but éducatif à commande électrique avec présentation individuelle d'une information à une pluralité de postes d'élèves
5.
IMAGE CODING METHOD AND APPARATUS, IMAGE DECODING METHOD AND APPARATUS, AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Yan
Pan, Dongping
Sun, Yucheng
Chen, Fangdong
Abrégé
Provided in the present application are an image coding method and apparatus, an image decoding method and apparatus, and a storage medium. The coding method comprises: acquiring a coding unit, wherein the coding unit is an image block in an image to be processed, and comprises coding blocks of a plurality of channels, the plurality of channels comprise a first channel, and the first channel is any one of the plurality of channels; and coding the coding block of the first channel according to a first coding mode. The method is suitable for image coding and decoding processes, and is used for solving the problem of substream buffers being set to be excessively large.
H04N 19/176 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p.ex. un objet la zone étant un bloc, p.ex. un macrobloc
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Jian
Wang, Kangli
Zhang, Shujun
Abrégé
Provided in the present application are an integrated antenna and an electronic device. The integrated antenna (20) comprises a dielectric substrate (21) and an antenna radiator (22). The dielectric substrate (21) comprises a floor layer (211) and a clearance area (212), wherein the floor layer (211) is provided with a gap (213) in communication with the clearance area (212). The antenna radiator (22) is arranged in the clearance area (212), the antenna radiator (22) comprises a feed point (221), and the antenna radiator (22) and the gap (213) are located on the same side of the feed point (221). Further provided in the present application is an electronic device (10), which comprises the integrated antenna (20).
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Kan, Jiangnan
Abrégé
Provided in the present application are a host device and a slave device of a building intercom system, and a building intercom system. The host device comprises a host circuit, the host circuit comprising a host power supply end, a host signal processing circuit and a host interface circuit. The host interface circuit is electrically connected to the host communication end, the host power receiving end and the host power supply end. The host interface circuit comprises a host communication interface circuit, a host power interface circuit and a host interface. The host communication interface circuit is electrically connected to the host communication end, the host power interface circuit is electrically connected to the host power receiving end and the host power supply end, the host communication interface circuit and the host power interface circuit are both electrically connected to a first host terminal and a second host terminal of the host interface, and the first host terminal and the second host terminal are used for electrically connecting to the slave device of the building intercom system by means of transmission lines.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pan, Dongping
Sun, Yucheng
Wu, Xiaoyang
Chen, Fangdong
Abrégé
The present application relates to the field of video encoding and decoding, and provides an image encoding method and device, and an image decoding method and device, which can be used for avoiding code stream overflow. The specific decoding method comprises: parsing a code stream of a block to be decoded, and if the code stream of said block comprises a first code word, determining whether a fallback mode is used for an image block corresponding to the block to be decoded; if a fallback mode is used for the image block corresponding to the block to be decoded and the length of code streams stored in a code stream buffer exceeds a set upper overflow limit, according to an excess code stream length of the code stream buffer, determining a fixed code stream length of each component of the block to be decoded, wherein the block to be decoded comprises one or more components; for a first component of the block to be decoded, a fixed code stream length of the first component is used for indicating the code stream length required for parsing single pixels of the first component, and the excess code stream length of the code stream buffer is the code stream length by which the length of the code streams stored in the code stream buffer exceeds the set upper overflow limit; and parsing the pixels of each component on the basis of the fixed code stream length of each component so as to decode the block to be decoded.
H04N 19/152 - Débit ou quantité de données codées à la sortie du codeur par mesure de l’état de remplissage de la mémoire tampon de transmission
H04N 19/186 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une couleur ou une composante de chrominance
H04N 19/85 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le pré-traitement ou le post-traitement spécialement adaptés pour la compression vidéo
9.
VIDEO IMAGE DECODING METHOD AND CODING METHOD, APPARATUS, AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Yan
Sun, Yucheng
Chen, Fangdong
Wu, Xiaoyang
Abrégé
The present application relates to the technical field of video decoding. Provided in the embodiments of the present application are a video image decoding method and coding method, an apparatus, and a storage medium, which help to improving the image quality. The method comprises: acquiring channel-level complexity levels from a data stream, the data stream being a coding data stream of a current block; according to at least two channel-level complexity levels, determining the block-level complexity level of the current block, the channel-level complexity levels being used for representing the complexity degree of the channel-level texture of the current block; according to a code control parameter, determining a target bit number of the current block, the code control parameter comprising the block-level complexity level of the current block; on the basis of the target bit number, determining a quantization parameter of the current block; and on the basis of the quantization parameter, decoding the current block.
H04N 19/176 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p.ex. un objet la zone étant un bloc, p.ex. un macrobloc
H04N 19/186 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une couleur ou une composante de chrominance
10.
ENCODING AND DECODING METHOD, APPARATUS AND DEVICE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pan, Dongping
Wu, Xiaoyang
Sun, Yucheng
Chen, Fangdong
Abrégé
The present invention provides an encoding and decoding method, apparatus and device. The method comprises: when a reference pixel of a current block is not available, removing a target prediction mode from an initial prediction mode list corresponding to the current block, so as to obtain a target prediction mode list; and encoding and decoding the current block on the basis of the target prediction mode list. The present invention can improve the encoding performance and the decoding performance.
H04N 19/103 - Sélection du mode de codage ou du mode de prédiction
H04N 19/61 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant un codage par transformée combiné avec un codage prédictif
11.
IMAGE DECODING METHOD AND APPARATUS, AND IMAGE CODING METHOD AND APPARATUS
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wei, Liang
Chen, Fangdong
Wang, Li
Wu, Xiaoyang
Abrégé
Disclosed in the present application are an image decoding method and apparatus, and an image coding method and apparatus. The image decoding method comprises: determining a predicted residual of a first pixel point according to a prediction mode of the first pixel point, wherein the predicted residual is used for reflecting the gradient of the first pixel point, the prediction mode is used for indicating the position of a reconstructed pixel point referenced when pixel points are predicted, and the first pixel point is any pixel point in the current coding block; determining a target quantization parameter (QP) value of the first pixel point according to the predicted residual of the first pixel point; and performing dequantization on the first pixel point according to the target QP value of the first pixel point.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhao, Xin
Abrégé
Disclosed in the present application are a scene adaptability improvement method and apparatus for object detection, and an object detection system. The method comprises: obtaining a detection result of current object data; performing object feature extraction on the current object data; determining a degree of matching between each object feature and each feature in a feature library; comparing each degree of matching with a detection threshold bound with a matched feature, in the feature library, used for determining the degree of matching; and determining processing of the detection result according to the comparison result, wherein the feature library is a feature set of object data calibrated according to the detection result which indicates a false alarm or a missing alarm; and the detection threshold bound with each matched feature is adjusted along with a degree of matching between the matched feature and the object feature of the object data within a preset range. The present application facilitates the reduction of missing alarms and false alarms, and has high scene adaptability.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Fangdong
Ye, Zongmiao
Wu, Xiaoyang
Abrégé
Provided in the present disclosure are an image decoding method and apparatus based on a neural network, an image encoding method and apparatus based on a neural network, and a device thereof. The image decoding method comprises: decoding, from a code stream, a control parameter and image information, which correspond to the current block; acquiring, from the control parameter, neural network information corresponding to a decoding processing unit, and on the basis of the neural network information, generating a decoding neural network corresponding to the decoding processing unit; and on the basis of the image information, determining an input feature corresponding to the decoding processing unit, and processing the input feature on the basis of the decoding neural network, so as to obtain an output feature corresponding to the decoding processing unit. By means of the present disclosure, the encoding performance and the decoding performance can be improved.
H04N 21/2343 - Traitement de flux vidéo élémentaires, p.ex. raccordement de flux vidéo ou transformation de graphes de scènes MPEG-4 impliquant des opérations de reformatage de signaux vidéo pour la distribution ou la mise en conformité avec les requêtes des utilisateurs finaux ou les exigences des dispositifs des utilisateurs finaux
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Shao, Youbang
Xiong, Hui
Abrégé
An electronic patrol method, apparatus, and device. The method comprises: determining whether a target user has an effective operation for a target video (101); if yes, determining that the target user has completed an electronic patrol task for the target video (102); and if not, determining that the target user has not completed the electronic patrol task for the target video (103). The method can prompt a target user to view the content of a target video, to ensure that the target user views the video content, so that when an abnormal event occurs, the target user can timely discover the abnormal event, and the abnormal event can be timely handled.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Li, Xu
Abrégé
Disclosed in the present invention is a method for issuing facial data. Further disclosed are an apparatus for issuing facial data, and a device. The method comprises: sending, to a first device and by means of a software management platform, first facial data, the data type of which is a picture, wherein the first device comprises a first facial-data application device or a facial-data modeling server; acquiring, from the first device, modeling data corresponding to the first facial data, and then sending a deletion instruction to the first device for the first device to delete the first facial data; and locally deleting the first facial data on a software management platform.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhu, Shuaibo
Abrégé
A video query method and apparatus, and a logistics monitoring system, a device and a program product. The method comprises: acquiring an identifier to be queried; determining, from order information of pre-recorded orders, an acquisition time of the first order information corresponding to a target order, and taking the acquisition time as a processing start time; determining an acquisition time of the last order information corresponding to the target order, and taking the acquisition time as a processing end time; and acquiring, on the basis of the processing start time and the processing end time, a monitoring video corresponding to the target order. By means of order information of pre-recorded orders, a processing start time and a processing end time of an order to which an identifier to be queried belongs can be determined, such that a monitoring video corresponding to the order to which the identifier to be queried belongs can be acquired. A monitoring video corresponding to a target order that a user wants to query can be acquired without the need for manual query, watching and interception, thereby greatly improving the video query efficiency.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Xiong, Hui
Shao, Youbang
Abrégé
A video patrol inspection method and apparatus, an electronic device, and a computer program product. The method comprises: acquiring a target patrol inspection task and, on the basis of a planned time range of the target patrol inspection task and a processing condition of the target patrol inspection task, generating a patrol inspection evaluation record of the target patrol inspection task. After the target patrol inspection task is acquired, by means of acquiring the preset planned time range of the target patrol inspection task and acquiring the processing condition of the target patrol inspection task, the patrol inspection evaluation record of the target patrol inspection task can be generated. Therefore, not only can the target patrol inspection task be executed, but also the patrol inspection evaluation record of the target patrol inspection task can be generated. Thus, when a specific completion condition of the target patrol inspection task needs to be traced later on, the specific completion condition of the target patrol inspection task can be traced back on the basis of the patrol inspection evaluation record of the target patrol inspection task.
G07C 1/20 - Contrôle de rondes tenues à un horaire, p.ex. de gardien
G07C 1/10 - Enregistrement ou indication de l'heure d'un événement ou d'un temps écoulé, p.ex. horodateurs pour la main-d'œuvre combinés avec l'enregistrement ou l'indication d'autres données, p.ex. de signes d'identification
18.
ANTI-PASSBACK PROCESSING METHOD, APPARATUS AND DEVICE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Tao, Duolei
Shen, Zhiming
Abrégé
An anti-passback processing method, apparatus and device, capable of effectively improving the control flexibility and the intelligent degree of an access control system. The method comprises: receiving a first pass request for a target area (S201); according to reference information and a condition, determining whether an anti-passback function takes effect (S202); when the reference information satisfies the condition, determining that the anti-passback function does not take effect (S203); when the reference information does not satisfy the condition, determining that the anti-passback function takes effect (S204); when the anti-passback function does not take effect and access verification on the first pass request is successful, allowing the passing for the first pass request; and when the anti-passback function takes effect and both the access verification and anti-passback verification on the first pass request are successful, allowing the passing for the first pass request, wherein the access verification is different from the anti-passback verification, and the anti-passback verification is: when it is determined that the anti-passback function takes effect, determining whether the first pass request follows an anti-passback rule.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhao, Shulei
Abrégé
A user service request assigning method, apparatus and system, and a device. The method comprises: determining, by means of a work order management end, estimated processing time of a user service request to be assigned; then determining a target technical service center which is in working time at the estimated processing time from among a plurality of technical service centers arranged in different time zones, the working time of each technical service center being within a preset time period of the time zone to which the technical service center belongs; and finally, assigning the user service request to the target technical service center for processing. A plurality of technical service centers arranged in different time zones collaboratively serve users, so that manual technical services are provided for the users in more time periods. Compared with conventional robot services which can only complete simple services, the technical service centers in the present application can provide more professional manual technical services for users in more time periods, and the service quality and the solving efficiency of service requests are improved.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
20.
VIDEO PROCESSING DEVICE, PROGRESS BAR TIME UPDATING METHOD, APPARATUS, AND ELECTRONIC DEVICE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Junjie
Zhang, Zhen
Abrégé
Disclosed in the present application are a video processing device, a progress bar time updating method, an apparatus, and a storage medium. The video processing device is used for: in response to receiving a playback instruction, acquiring a program stream assigned by the playback instruction, the program stream being obtained by performing program stream packaging on an encoded video stream of shot original video data; decoding the program stream to obtain a decoded video stream, the decoded video stream comprising one or more video sequences, and each video sequence comprising a key frame and at least one target frame associated with the key frame; for any target video sequence among the one or more video sequences, determining the absolute time of the target frame on the basis of the absolute time of the key frame and the time interval between the key frame and the target frame, the absolute time being the actual recording time of the video picture corresponding to the video frame; and by means of the absolute time of the key frame and the absolute time of the target frame, determining the current playing time displayed on the playback progress bar when the decoded video stream is played back.
H04N 21/472 - Interface pour utilisateurs finaux pour la requête de contenu, de données additionnelles ou de services; Interface pour utilisateurs finaux pour l'interaction avec le contenu, p.ex. pour la réservation de contenu ou la mise en place de rappels, pour la requête de notification d'événement ou pour la transformation de contenus affichés
H04N 21/845 - Structuration du contenu, p.ex. décomposition du contenu en segments temporels
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Song, Xin
Gao, Yingtong
Feng, Wei
Rao, Dongwei
Liu, Huafeng
Weng, Kejie
Ye, Jun
Ding, Shaojie
Mi, Shihao
Abrégé
A gate (100), comprising a box, one side of a plane where the box is located being a passage space, the passage space being used for allowing a passing object to pass, the box comprising a box housing, and the box housing being configured to accommodate a machine core assembly; a top cover (30), covering the upper end of the box; and a door baffle, capable of moving under the driving of a control assembly to control the passage of a target. The machine core assembly comprises the control assembly. The machine core assembly further comprises a camera assembly (1), and the camera assembly comprises a camera. The camera is arranged towards an inlet direction of the passage space, is arranged at a position lower than a plane where the top cover (30) is located, and is configured to obtain an image of the passing object. The machine core assembly further comprises a light supplementing lamp (2), and the light supplementing lamp (2) emits supplemental light toward the inlet direction of the passage space, and is arranged at a position lower than the plane where the top cover (30) is located. The field of view of the camera and the light supplementing range of the light supplementing lamp (2) at least overlap at an entrance of the passage space.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Ma, Qiang
Gao, Zaiwei
Abrégé
The present application provides an image processing method and apparatus, and a device. The method comprises: dividing all P frames in a GOP sequence into at least two types of P frames, the at least two types of P frames comprising P frames that cannot be used as reference frames and P frames that can be used as reference frames; and if it is determined that the P frames in the GOP sequence need to be subjected to step printing, performing step printing on the P frames that cannot be used as reference frames, or if it is determined that the P frames in the GOP sequence need to be subjected to step printing, performing step printing on the P frames that cannot be used as reference frames and the P frames that can be used as reference frames. By means of the technical solution of the present application, frame dropping can be performed according to a certain rule, such that a video frame sequence can be ensured to be played in order, and some P frames can also be dropped in some special scenarios to save bandwidth.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Yi, Yinglin
Zhu, Kunpeng
Ma, Qiang
Abrégé
Embodiments of the present application provide a coding and decoding resource allocation method and apparatus, and an electronic device. The method comprises: first, obtaining a first-type operation for a media stream to be processed; then determining a target protocol, a target resolution, and a target frame rate corresponding to the first-type operation; according to the target protocol, the target resolution, and the target frame rate, determining the quantity of coding and decoding resources to be consumed by the first-type operation, to obtain an allocation quantity; under the condition that the quantity of currently-idle coding and decoding resources is not smaller than the allocation quantity, allocating, from the currently-idle coding and decoding resources, coding and decoding resources of the allocation quantity to said media stream; and under the condition that the quantity of the currently-idle coding and decoding resources is smaller than the allocation quantity, generating prompt information indicating that the coding and decoding resources are insufficient. Corresponding coding and decoding resources are determined by combining the target protocol, the resolution, and the frame rate, so that resource calculation errors can be reduced, and reasonable control and allocation of the coding and decoding resources is realized.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Jian
Zhang, Shujun
Abrégé
A photographic device, which comprises a gimbal assembly, a camera assembly and an antenna assembly, wherein the camera assembly is arranged on the gimbal assembly, and comprises a housing and a camera core arranged in the housing; the antenna assembly comprises an antenna support, an antenna group and electrical connectors; the antenna support is arranged on the housing; the antenna group comprises a plurality of antennas fixed to the antenna support; and the antennas are all electrically connected to the electrical connectors, which are also electrically connected to the camera core.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pan, Dongping
Sun, Yucheng
Chen, Fangdong
Wei, Liang
Abrégé
The present application relates to the field of video encoding and decoding. Provided are an image encoding method and apparatus, and an image decoding method and apparatus, which can be used for avoiding the overflow of a code stream. The image decoding method specifically comprises: on the basis of a code stream of a block to be decoded, determining whether an image block corresponding to the block to be decoded uses a fallback mode, wherein the code length of the block to be decoded of the image block is less than or equal to the maximum code length of the block to be decoded, the maximum code length being the maximum code stream length which is allowed to be cached in a code stream buffer; when the image block corresponding to the block to be decoded uses the fallback mode, acquiring a first fixed code length, wherein the first fixed code length is the code length of a sub-block to be decoded, and the block to be decoded comprises one or more sub-blocks to be decoded; and parsing the code stream on the basis of the first fixed code length, so as to decode the block to be decoded.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Yan
Sun, Yucheng
Chen, Fangdong
Abrégé
Embodiments of the present application relate to the technical field of video decoding, and provide a video decoding method and apparatus and a storage medium, which are beneficial to improving the decoding efficiency. The method comprises: acquiring complexity information of a current block in an image to be processed, wherein the complexity information of the current block is obtained by calculating at least one angular gradient of the current block according to at least pixel values of the current block; determining quantization parameters of the current block according to the complexity information of the current block; and decoding the current block on the basis of the quantization parameters.
H04N 19/176 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p.ex. un objet la zone étant un bloc, p.ex. un macrobloc
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Bu, Xuegang
Lu, Lingfeng
Yu, Xuehai
Li, Yang
Yan, Caisheng
Abrégé
A camera, comprising a T-shaped camera body, a base assembly, a first lens assembly and a second lens assembly. The T-shaped camera body comprises a horizontal portion and a vertical portion; the base assembly supports the vertical portion; a first horizontal transmission assembly and a second horizontal transmission assembly are symmetrically arranged in a cavity of the horizontal portion; under the horizontal transmission force of the first horizontal transmission assembly, the first lens assembly rotates relative to the camera body parallel to the axis of the vertical portion; and under the horizontal transmission force of the second horizontal transmission assembly, the second lens assembly rotates relative to the body parallel to the axis of the vertical portion. A first lens and a first vertical transmission assembly are arranged inside a first lens housing. A second lens and a second vertical transmission assembly are arranged inside a second lens housing. Under the vertical transmission force of the first vertical transmission assembly, the first lens pitches relative to the first lens housing and the T-shaped camera body; and under the vertical transmission force of the second vertical transmission assembly, the second lens pitches relative to the second lens housing and the T-shaped camera body.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Gong, Hehe
Abrégé
The present application discloses an algorithm model running processing method and apparatus, and an intelligent edge device. The method comprises: obtaining at least one algorithm model, wherein the algorithm model is an artificial intelligence algorithm model; obtaining a plurality of virtual engines, wherein the virtual engines are virtualized engines obtained after performing software packaging on a physical engine; respectively binding each algorithm model in the at least one algorithm model to one virtual engine, wherein one virtual engine is used for binding one algorithm model; and receiving a task, and executing the task on the virtual engine on the basis of the algorithm model. According to the present application, simultaneous running of multiple algorithm models can be realized on the intelligent edge device, and the requirements of low cost and a fusion analysis of multiple algorithm models are met.
G06F 9/455 - Dispositions pour exécuter des programmes spécifiques Émulation; Interprétation; Simulation de logiciel, p.ex. virtualisation ou émulation des moteurs d’exécution d’applications ou de systèmes d’exploitation
29.
CAMERA ELECTRIC MOTOR DRIVING METHOD BASED ON TRM SENSOR
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Ren, Jian
Gong, Qi
Ma, Weimin
Abrégé
The present application relates to the technical field of security monitoring and camera lenses. Disclosed is a camera electric motor driving method based on a TRM sensor, by means of which method a zooming operation and/or a focusing operation of an optical camera lens can be implemented in a short time. The method comprises: acquiring a first parameter value, at a first moment, of a target electrical signal which is generated by a TMR sensor, wherein the first parameter value is used for representing a ratio between two-phase signals of the target electrical signal; determining a target angle of the target electrical signal at the first moment according to the correlation between a plurality of first parameter values of the target electrical signal and a plurality of angles of the target electrical signal in a single cycle, and the first parameter value of the target electrical signal at the first moment, wherein the first parameter values correspond to the angles on a one-to-one basis; determining the current position of a lens group at the current moment at least on the basis of the target angle; generating a driving signal on the basis of the current position of the lens group and a target position of the lens group; and driving a voice coil electric motor by using the driving signal, such that the lens group is adjusted from the current position to the target position.
G02B 7/10 - Montures, moyens de réglage ou raccords étanches à la lumière pour éléments optiques pour lentilles avec mécanisme de mise au point ou pour faire varier le grossissement par déplacement axial relatif de plusieurs lentilles, p.ex. lentilles d'objectif à distance focale variable
G02B 7/28 - Systèmes pour la génération automatique de signaux de mise au point
G02B 7/04 - Montures, moyens de réglage ou raccords étanches à la lumière pour éléments optiques pour lentilles avec mécanisme de mise au point ou pour faire varier le grossissement
H04N 23/67 - Commande de la mise au point basée sur les signaux électroniques du capteur d'image
30.
DECODING METHOD AND APPARATUS, ENCODING METHOD AND APPARATUS, AND DEVICES THEREFOR
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Sun, Yucheng
Cao, Xiaoqiang
Chen, Fangdong
Abrégé
The invention provides a decoding method and apparatus, an encoding method and apparatus, and devices therefor. The decoding method comprises: on the basis of feature information corresponding to a current image region, determining whether reconstruction value adjustment is required for said region; if it is determined that reconstruction value adjustment is required for said region, then obtaining from a bit stream corresponding to said region an adjustment parameter corresponding to said region; and adjusting a reconstruction value of said region on the basis of the adjustment parameter. The present invention allows for improved coding and decoding performance.
H04N 19/102 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’élément, le paramètre ou la sélection affectés ou contrôlés par le codage adaptatif
31.
COMMUNICATION METHOD, APPARATUS AND SYSTEM, TERMINAL, AND SERVER
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pu, Yina
Abrégé
Embodiments of the present application provide a communication method, apparatus and system, a terminal, and a server. The method is applied to the terminal, and a client and a local service process runs at the terminal. The method comprises: after passing login authentication of the server, the client sends a session authentication information request to the server, such that the server returns first session authentication information after the local service process passes the authentication; and the local service process communicates with the server on the basis of the first session authentication information and a token maintained by the local service process. When the local service process communicates with the server each time, the local service process does not need to obtain the token from the client each time, but communicates with the server on the basis of the first session authentication information and the token maintained by the local service process, such that the communication efficiency can be improved.
H04L 9/32 - Dispositions pour les communications secrètes ou protégées; Protocoles réseaux de sécurité comprenant des moyens pour vérifier l'identité ou l'autorisation d'un utilisateur du système
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Fan, Xunfeng
Jiang, Qingping
Abrégé
A course information recognition method, system and apparatus. The method comprises: performing bell recognition on each bell among a plurality of collected bells, so as to recognize whether each bell is a class start bell or a class end bell (101); and determining a class attending time period according to a bell recognition result, and determining course information corresponding to the class attending time period according to a facial recognition result of a teacher who is giving a lesson in a classroom within the class attending time period (102). In the method, bell recognition is combined with facial recognition, such that course information corresponding to a class attending time period can be dynamically recognized, and a class schedule applicable to an educational administration management system can be quickly and intelligently generated.
G06F 40/183 - Tabulation, c. à d. positionnement unidimensionnel
G10L 25/51 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation
33.
IMAGE CODING METHOD AND APPARATUS, IMAGE DECODING METHOD AND APPARATUS, AND ELECTRONIC DEVICE AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Fangdong
Wei, Liang
Abrégé
An image coding method and apparatus, an image decoding method and apparatus, and an electronic device and a storage medium, which relate to the technical field of image coding and decoding. The image coding method comprises: determining a target prediction mode of a block to be coded, and determining a target prediction sequence corresponding to the target prediction mode (S101); according to the target prediction mode, predicting, according to the target prediction sequence, each pixel in the block to be coded (S102); on the basis of a predicted value of each pixel, determining a residual block of the block to be coded (S103); and coding the residual block according to the target prediction sequence, so as to obtain a code stream of the block to be coded. By means of the method, the efficiency of image coding can be improved.
H04N 19/13 - Codage entropique adaptatif, p.ex. codage adaptatif à longueur variable [CALV] ou codage arithmétique binaire adaptatif en fonction du contexte [CABAC]
34.
METHOD, SYSTEM AND DEVICE FOR PROCESSING APPLICATION OPERATION LICENSING
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Xiaoqi
Abrégé
The present application discloses a method, system and device for processing application operation licensing. The method comprises: obtaining license information of a target application, wherein the license information comprises two dimensions, the first dimension of the two dimensions is used for limiting the capability of the target application to analyze multimedia, and the second dimension is used for indicating a total duration that the target application is licensed; determining, according to the two dimensions of the license information, whether the target application exceeds limits in the license information; if the limits in the license information are not exceeded, accumulating the use of the target application; and if the limits in the license information are exceeded, limiting the operation of the target application according to a predefined rule. The present application solves the problem in the prior art caused by performing licensing using natural time, such that the flexibility of licensing is improved, and licensing can be finely performed.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Cao, Xiaoqiang
Sun, Yucheng
Chen, Fangdong
Wang, Li
Abrégé
The present application provides encoding and decoding methods and apparatuses, and devices therefor. According to one example of the decoding method, an image to be processed can be divided into X*Y stripes, and the number Z of code stream fragments in each stripe is determined; then, for each of Y stripe rows corresponding to the image to be processed: code stream fragments corresponding to X stripes in the horizontal direction of the stripe row in a target code stream are de-interleaved to obtain Z code stream fragments corresponding to each of the X stripes, at least code stream fragments of two sizes existing in the Z code stream fragments; and the X stripes are decoded on the basis of bitstream buffer areas corresponding to the X stripes in the horizontal direction of the stripe row, wherein a bitstream buffer area corresponding to each stripe comprises a code stream fragment corresponding to the stripe.
H04N 19/426 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques - caractérisés par les détails de mise en œuvre ou le matériel spécialement adapté à la compression ou à la décompression vidéo, p.ex. la mise en œuvre de logiciels spécialisés caractérisés par les dispositions des mémoires utilisant des procédés de diminution de taille de mémoire
H04N 19/119 - Aspects de subdivision adaptative, p.ex. subdivision d’une image en blocs de codage rectangulaires ou non
36.
AUTONOMOUS LEARNING METHOD AND APPARATUS, AND ELECTRONIC DEVICE AND MACHINE-READABLE STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Jin
Abrégé
Provided in the present application are an autonomous learning method and apparatus, and an electronic device and a machine-readable storage medium. The method comprises: when it is determined that an autonomous learning trigger condition is met, collecting the current training data; according to the current training data, a high-value historical sample and acquired labeled data, performing online training on a first model, so as to obtain a second model; and updating the first model according to the second model. By using the method, continuous evolution of a model can be realized, and the forgetting of the model in terms of old knowledge is effectively alleviated while guaranteeing the processing performance of the model for new data.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wei, Liang
Chen, Fangdong
Wang, Li
Abrégé
Embodiments of the present application relate to the field of video coding and decoding, and provide an image decoding method, an image coding method, and corresponding devices. According to one example of the image decoding method, a quantization parameter (QP) value of a pixel point is determined for any pixel point in the current coding block or any plurality of parallel dequantized pixel points, the QP values of at least two pixel points among the pixel points in the current coding block being different; the pixel point is then dequantized according to the QP value of the pixel point. The QP value of each pixel point is determined for the coding block; therefore, each pixel point can be dequantized according to the QP value of each pixel point.
H04N 19/40 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le transcodage vidéo, c. à d. le décodage partiel ou complet d’un flux d’entrée codé suivi par un ré-encodage du flux de sortie décodé
H04N 19/182 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant un pixel
38.
COEFFICIENT DECODING METHOD AND APPARATUS, AND IMAGE DECODER AND ELECTRONIC DEVICE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pan, Dongping
Sun, Yucheng
Cao, Xiaoqiang
Chen, Fangdong
Abrégé
The embodiments of the present application relate to the field of image coding and decoding. Provided are a coefficient decoding method and apparatus, and an image decoder and an electronic device, which can improve the image decoding performance. The method comprises: parsing a code stream, so as to obtain coefficient group information of a unit to be decoded, wherein coefficients of said unit are divided into at least one coefficient group, each coefficient group comprises at least one coefficient code, the coefficient codes in the same coefficient group are fixed-length codes having the same coding length, the at least one coefficient group comprises a first coefficient group, and the coefficient group information comprises a boundary symbol of the first coefficient group; parsing the coefficient code of the first coefficient group into a coefficient value; and according to the boundary symbol, determining that the coefficient value in the first coefficient group is a positive value or a negative value.
H04N 19/18 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant un ensemble de coefficients de transformée
H04N 19/645 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant un codage par transformée utilisant une transformée en sous-bandes, p.ex. ondelettes caractérisé par l’ordonnancement des coefficients ou des bits à transmettre par regroupement de coefficients en blocs après la transformée
39.
VIDEO DECODING METHOD AND APPARATUS, VIDEO DECODER AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Yan
Chen, Fangdong
Cao, Xiaoqiang
Sun, Yucheng
Abrégé
Embodiments of the present application provide a video decoding method and apparatus, a video decoder and a storage medium, relate to the technical field of video decoding, and are beneficial to saving resources in code streams and improving the transmission efficiency of the code streams. The method comprises: obtaining one or more code rate control parameters of a current block in an image to be decoded; determining a quantization parameter of the current block according to the one or more code rate control parameters; and decoding the current block on the basis of the quantization parameter of the current block.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Fangdong
Pan, Dongping
Abrégé
The present application provides an image coding and decoding method and apparatus, and a storage medium, relates to the technical field of image coding and decoding, and is beneficial to improving the coding and decoding efficiency. An image decoding method comprises: parsing a code stream to obtain a first syntax element, the first syntax element comprising an index of a target prediction mode of a unit to be decoded; determining the target prediction mode from an index table on the basis of the index of the target prediction mode, wherein the index table comprises correspondences between indexes of a plurality of prediction modes and the plurality of prediction modes; and reconstructing said unit at least on the basis of the target prediction mode to obtain a reconstruction block.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Xu, Haidong
Xu, Guobin
Li, Xuanjiao
Abrégé
An intrusion detector, comprising: a housing (100); a supporting frame (110) provided in the housing (100) and comprising a fixed portion (111) and a movable portion (112), the fixed portion (111) being connected to the movable portion (112), and the movable portion (112) rotating relative to the fixed portion (111); a detector body (300) provided on the movable portion (112); and an anti-shielding assembly (200) comprising a transmitter (210) and a receiver (220), the transmitter (210) being configured to transmit a detection signal used for detecting a shielding object, the receiver (220) being configured to receive a reflection signal formed by the reflection of the detection signal by the shielding object, and the transmitter (210) being provided on the movable portion (112).
G08B 13/19 - Déclenchement influencé par la chaleur, la lumière, ou les radiations de longueur d'onde plus courte; Déclenchement par introduction de sources de chaleur, de lumière, ou de radiations de longueur d'onde plus courte utilisant des systèmes détecteurs de radiations passifs utilisant des systèmes détecteurs de radiations infrarouges
42.
VIDEO TRANSCODING AND VIDEO DISPLAY METHOD, APPARATUS, AND ELECTRONIC DEVICE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Hou
Abrégé
Embodiments of the present application provide a video transcoding and video display method, apparatus, and electronic device, and relate to the technical field of video processing. The video transcoding method comprises: acquiring a first image in an initial image obtained by splicing multiple paths of video images; determining an initial resolution of each initial sub-image; wherein each initial resolution is not greater than the maximum resolution of input data that can be supported by a preset encoder, and the target resolution of a target sub-image after transcoding of each initial sub-image is not greater than the maximum resolution of the output data that can be supported by the preset encoder; on the basis of each initial resolution, segmenting an image to be cut into initial sub-images; using a preset encoder to encode the initial sub-image according to the target resolution of the target sub-image after transcoding of each initial sub-image so as to obtain each target code stream. In comparison with the prior art, applying the solution provided by embodiments of the present application achieves transcoding of a video picture after a multi-channel video picture is spliced.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Yu, Xiang
Huang, Fanfu
Chen, Zhe
Abrégé
Disclosed in the embodiments of the present application are image display methods, apparatuses and system and a device. In the present application, a server device may generate a first image corresponding to a non-hidden region in an original image and a second image corresponding to a hidden region in the original image, and encrypt second coded data, which is obtained after encoding the second image, to obtain third encoded data, so that privacy information is prevented from being leaked in a transmission process of the second image. Then, when a client device receives first coded data obtained after encoding the first image, and the third coded data, the first coded data may be directly decoded to obtain the first image, so that even if the client device does not support hidden region display, normal display of the first image may be ensured; and if the client device is allowed to display the hidden region in the original image, the client device may obtain the second image according to the third coded data, generate the original image one the basis of the first image and the second image, and display the original image.
H04N 19/17 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p.ex. un objet
44.
TRAINING METHOD AND APPARATUS FOR FACE RECOGNITION MODEL, ELECTRONIC DEVICE AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Shuo
Abrégé
Embodiments of the present application provide a training method and apparatus for a face recognition model, an electronic device and a storage medium. The method comprises: acquiring source domain face features and an initialization recognition model; acquiring target face image samples of a target domain; and on the basis of the target face image samples and the source domain face features, adjusting a portion of model parameters of the initialization recognition model until the initialization recognition model converges so as to obtain a face recognition model for a source domain and target domain. Once an initialization model is trained by using the full quantity of face image samples of the source domain, a portion of the source domain face features are stored, and a portion of the parameters of the initialization model are fixed. Further, once the initialization model is further trained by using the target face image samples of the target domain and the source domain face features, a face recognition model for the source domain and the target domain is obtained. Not only is the recognition capabilities of the full quantity of face images of the source domain maintained, but target face images of the target domain may also be accurately recognized, thereby improving the recognition capabilities and accuracy of the face recognition model.
G06V 40/16 - Visages humains, p.ex. parties du visage, croquis ou expressions
G06V 10/774 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p.ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]; Séparation aveugle de source méthodes de Bootstrap, p.ex. "bagging” ou “boosting”
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Yang, Xichao
Zhang, Yuan
Xie, Di
Pu, Shiliang
Abrégé
The embodiments of the present application provide a data processing method, a network training method, an electronic device, and a storage medium. The method comprises: acquiring input data of a network layer of a deep neural network, wherein an original weight of the network layer is decomposed into N sub-weights for quantization processing; performing convolution processing on the input data and each of the N sub-weights, so as to obtain N pieces of intermediate data corresponding to the N sub-weights; and summing the N pieces of intermediate data, so as to obtain output data of the network layer. In this way, by means of decomposing an original weight of a network layer into N sub-weights for quantization processing, and adjusting the value of N, the efficiency and performance of a network can be flexibly balanced.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Rudan
Zhang, Yuan
Xie, Di
Pu, Shiliang
Abrégé
Embodiments of the present application provide a data processing method and apparatus and an edge computing device. The method comprises: quantizing first input data of a neural network to obtain second input data; determining first output data of the neural network according to the second input data and quantization parameters of all forward calculation parameters of each network layer in the neural network; quantizing the first output data to obtain second output data; when the neural network is trained, inputting the second output data into a preset loss function to obtain a first reverse gradient; quantizing the first reverse gradient to obtain a second reverse gradient; and adjusting the forward calculation parameters in the neural network according to the second reverse gradient and quantization parameters of all reverse calculation parameters of each network layer in the neural network. By applying the technical solution provided in the embodiments of the present application, the amount of calculations of a neural network can be reduced, and application scenarios of the neural network can be expanded.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Leilei
Abrégé
Disclosed is a dust removal camera. The dust removal camera comprises: a housing assembly (3), upon which a lens assembly (4) is mounted; a lower cover assembly (2), which is mounted to the housing assembly (3) and has a transparent window (22), the lens assembly (4) acquiring image information by means of said transparent window (22); and a wiper assembly (1), which is mounted to the housing assembly (3) and has a wiper strip (11); wherein the transparent window (22) and the wiper strip (11) are configured to rotate relative to each other, and a surface of the transparent window (22) is cleaned by means of the wiper strip (11) sweeping across the surface of the transparent window (22).
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Bin
Zhou, Shaopeng
Wang, Xu
Zhang, Feng
Bi, Zhicheng
Wan, Li
Li, Jun
Wang, Chonghua
Zhao, Haitao
Abrégé
The present application provides a traffic proxy-based Internet of Things terminal key information leakage monitoring method and system, an electronic device, a storage medium, and a computer program. The method comprises: receiving a proxy request sent by an Internet of Things terminal, wherein the proxy request comprises protocol related information of the Internet of Things terminal, and the protocol related information comprises part or all of device model information, service type information, and data packet information; according to the protocol related information of the Internet of Things terminal, determining a target protocol corresponding to the Internet of Things terminal; and allocating a target proxy service to the Internet of Things terminal according to the target protocol, and a usage state and an online state of each proxy service in a full traffic proxy pool, and performing key information monitoring on the traffic of the Internet of Things terminal by means of the target proxy service.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Shengguo
Wang, Cong
Abrégé
A turnstile synchronous control system (100), comprising: a first turnstile, the first turnstile comprising a first motor control system (10), a first motor, and a first gate (50), and the first motor control system (10) being used for controlling the first gate (50) by means of the first motor; and a second turnstile, the second turnstile comprising a second motor control system (20), a second motor, and a second gate (60), and the second motor control system (20) being used for controlling the second gate (60) by means of the second motor. The first motor control system (10) is connected to the second motor control system (20) by means of a bus; and the first motor control system (10) is used for obtaining the turnstile information of the second turnstile by means of the bus, and controlling the first turnstile according to the turnstile information of the second turnstile, so that the target position of the first motor is consistent with the target position of the second motor.
G05B 19/042 - Commande à programme autre que la commande numérique, c.à d. dans des automatismes à séquence ou dans des automates à logique utilisant des processeurs numériques
50.
AUTOMATIC OBJECT ANNOTATION METHOD AND APPARATUS, ELECTRONIC DEVICE AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Shui, Guozhi
Zhong, Chuanqi
Li, Yang
Abrégé
An automatic object annotation method and apparatus, an electronic device and a storage medium. The method comprises: obtaining a first image to be annotated which contains a marker and an object to be annotated; performing marker recognition on the first image to be annotated so as to obtain target marker information; determining a target three-dimensional model corresponding to the target marker information according to a correspondence relationship between the preset marker information and the three-dimensional model of the object; detecting the first image to be annotated on the basis of the target three-dimensional model so as to determine the position information of the object to be annotated in the first image to be annotated; and annotating the object to be annotated in the first image to be annotated according to the position information of the object to be annotated in the first image to be annotated. The automatic annotation of the object is realized, the annotation cost of the image can be reduced, and the annotation efficiency of the image can be improved.
G06V 10/44 - Extraction de caractéristiques locales par analyse des parties du motif, p.ex. par détection d’arêtes, de contours, de boucles, d’angles, de barres ou d’intersections; Analyse de connectivité, p.ex. de composantes connectées
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Guan, Hongjie
Tian, Wei
Xue, Kang
Abrégé
Provided in the present disclosure is a camera, comprising: a camera lens assembly comprising a camera lens, the camera lens comprising a lens arranged at the front end of the camera lens; and a mirror, the mirror and the camera lens assembly being arranged on a support in a first direction, the camera lens assembly being rotatably arranged on the support, the support having a second direction perpendicular to the first direction, and the mirror being rotatably arranged on the support by taking a first axis parallel to the second direction as an axis. The lens faces the mirror, and the mirror can rotate relative to the lens, so as to make at least some light reflected by the mirror incident on the lens.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Shui, Guozhi
Zhong, Chuanqi
Li, Yang
Abrégé
An object model establishment method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring a plurality of sample images, each of which is collected by an image collection device and includes markers and a target object, wherein in the plurality of sample images, the markers are provided at a plurality of key points of the target object; respectively determining the positions of the markers in the sample images; acquiring pose information when the image collection device collects each sample image; for each sample image, determining the position, in a world coordinate system, of the marker in the sample image according to the pose information when the image collection device collects the sample image, and the position of the marker in the sample image; and establishing a three-dimensional sparse point cloud model of the target object according to the positions, in the world coordinate system, of the markers in the sample images. Therefore, automatic modeling of an object model is realized, such that the modeling workload can be reduced; and the scale of model data is small, the making difficulty is low, and the present invention is particularly suitable for application in an actual scenario.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhu, Shuaishuai
Xiang, Kun
Qi, Fuqiang
Tian, Wei
Abrégé
Provided in the present disclosure are a camera mounting assembly and a camera. The camera mounting assembly comprises a mounting base and a mounting head, wherein the mounting base comprises a mounting cavity, a surrounding wall, and a plurality of pre-hanging connection members and a plurality of fasteners, which penetrate the surrounding wall, the plurality of pre-hanging connection members being fixed relative to the surrounding wall and extending into the mounting cavity, and the plurality of fasteners being movably arranged on the surrounding wall; the mounting head is inserted into the mounting cavity, and comprises a plurality of mounting slots, which correspond to the plurality of pre-hanging connection members on a one-to-one basis and fit with same, and a first groove body; the mounting slots extend in an insertion direction; each of the plurality of pre-hanging connection members enters the first groove body from the mounting slot corresponding to the pre-hanging connection member, and is connected to the mounting head in a hanging manner in the first groove body; and the plurality of fasteners can abut against the mounting head when extending into the mounting cavity, so that the mounting head is clamped and fixed in the mounting base. The camera comprises a camera body and the camera mounting assembly, and one of the mounting base and the mounting head is arranged at the top of the camera body.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Wenkai
Abrégé
An early-warning rule issuing method and apparatus, and an electronic device and a computer program product. The method comprises: displaying a background image, wherein the position of a radar and at least one defense area within an effective detection range of the radar are marked in the background image; acquiring the radius of a cutting line for the at least one defense area; dividing the at least one defense area in the background image into a plurality of defense sub-areas according to an arc cutting line, which is formed by taking the position of the radar as the center of a circle and taking the radius of the cutting line as a radius; setting an early-warning rule for at least one of the plurality of defense sub-areas; and issuing, to the radar, the position of the defense sub-area, for which the early-warning rule is set, and the corresponding early-warning rule, and thereby realizing the setting of an early-warning rule for the radar.
G08B 31/00 - Systèmes d'alarme à prédiction caractérisés par une extrapolation ou un autre type de calcul utilisant des données historiques mises à jour
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Lin, Yuhao
Yan, Caisheng
Ye, Zhan
Li, Junnan
Wang, Yangjian
Zhang, Hao
Zhou, Bin
Abrégé
Provided in the present disclosure are a camera, and a shell assembly of a camera. The camera comprises: a shell assembly, which is formed as a revolving body structure having a central axis and comprises an outer shell made of plastic and an inner shell made of thermally conductive plastic, the outer shell covering an outer side of the inner shell, an outer surface of the inner shell fitting with an inner surface of the outer shell, and the inner shell and the outer shell staying relatively fixed by means of a connecting structure; and a lens assembly, an electronic device and a heat dissipation metal plate, which are accommodated inside the shell assembly, with the optical axis of the lens assembly being in the same direction as the central axis, and the heat dissipation metal plate being connected to the electronic device and the inner shell for transferring the heat generated by the electronic device to the inner shell.
G03B 17/55 - APPAREILS OU DISPOSITIONS POUR PRENDRE DES PHOTOGRAPHIES, POUR LES PROJETER OU LES VISIONNER; APPAREILS OU DISPOSITIONS UTILISANT DES TECHNIQUES ANALOGUES UTILISANT D'AUTRES ONDES QUE DES ONDES OPTIQUES; LEURS ACCESSOIRES - Parties constitutives des appareils ou corps d'appareils; Leurs accessoires avec des dispositions pour chauffer ou réfrigérer, p.ex. avion
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Binbin
Chen, Weijie
Yang, Shicai
Abrégé
Provided in the present disclosure are a target detection method and apparatus. The method comprises: adding pseudo labels to label-free data, and classifying the pseudo labels into a high-quality pseudo label and an uncertain pseudo label; inputting the label-free data into an initial learning model to obtain first prediction values; on the basis of the first prediction value corresponding to the high-quality pseudo label, determining a first prediction label and a first prediction box, and on the basis of the first prediction value corresponding to the uncertain pseudo label, determining a second prediction label and a second prediction box; inputting the label-free data into an initial management model to obtain second prediction values, and on the basis of the second prediction value corresponding to the uncertain pseudo label, determining a third prediction label and a third prediction box; and on the basis of the first prediction label, the first prediction box, the second prediction label, the second prediction box, the third prediction label and the third prediction box, training the initial management model, so as to obtain a target management model, wherein the target management model is used for performing target detection on data to be subjected to detection.
G06F 30/27 - Optimisation, vérification ou simulation de l’objet conçu utilisant l’apprentissage automatique, p.ex. l’intelligence artificielle, les réseaux neuronaux, les machines à support de vecteur [MSV] ou l’apprentissage d’un modèle
57.
METHOD, APPARATUS AND DEVICE FOR DETECTING ABNORMAL VEHICLE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Qin
Ding, Lingde
Lou, Jianhao
Zhang, Hao
Chen, Zequn
Abrégé
Provided in the present application are a method, apparatus and device for detecting an abnormal vehicle. The method comprises: if a target vehicle travels from a first position point to a second position point, acquiring a first time point of when the target vehicle is at the first position point, a second time point of when the target vehicle is at the second position point, and the number of target position points, which are passed by the target vehicle when same travels from the first position point to the second position point; if the difference between the second time point and the first time point is less than the minimum duration for traveling from the first position point to the second position point, determining the target vehicle to be an abnormal vehicle; and if the difference between the second time point and the first time point is not less than the minimum traveling duration, and the minimum number of position points between the first position point and the second position point is greater than the sum of the number of target position points and a preset number threshold value, determining the target vehicle to be an abnormal vehicle.
G06V 20/62 - Texte, p.ex. plaques d’immatriculation, textes superposés ou légendes des images de télévision
G06V 10/764 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant la classification, p.ex. des objets vidéo
G06K 9/62 - Méthodes ou dispositions pour la reconnaissance utilisant des moyens électroniques
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pan, Dongping
Sun, Yucheng
Chen, Fangdong
Cao, Xiaoqiang
Wei, Liang
Abrégé
The present application relates to the technical field of image processing, provides a video encoding/decoding method and apparatus, and solves the problem in the prior art of low video encoding and decoding performance or high complexity of encoding and decoding algorithms. The method comprises: a decoding end obtaining a code stream of a unit to be decoded; determining a scanning mode and a grouping mode of said unit and an encoding mode corresponding to each group; decoding according to the encoding mode of each group to obtain a coefficient block corresponding to said unit; and according to the scanning mode of said unit, recovering coefficients in the coefficient blocks in each group one by one to obtain a reconstructed data block corresponding to said unit.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Cao, Xiaoqiang
Sun, Yucheng
Chen, Fangdong
Wang, Li
Abrégé
The present application relates to the technical field of video encoding and decoding, and discloses a video encoding and decoding method and apparatus, which are used for providing a new transformation method for current encoding and decoding technologies. The transformation method can improve the transformation flexibility. The use of the transformation method based on different dimensions can reduce the calculation complexity, reduce the calculation burden of a hardware device, reduce the hardware implementation complexity, and improve the compression performance. The decoding method comprises: performing entropy decoding and inverse quantization on a code stream to obtain an inverse transform unit; and performing discrete wavelet inverse transform on the inverse transform unit to obtain an inverse transform coefficient.
H04N 19/63 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant un codage par transformée utilisant une transformée en sous-bandes, p.ex. ondelettes
60.
IMAGE DECODING METHOD AND APPARATUS, AND IMAGE ENCODING METHOD AND APPARATUS
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Fangdong
Wang, Yan
Abrégé
The present application relates to the technical field of video encoding and decoding, and discloses an image decoding method and apparatus, and an image encoding method and apparatus, solving the problem of low prediction efficiency in the process of image encoding and decoding (or video encoding and decoding). The image decoding method comprises: parsing a bitstream to obtain a syntax element, the syntax element being used for obtaining a residual block of a unit to be decoded, and said unit comprising at least one prediction group; determining a prediction mode of any one of the at least one prediction group; predicting the any prediction group on the basis of the prediction mode to obtain a predicted value of the any prediction group; and decoding said unit on the basis of the residual block of said unit and the predicted value of the at least one prediction group.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Meng, Rang
Pu, Shiliang
Chen, Weijie
Yang, Shicai
Xie, Di
Abrégé
Provided in the present application are a method and apparatus for training an intelligent model, and an electronic device and a storage medium. The method comprises: acquiring, from a first neural network, a first network set which comprises a first neural network and m-1 second neural networks, and a second network set which comprises m second neural networks, wherein the m-1 second neural networks and the m second neural networks are different sub-networks in the first neural network; training each neural network in the first network set on the basis of a first sample set and a second sample set, so as to obtain a first model set, wherein the first model set comprises a first intelligent model, which is obtained by means of training the first neural network, and m-1 second intelligent models, which are obtained by means of training m-1 second neural networks; and training each neural network in the second network set on the basis of the first sample set, the second sample set and the first model set, so as to obtain a second model set, wherein the second model set comprises m second intelligent models, which are obtained by means of training the m second neural networks.
G06F 30/27 - Optimisation, vérification ou simulation de l’objet conçu utilisant l’apprentissage automatique, p.ex. l’intelligence artificielle, les réseaux neuronaux, les machines à support de vecteur [MSV] ou l’apprentissage d’un modèle
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wei, Liang
Chen, Fangdong
Wang, Li
Abrégé
An image decoding method, coding method and apparatuses, relating to the field of video coding and decoding. The decoding method comprises: first, parsing a code stream to obtain one or more image frames, wherein one image frame comprises one or a plurality of CUs; second, determining a plurality of QP values for the image frame, wherein a CU comprises a plurality of QGs, and one QG corresponds to one QP value; and finally, decoding the image frame on the basis of the plurality of QP values.
H04N 19/186 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c. à d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une couleur ou une composante de chrominance
63.
POSE DISPLAY METHOD AND APPARATUS, AND SYSTEM, SERVER AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Li, Jianing
Li, Jie
Mao, Hui
Pu, Shiliang
Abrégé
Provided are a pose display method and apparatus, and a system. The method comprises: during the process of a terminal device moving in a target scene, acquiring a target image of the target scene and motion data of the terminal device, and determining a self-positioning trajectory on the basis of the target image and the motion data (101); if the target image comprises a plurality of frames of images, the terminal device selecting, from the plurality of frames of image, some images as images to be subjected to detection, and sending said images and the self-positioning trajectory to a server (102); the server generating, on the basis of said images and the self-positioning trajectory, a fused positioning trajectory of the terminal device in a three-dimensional visual map, wherein the fused positioning trajectory comprises a plurality of fused positioning poses (103); and for each fused positioning pose, the server determining a target positioning pose corresponding to the fused positioning pose, and displaying the target positioning pose (104). In this way, a positioning function with a high frame rate and high precision is realized, and a terminal device only sends a self-positioning trajectory and images to be subjected to detection, thereby reducing the amount of data transmitted by a network, and reducing the computing resource consumption and storage resource consumption of the terminal device.
G01C 21/00 - Navigation; Instruments de navigation non prévus dans les groupes
G06V 10/80 - Fusion, c. à d. combinaison des données de diverses sources au niveau du capteur, du prétraitement, de l’extraction des caractéristiques ou de la classification
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Huang, Bijun
Fang, Zhiqiang
Yan, Caisheng
Abrégé
A video camera is provided. The video camera comprises a lens window; a gas nozzle comprising a gas nozzle chamber that defines a rectification gas chamber (38); a gas inlet (33) that is located on a gas intake side of the rectification gas chamber (38) and is in communication with the gas intake side of the rectification gas chamber (38), the cross section of the gas inlet (33) being circular; and a gas outlet (34) that is located on a gas discharge side of the rectification gas chamber (38) and is in communication with the gas discharge side of the rectification gas chamber (38). A 3D coordinate system is generated by the following means: the direction from the gas inlet (33) to the gas outlet (34) is the X direction, the length direction of the gas outlet (34) is the Y direction, and the direction perpendicular to the X direction and the Y direction is the Z direction. In the X direction, from the gas intake side to the gas discharge side, the size of the rectification gas chamber (38) in the Y direction gradually increases, and the size thereof in the Z direction gradually decreases. The video camera is configured as follows: gas flowing out from the gas discharge side is used to clean the lens window, thereby providing good cleaning capabilities for the lens window of the video camera.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Guo, Jietian
Abrégé
A sample image determination method and apparatus, a device, and a storage medium. The method comprises: performing a false negative/positive analysis on a video stream to determine a first image and a false negative/positive result corresponding to the first image, the first image being an image in which a false negative/positive object exists in the video stream, and the false negative/positive object being a target object of false negative analysis or a target object of false positive analysis; obtaining a plurality of foreground images and a plurality of background images from the video stream on the basis of the false negative/positive result corresponding to the first image; fusing the plurality of foreground images and the plurality of background images to obtain a plurality of second images; and determining the first image and the plurality of second images as sample images. In embodiments of the present application, a first neural network model is trained using these sample images, such that training effect of the first neural network model can be improved, thereby effectively improving analysis performance of the first neural network model.
G06V 20/40 - RECONNAISSANCE OU COMPRÉHENSION D’IMAGES OU DE VIDÉOS Éléments spécifiques à la scène dans le contenu vidéo
G06V 10/774 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p.ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]; Séparation aveugle de source méthodes de Bootstrap, p.ex. "bagging” ou “boosting”
G06V 10/80 - Fusion, c. à d. combinaison des données de diverses sources au niveau du capteur, du prétraitement, de l’extraction des caractéristiques ou de la classification
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
66.
METHOD AND APPARATUS FOR DETERMINING CAMERA PARAMETERS, ELECTRONIC DEVICE AND PROGRAM PRODUCT
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Liu, Chunhui
Chen, Junwei
Feng, Zhongjian
Abrégé
The embodiments of the present application relate to the technical field of computers, and provide a method and apparatus for determining camera parameters, an electronic device and a program product. The method comprises: obtaining a scene model used for simulating a target scene, and deploying a virtual camera in the scene model; according to virtual parameters of the virtual camera, simulating the virtual camera for deployment and control in the scene model so as to obtain a simulated monitoring image, wherein the virtual parameters comprise virtual deployment parameters and virtual configuration parameters; and when the simulated monitoring image meets monitoring requirements, determining that the virtual deployment parameters and/or virtual configuration parameters of the virtual camera are reference deployment parameters and/or reference configuration parameters of a camera to be deployed in the target scene. By applying the solution provided by the embodiments of the present application, the accuracy of determined camera parameters may be improved.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Hailong
Wang, Jun
Ma, Qiang
Abrégé
Disclosed in the embodiments of the present application are a video data encoding method and apparatus, and device. The method comprises: determining, on the basis of a first target bit rate corresponding to a first period, second target bit rates corresponding to a plurality of adjustment periods, wherein the first period comprises the plurality of adjustment periods, the first target bit rate is a constant value, and the second target bit rates corresponding to different adjustment periods are the same or different; for the current adjustment period among the plurality of adjustment periods, determining a target quantification parameter of the current adjustment period on the basis of a target quantification parameter range corresponding to the current adjustment period and the second target bit rate corresponding to the current adjustment period, wherein the target quantification parameter range is used for constraining the maximum quantification parameter value and the minimum quantification parameter value of the current adjustment period; and encoding video data on the basis of the target quantification parameter within the current adjustment period. By means of the embodiments of the present application, a bit rate can be adaptively controlled according to a scene, and a time when video recording is allowed can also be predicted in advance.
H04N 19/423 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques - caractérisés par les détails de mise en œuvre ou le matériel spécialement adapté à la compression ou à la décompression vidéo, p.ex. la mise en œuvre de logiciels spécialisés caractérisés par les dispositions des mémoires
68.
DIGITAL VIDEO RECORDER, AND METHOD FOR DETECTING COAXIAL AUDIO DATA
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Hailong
Wang, Jun
Ma, Qiang
Abrégé
The embodiments of the present application belong to the field of audio and video data transmission. Disclosed are a digital video recorder, and a method for detecting coaxial audio data. The method comprises: determining the signal system of a path of video signals; on the basis of the signal system, determining a coaxial audio modulation position; detecting voltages at the coaxial audio modulation position in M frames of video signals of the path of video signals, so as to obtain K voltages; and when the K voltages meet a coaxial audio condition, determining that the path of video signals contains coaxial audio data. In the embodiments of the present application, by means of determining that a video signal contains coaxial audio data, subsequent correct processing of the coaxial audio data is ensured, and subsequent normal playing of audio data is also ensured.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Tao, Wei
Zhou, Bin
Abrégé
Provided in the present disclosure are a water collection assembly for use in a camera, and a camera. The water collection assembly for use in a camera comprises a semiconductor refrigeration sheet, a water condensation member and a water tank, wherein after the semiconductor refrigeration sheet is electrified, a cold side and a hot side of different temperatures are formed thereon, with the cold side coming into direct or indirect contact with the water condensation member to transfer cold energy to the water condensation member, such that the temperature of the water condensation member is lower than the dew-point temperature of ambient air; and the water tank comprises a water inlet and a water outlet, the water inlet being arranged below the water condensation member for condensed water on the water condensation member to drip into.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wan, Xin
Abrégé
A directional antenna-based rotatable camera assembly, comprising: a video image acquisition device and an antenna assembly. The antenna assembly comprises a directional antenna, a motor, a wireless circuit, and a controller assembly. The motor is connected to the directional antenna and is used for driving the directional antenna to rotate, so that the directional antenna faces different directions; the wireless circuit is electrically connected to the directional antenna; the controller assembly is electrically connected to the wireless circuit and the motor, and is used for controlling the motor to rotate towards a direction in which a communication performance value reaches a first performance threshold; the video image acquisition device is connected to the wireless circuit; and when the directional antenna rotates to the direction of the first performance threshold, the video image acquisition device sends an acquired video image by means of the directional antenna.
H04N 7/18 - Systèmes de télévision en circuit fermé [CCTV], c. à d. systèmes dans lesquels le signal vidéo n'est pas diffusé
H01Q 3/02 - Dispositifs pour changer ou faire varier l'orientation ou la forme du diagramme de directivité des ondes rayonnées par une antenne ou un système d'antenne utilisant un mouvement mécanique de l'ensemble d'antenne ou du système d'antenne
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Huan
Abrégé
A camera for realizing cooperative anti-shake by using optical anti-shake and electronic anti-shake. On the basis of the present application, in any refresh cycle of an image sensor, it is possible that only part of a real-time spatial angle of the camera is offset by optical anti-shake within an optical anti-shake capability range of the camera, so as to facilitate a reduction in the risk of optical anti-shake failure. In addition, on the basis of the part of the spatial angle that is offset by optical anti-shake, it is also possible to reduce the risk of image definition being excessively low due to an excessively large spatial angle. Therefore, at a refresh moment when an imaging cycle ends, image processing is performed on an image, the definition of which has been improved by optical anti-shake, by means of electronic anti-shake, such that the influence of the remaining part of the real-time spatial angle of the camera on image quality can be compensated for. Thus, two modes are combined in such a way that electronic anti-shake compensates for optical anti-shake, thereby facilitating a reduction in the risk of anti-shake failure.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Zhan
Abrégé
An audio data processing method, apparatus and device. The method comprises: acquiring, in a noise reduction application scenario, audio data to be processed that has noise (201); determining an audio feature vector corresponding to the audio data to be processed (202); inputting the audio feature vector to a trained target vocoder model, and outputting from the target vocoder model target audio data corresponding to the audio feature vector, wherein the target audio data is audio data after noise reduction processing has been carried out on the noise of the audio data to be processed.
G10L 15/20 - Techniques de reconnaissance de la parole spécialement adaptées de par leur robustesse contre les perturbations environnantes, p.ex. en milieu bruyant ou reconnaissance de la parole émise dans une situation de stress
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhao, Xiuwei
Abrégé
A method for SMR hard disk-based RAID creation, relating to the technical field of data storage. The method for SMR hard disk-based RAID creation is applied to a preset RAID program, the creation method comprising: determining a plurality of SMR hard disks for creating RAIDs; configuring an SMR region of the plurality of SMR hard disks as a first array to be created, wherein the first array comprises a plurality of stripes, and each stripe comprises a write region with the same offset address in the SMR region of the plurality of SMR hard disks and is used for storing data files written in aligned order; and configuring a CMR region of the plurality of SMR hard disks as a second array to be created, wherein the first array and the second array are different RAIDs. Compared to the prior art, application of the present creation method enables a RAID to be created using an SMR hard disk without using another hard disk as a cache.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Xiang, Kun
Guan, Hongjie
Sun, Mingdong
Tian, Wei
Wu, Yingquan
Abrégé
A cable assembly (100), used for being assembled on a mounting base (10), comprising: a core wire (21) and an SR joint (20). The SR joint comprises an insertion portion (221) and a connection portion (222). The insertion portion (221) comprises a through insertion hole (2215), the core wire (21) passes through the insertion hole (2215), and both ends of the core wire (21) extend out of the insertion hole (2215). The core wire (21) and the insertion portion (221) are integrally arranged, and the connection portion (222) is disposed outside the insertion portion (221) and configured to be connected to the mounting base (10). The insertion portion (221) and the connection portion (222) are integrally arranged, and the material hardness of the connection portion (222) is greater than that of the insertion portion (221). Also disclosed is a camera (200), comprising a mounting base (10) and a cable assembly (100).
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Fang, Zhenhuan
Hao, Xianyi
Lei, Weijun
Zhao, Dongdong
Yang, Fan
Li, Ruiming
Qian, Yuhuan
Shen, Zihao
Gao, Liang
Wang, Nan
Qiu, Jingying
Abrégé
A method and apparatus for controlling a display screen, relating to the technical field of electronics. The method comprises: receiving target alarm information, the target alarm information being linked with an image collected by at least one monitoring point in real time (301); on the basis of display states of a plurality of display windows in the display screen, determining a target window in the plurality of display windows that supports display of the image linked with the target alarm information, the target window comprising at least one display window (302); controlling the display screen to display, in the target window, the image collected by the at least one monitoring point in real time (303). The method and apparatus solve the problems that a process for displaying images collected by monitoring points and linked with alarm information is complex, and the display flexibility is low; the method and apparatus are used for displaying the images collected by the monitoring points and linked with the alarm information.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Cao, Xiaoqiang
Chen, Fangdong
Wang, Li
Abrégé
The present application provides a decoding method and apparatus, a coding method and apparatus, a device, and a machine-readable storage medium. As an example of the decoding method, for a received code stream, by analyzing a motion information index value of a skip mode or a direct mode of a current encoding unit, a candidate list of the skip mode or the direct mode can be constructed, and a prediction mode of the current encoding unit can be determined, such that motion compensation can be performed on the current encoding unit according to motion information of the current encoding unit obtained from the prediction mode of the current encoding unit, wherein the motion information index value of a skip mode or a direct mode of a current encoding unit is obtained by analyzing the number of motion vector angle prediction candidate motion information and the number of inter-frame prediction candidate historical motion information.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Lei, Weijun
Abrégé
A display window creating method and apparatus, and an electronic device. The method comprises: determining an initial window area; determining at least one target virtual output area having an intersection with the initial window area from a plurality of virtual output areas corresponding to a plurality of divided physical output areas of a television wall, the plurality of physical output areas corresponding to output ports configured to transmit decoded video streams on a decoding device connected to the television wall; and adjusting the initial window area according to the distance between corresponding boundaries of the initial window area and a target virtual output area, and sending the adjusted initial window area to the television wall to control a target display window created by the television wall according to the adjusted initial window area not to generate a window black edge.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Li, Xuanjiao
Xu, Haidong
He, Shaohua
Lin, Weiwei
Abrégé
A passive optical detector, relating to the technical field of optical detection, and comprising a housing, and a lens array (110), a detection unit, and a reflection component (130) which are provided in the housing. The lens array (110) comprises a plurality of optical lenses, and the detection unit comprises a photoelectric sensor (120). The plurality of optical lenses are arranged into a convex arc-shaped structure, and a convex surface of the convex arc-shaped structure protrudes in a direction away from the photoelectric sensor (120); the photoelectric sensor (120) is located on a focal plane of the convex arc-shaped structure. The reflection component (130) is provided on the inner side of the convex surface of the lens array (110), and is close to a first edge region of a first end (111) of the lens array (110). The lens array (110) having the convex arc-shaped structure is combined with the photoelectric sensor (120) for use, so that a detection distance and a detection field angle of the passive optical detector can be ensured, and the applicability and a detection effect of the passive optical detector are improved.
G01J 5/10 - Pyrométrie des radiations, p.ex. thermométrie infrarouge ou optique en utilisant des détecteurs électriques de radiations
G01J 5/34 - Pyrométrie des radiations, p.ex. thermométrie infrarouge ou optique en utilisant des détecteurs électriques de radiations en utilisant des condensateurs, p.ex. des condensateurs pyroélectriques
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Yao, Xinli
Zhu, Yonghao
Zhu, Zhenfeng
Cai, Hong
Zhang, Shifeng
Mao, Hui
Pu, Shiliang
Xu, Peng
Abrégé
A system for measuring spectral reflectivity. The system comprises an ambient light sensing module (11), a target spectrum collection module (12) and a data processing module (13). The ambient light sensing module (11) collects measurement ambient light spectrums at a target measurement moment, and sends the measurement ambient light spectrums to the data processing module (13); the target spectrum collection module (12) collects measurement target spectrums at the target measurement moment, and sends the measurement target spectrums to the data processing module (13); and the data processing module (13) determines a measurement ambient light spectrum and a measurement target spectrum, which correspond to the same target wavelength, and determines a measurement reference spectrum on the basis of the measurement ambient light spectrum and a determined mapping parameter, wherein the measurement reference spectrum is a spectrum of second ambient light, and the data processing module (13) determines, on the basis of the measurement target spectrum and the measurement reference spectrum, the spectral reflectivity of an object to be measured, the mapping parameter representing the mapping relationship between a reference spectrum and the ambient light spectrum. Further disclosed is a method for measuring spectral reflectivity. By means of the system for measuring spectral reflectivity and the method for measuring spectral reflectivity, the spectral reflectivity of an object to be measured can be accurately calculated.
G01J 3/42 - Spectrométrie d'absorption; Spectrométrie à double faisceau; Spectrométrie par scintillement; Spectrométrie par réflexion
G01N 21/25 - Couleur; Propriétés spectrales, c. à d. comparaison de l'effet du matériau sur la lumière pour plusieurs longueurs d'ondes ou plusieurs bandes de longueurs d'ondes différentes
80.
DATA INTEGRITY PROCESSING METHOD AND APPARATUS, AND ELECTRONIC DEVICE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Tao, Duolei
Shen, Zhiming
Abrégé
The present application provides a data integrity processing method and apparatus, and an electronic device. The method comprises: receiving data reported by at least one device managed by a management platform; when it is determined that data integrity processing needs to be performed, determining, from the received data, data reported by a target device within a specified time period, and determining, on the basis of a data identifier of the data reported by the target device within the specified time period, target data that the management platform should receive but does not receive from the target device, the target device being any device in the at least one device; and obtaining the target data from the target device. By using the solution provided by the present application, the management platform can automatically check the data integrity.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Tang, Zheng
Zhang, Junli
Gao, Qitao
Abrégé
An information association method and apparatus, a security inspection device, and a storage medium. The method comprises: obtaining a monitoring image of an entrance of a security inspection device (S101); determining a package to be inspected and a target person to which said package belongs in the monitoring image (S102); determining, according to a placement position of said package on a conveyor belt of the security inspection device and the position of an inspection area of the security inspection device, a target X-ray image acquired by the security inspection device, wherein the target X-ray image comprises said package (S103); and establishing a correspondence among said package, the target person, and the target X-ray image (S104). Since the association process is directly performed by the security inspection device on the basis of the acquired monitoring image and X-ray image, the method does not need manual participation, such that a time required by manual association is saved, the possibility of errors in manual association in a scenario with relatively high human traffic or a relatively complex environment is reduced, and the accuracy of information association is improved.
G01V 5/00 - Prospection ou détection au moyen de radiations nucléaires, p.ex. de la radioactivité naturelle ou provoquée
G01N 23/04 - Recherche ou analyse des matériaux par l'utilisation de rayonnement [ondes ou particules], p.ex. rayons X ou neutrons, non couvertes par les groupes , ou en transmettant la radiation à travers le matériau et formant des images des matériaux
82.
BARRIER GATE CONTROL METHOD, APPARATUS AND SYSTEM, AND SERVER
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Tao, Duolei
Xie, Yangyang
Shen, Zhiming
Abrégé
A barrier gate control method, apparatus and system, and a server, relating to the technical field of computers. The method comprises: determining a configuration relationship between a barrier gate device and a first identification device (201); acquiring first permission information that the barrier gate device allows persons to pass through (202); determining second permission information and third permission information from the first permission information according to the configuration relationship (203); and configuring the second permission information in the first identification device, and configuring the third permission information in the barrier gate device (204). According to the method, the permission information can be configured for the barrier gate device and the first identification device as required according to the identification capabilities of the barrier gate device and the first identification device, thereby improving the issuing efficiency of the permission information.
G07C 9/25 - Enregistrement de l’entrée ou de la sortie d'une entité isolée comportant l’utilisation d’un laissez-passer combiné à une vérification d’identité du titulaire du laissez-passer utilisant des données biométriques, p.ex. des empreintes digitales, un balayage de l’iris ou une reconnaissance de la voix
G07C 9/27 - Enregistrement de l’entrée ou de la sortie d'une entité isolée comportant l’utilisation d’un laissez-passer une station centrale gérant l’enregistrement
83.
SYNCHRONOUS EXPOSURE PROCESSING METHOD, APPARATUS, SYSTEM, AND DEVICE
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhao, Can
He, Shengyuan
Wang, Liang
Abrégé
The present application provides a synchronous exposure processing method, apparatus, system, and a device. The method comprises: determining a frame rate and an intra-frame data row sequence of an image sensor, the data row sequence being used for describing a distribution condition of valid data rows in intra-frame data rows, and the image sensor being a rolling shutter exposure-type image sensor; determining a row period of exposure of the image sensor on the basis of the frame rate and the total number of data rows in the data row sequence; obtaining a control reference row serial number on the basis of the row period and the serial number of the first valid data row in the data row sequence and in combination with a preset maximum exposure duration of each row; and on the basis of the control reference row serial number, synchronously controlling the image sensor and a light supplement lamp thereof to execute an exposure operation. Hence, the objectives of saving power consumption of the light supplement lamp and lowering the heating cost of the device can be achieved by synchronously controlling effective exposure of the image sensor and on/off time of the light supplement lamp under rolling shutter-type exposure.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Tu, Zhenyuan
Wang, Qinyu
Yu, Zhongwei
Abrégé
Disclosed are a configuration determination method and apparatus for a neural network model, and a device and a storage medium. Prior information and universal general information are queried in a preset model cost evaluation table according to dimension information of target network layers and hardware instructions of target hardware, so as to obtain a preset configuration, which enables the clock cycle quantity of each target network layer to be minimum, that is, the configuration of each target network layer when the running clock cycle quantity of a target neural network model is the minimum, and an optimal configuration of the target neural network model in the target hardware is thus obtained, such that fast implementation of the neural network model in the target hardware can subsequently be realized by using the optimal configuration.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Bin
Chen, Si
Chen, Jiadong
Yao, Xiangzhen
Li, Lin
Huang, Jingjing
Abrégé
The present application provides a method, apparatus, and system for encrypting a video data slice, and an electronic device. The method comprises: a target encryption node acquiring a first key ID, and, according to the first key ID, acquiring a first protection key from a key management system; the target encryption node generating a first random number, and using the first random number as a first video key to encrypt a video data slice to be encrypted, and obtaining a first video ciphertext; the target encryption node encrypting the first video key by using the first protection key, and obtaining a first key ciphertext; and the target encryption node storing the first key ciphertext and the first key ID in the first video ciphertext. The present method can improve the security of video data slices.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Guan, Hongjie
Ye, Zhan
Sun, Mingdong
Tian, Wei
Qi, Fuqiang
Yu, Zhantao
Mao, Minxia
Yuan, Quan
Liu, Qiang
Wang, Mengmeng
Abrégé
Disclosed are a camera and a multi-view camera, which relate to the fields of monitoring and security and protection. The camera comprises a first lens assembly (100), a second lens assembly (200), and a top cover assembly (400). In an embodiment of a first aspect, the first lens assembly (100) comprises a first housing (110) and a first lens (120) arranged on the first housing (110), the first lens being capable of pitching and/or rotating horizontally. The second lens assembly (200) comprises a second housing (210), a plurality of lens supports (220) and a plurality of second lenses (230), wherein the second housing (210) comprises a plurality of side walls (212) extending radially from the middle of the second housing (210) to the edge; a plurality of accommodation spaces (213) having outward openings are formed by the plurality of side walls (212); and any one of the lens supports (220) is arranged in any one of the accommodation spaces (213). The top cover assembly (400) is connected to the second lens assembly (200), and the camera can be assembled in a hoisted manner; and the center of the second lens assembly (200) and the center of the top cover assembly (400) are coaxial.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Guan, Hongjie
Ye, Zhan
Yan, Caisheng
Abrégé
Embodiments of the present disclosure provide a camera and a camera assembly. The camera comprises: a motor assembly, an image sensor assembly, and a second support; one surface of the image sensor assembly is provided with an image sensor, and the other surface of the image sensor assembly opposite to the one surface has a longitudinal support arm extending in a first direction, wherein the first direction is perpendicular to the other surface of the image sensor assembly; the second support is defined to be adjacent to the other surface of the image sensor assembly; the motor assembly is fixedly connected to the second support, and has an output shaft extending in a third direction, and the motor assembly drives the output shaft to move in the first direction, wherein the third direction is perpendicular to the first direction; and the longitudinal support arm receives the output shaft, such that under the driving force of the output shaft, the longitudinal support arm can drive, in the first direction, the image sensor assembly to move in the first direction.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Junli
Tang, Zheng
Chen, Tao
Abrégé
The embodiments of the present application belong to the field of security supervision, and disclose an information association method, system and apparatus, and a server and a storage medium. The method comprises: detecting and tracking a target user by means of a first video collected by a binocular camera, and determining a user identifier of the target user, and three-dimensional coordinates of a body skeleton key point of the target user in a binocular camera coordinate system; determining a package placement moment and a visible light package image on the basis of the user identifier and the three-dimensional coordinates of the body skeleton key point in the binocular camera coordinate system; on the basis of the package placement moment, determining an X-ray package image of a package in an X-ray detection region by means of a security check machine; on the basis of the three-dimensional coordinates of the body skeleton key point in the binocular camera coordinate system, determining a facial image of the target user by means of a facial capture machine; and associating the visible light package image, the X-ray package image and the facial image. In the embodiments of the present application, information association can be realized by means of simple devices such as a binocular camera, a facial capture machine, a security check machine, etc., and a hardware environment is simply built.
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
G06T 7/80 - Analyse des images capturées pour déterminer les paramètres de caméra intrinsèques ou extrinsèques, c. à d. étalonnage de caméra
89.
DECODING METHOD AND APPARATUS, ENCODING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Cao, Xiaoqiang
Sun, Yucheng
Chen, Fangdong
Abrégé
The present application provides a decoding method and apparatus, an encoding method and apparatus, a device, and a storage medium. The decoding method comprises: obtaining the value of an enhanced temporal motion vector prediction mode flag bit of a current coding unit and an enhanced temporal motion vector prediction mode index value; and when the value of the enhanced temporal motion vector prediction mode flag bit is a first value: determining, according to coordinate information of the current coding unit, coordinate information of an initial matching coding unit of the current coding unit; constructing an enhanced temporal candidate list according to the coordinate information of the initial matching coding unit; determining coordinate information of a target matching coding unit according to the enhanced temporal motion vector prediction mode index value; and determining, according to the coordinate information of the target matching coding unit, motion information of sub-blocks at corresponding positions in the current coding unit. The present method can improve encoding and decoding performance.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wei, Liang
Chen, Fangdong
Wang, Li
Abrégé
Disclosed are a decoding method based on an adaptive intra-frame refreshing mechanism, an encoding method based on an adaptive intra-frame refresh mechanism, and a related device, which belong to the field of video encoding and decoding. In the embodiments of the present application, an adaptive intra-frame video refreshing extension number and virtual boundary location mark information are newly added to extended data in a code stream of the current frame. In this way, since virtual boundary location mark information can indicate the location of a virtual boundary, and the virtual boundary is at least used for distinguishing between a refreshed area and a non-refreshed area in the current frame, when dividing the refreshed area of the current frame, an encoding terminal can arbitrarily set the virtual boundary on the basis of actual demands, and indicate the location of the virtual boundary by means of the virtual boundary location mark information, thereby effectively improving the flexibility of area division.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Liu, Chao
Abrégé
A multispectral camera lens (1), a multispectral optical system (3) and a multispectral camera (2). The camera lens (1) comprises a housing (10), a first lens set (21), a second lens set (22) and an aperture assembly (30), wherein the housing (10) is in the shape of a cylinder having a hollow cavity; the first lens set (21) and the second lens set (22) are mounted in the hollow cavity, the first lens set (21) is mounted on an object-space side of the housing (10), and the second lens set (22) is mounted on an image-space side of the housing (10); and the aperture assembly (30) is mounted between the first lens set (21) and the second lens set (22), and after being transmitted through the first lens set (21), light rays pass through the aperture assembly (30) to reach the second lens set (22). The aperture assembly (30) comprises a first aperture used for transmitting light rays in a first wavelength range, and a second aperture used for transmitting light rays in a second wavelength range, wherein the first aperture and the second aperture are formed in the same plane, a wavelength in the first wavelength range is greater than a wavelength in the second wavelength range, and the area of the first aperture is smaller than the area of the second aperture.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhu, Haiyan
Abrégé
The present application provides an image processing method and apparatus, and a camera. The camera comprises a processing chip, an image sensor and an infrared fill light, wherein the processing chip is used for determining a turn-on time interval and a turn-off time interval corresponding to the infrared fill light, and the turn-on time interval and the turn-off time interval alternately appear; controlling the infrared fill light to fill a target scene in the turn-on time interval; controlling the image sensor to collect an infrared image of the target scene in the turn-on time interval, and controlling the image sensor to collect a color image of the target scene in the turn-off time interval, the infrared image being generated by the image sensor on the basis of infrared light when the infrared fill light fills the target scene, and the color image being generated by the image sensor on the basis of visible light when the infrared fill light does not fill the target scene; and performing image fusion on the infrared image and the color image. By means of the technical solution of the present application, the fill time is shortened, the power consumption is reduced, and the light pollution caused by long-time filling is reduced.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Pan, Dongping
Sun, Yucheng
Chen, Fangdong
Wang, Li
Abrégé
The present application provides a filtering method and apparatus, and a device. According to one example, the filtering method comprises: determining whether a current adaptive correction filtering unit allows the use of enhanced adaptive correction filtering; if it is determined that the current adaptive correction filtering unit allows the use of enhanced adaptive correction filtering, performing adaptive correction filtering on the current adaptive correction filtering unit by using the first filter; and if it is determined that the current adaptive correction filtering unit does not allow the use of the enhanced adaptive correction filtering, performing adaptive correction filtering on the current adaptive correction filtering unit by using the second filter. The first filter is a centrosymmetric filter in a shape of a 7*7 cross and a 5*5 square, and the second filter is a centrosymmetric filter in a shape of a 7*7 cross and a 5*5 square.
H04N 19/10 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif
H04N 19/635 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant un codage par transformée utilisant une transformée en sous-bandes, p.ex. ondelettes - caractérisé par la définition du filtre ou les détails de mise en œuvre
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Ye, Weiran
Abrégé
A doorbell camera. The doorbell camera comprises a power supply end, a mechanical doorbell, a camera circuit, a charging capacitor, and a control circuit. The power supply end is used for being connected to a power supply. The control circuit comprises a linked switch and a controller; the camera circuit, the charging capacitor, and the linked switch are connected in parallel to the power supply end; the mechanical doorbell and the linked switch are connected in series to the power supply end; and the controller is connected to the linked switch and used for controlling the on/off of the linked switch. When the linked switch is switched on, the power supply end is used for supplying power to the mechanical doorbell to make the mechanical doorbell sound, and the charging capacitor is used for supplying power to the camera circuit; and when the linked switch is switched off, the power supply end is used for charging the charging capacitor by means of the mechanical doorbell and supplying power to the camera circuit, and the mechanical doorbell does not make a sound.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Chen, Fangdong
Cao, Xiaoqiang
Sun, Yucheng
Abrégé
Provided are a coding and decoding method and apparatus, and devices therefor. The method may comprise: if the current pixel point in the current block meets an enabling condition for an enhanced adjustment mode, determining a gradient value of the current pixel point on the basis of an original pixel value of the current pixel point and original pixel values of surrounding pixel points of the current pixel point; and determining an adjustment pixel value of the current pixel point on the basis of the gradient value of the current pixel point and the original pixel value of the current pixel point. By means of the technical solution of the present application, the coding performance can be improved.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Yu, Gang
Zheng, Le
Abrégé
Disclosed in the present disclosure are a P-direction adjusting structure and a dome camera. The P-direction adjusting structure is applied to a dome camera, and comprises: an upper cover assembly, a pin bolt, a base, and a wire hiding box; the base is rotatably connected to the wire hiding box; the upper cover assembly is mounted on the base; the upper cover assembly is provided with an upward-pushing portion, and the upward-pushing portion can drive the pin bolt to switch between a release position and a locking position; when the pin bolt is switched to the locking position, the rotational degree of freedom of the base and the wire hiding box is locked; and when the pin bolt is switched to the release position, the locking is released. The P-direction adjusting structure of the present disclosure is simple in structure and easy to operate; as far as a P-direction locking operation, said operation is simple and can be implemented only by normally closing and fastening the upper cover, and no redundant operation is required.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zha, Wanghua
Xu, Zhuodong
Chen, Rao
Zhou, Zhiyang
Zhao, Liang
Abrégé
A camera. According to the present application, the touch assembly of the camera can detect a touch operation on a barrel wall of a housing, and can control a light supplementing assembly according to the detected touch operation, such that the luminescent brightness of the lamp beads surrounding the lens of an imaging assembly can be adjusted by means of the touch operation.
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Zhang, Jianliang
Abrégé
The present invention relates to the technical field of monitoring devices. Disclosed are a camera assembly and a silica gel ring. The camera assembly provided by the present invention comprises a camera cover, a heating sheet, a housing, and the silica gel ring; the camera cover is made of glass, and the shape is defined as a hemispherical shape of a first radius. The heating sheet is arranged on the inner side of the camera cover; a through hole is formed on the housing; the camera cover is fixed to the through hole by means of the silica gel ring. The present invention can solve the problems of poor water resistance and poor light transmission effect, etc. of a camera.
G03B 17/08 - Corps d'appareils ou boîtiers étanches à l'eau
G03B 17/55 - APPAREILS OU DISPOSITIONS POUR PRENDRE DES PHOTOGRAPHIES, POUR LES PROJETER OU LES VISIONNER; APPAREILS OU DISPOSITIONS UTILISANT DES TECHNIQUES ANALOGUES UTILISANT D'AUTRES ONDES QUE DES ONDES OPTIQUES; LEURS ACCESSOIRES - Parties constitutives des appareils ou corps d'appareils; Leurs accessoires avec des dispositions pour chauffer ou réfrigérer, p.ex. avion
99.
LIVING BODY FINGERPRINT DETECTION SYSTEM, METHOD AND APPARATUS
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Ren, Zhihao
Abrégé
A living body fingerprint detection system, method and apparatus. Said system comprises: a light source apparatus, a multi-spectrum apparatus, and a control unit; the light source apparatus is used for providing light of a plurality of different wavebands; the control unit is used for controlling the light source apparatus to emit the light of a plurality of wavebands to a finger contact surface of a prism; the multi-spectrum apparatus is used for sensing, by means of a multi-spectrum sensor, fingerprint-reflected light corresponding to the light of each waveband to obtain a spectrum response value and send same to the control unit, wherein the fingerprint-reflected light is reflected light formed by the light emitted by the light source apparatus being reflected by the finger contact surface of the prism; and the control unit is further used for comparing the similarity between the spectrum response value and a reference spectrum response value, and if the similarity does not satisfy a preset condition, determining that the fingerprint is a non-living body fingerprint.
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. (Chine)
Inventeur(s)
Wang, Huan
Ma, Weimin
Abrégé
A calibration method of a monitoring camera. The method is applied to a first camera in two linkage cameras for monitoring a same field scene, and comprises: obtaining a first image collected at a preset first position by the first camera for a preset scene, and multiple second images collected at multiple preset second positions by a second camera of the two linkage cameras for the preset scene; obtaining a theoretical focal length of the first camera, and calculating a ratio between the actual focal length and the theoretical focal length to obtain an actual focal length coefficient of the first camera; calculating to obtain an actual internal parameter matrix of the first camera on the basis of the actual focal length coefficient and an original internal parameter matrix of the first camera; and determining an external parameter matrix of the first camera on the basis of a positional relationship between the first camera and the second camera and an original external parameter matrix of the first camera. The method can implement calibration of two linkage cameras of an image collection device comprising a movable gun camera and a ball camera.