WO2021043168A1 - Procédé d'entraînement de réseau de ré-identification de personnes et procédé et appareil de ré-identification de personnes - Google Patents

Procédé d'entraînement de réseau de ré-identification de personnes et procédé et appareil de ré-identification de personnes Download PDF

Info

Publication number
WO2021043168A1
WO2021043168A1 PCT/CN2020/113041 CN2020113041W WO2021043168A1 WO 2021043168 A1 WO2021043168 A1 WO 2021043168A1 CN 2020113041 W CN2020113041 W CN 2020113041W WO 2021043168 A1 WO2021043168 A1 WO 2021043168A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
pedestrian
training
anchor point
network
Prior art date
Application number
PCT/CN2020/113041
Other languages
English (en)
Chinese (zh)
Inventor
魏龙辉
张天宇
谢凌曦
田奇
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2021043168A1 publication Critical patent/WO2021043168A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Definitions

  • Pedestrian re-identification can also be called pedestrian re-identification.
  • Pedestrian re-identification is a technology that uses computer vision technology to determine whether there is a specific pedestrian in an image or video sequence.
  • Step 1 Obtain training data
  • the training data in step 1 includes M training images and labeled data of M training images, and M is an integer greater than 1;
  • Step 2 Initialize the network parameters of the pedestrian re-identification network to obtain the initial values of the network parameters of the pedestrian re-identification network;
  • Step 3 Input a batch of training images from the M training images to the pedestrian recognition network for feature extraction, and obtain the feature vector of each training image in the batch of training images;
  • Step 4 Determine the function value of the loss function according to the feature vector of a batch of training images
  • each training image includes a pedestrian
  • the annotation data of each training image includes the bounding box where the pedestrian in each training image is located and the pedestrian identification information.
  • Different pedestrians Corresponding to different pedestrian identification information, among the M training images, the training images with the same pedestrian identification information come from the same image capturing device.
  • the M training images can be all the training images used in the training of the pedestrian re-recognition network. In the specific training process, a batch of training images of the M training images can be selected and input into the pedestrian re-recognition network each time. deal with.
  • the aforementioned image capturing device may specifically be a device capable of acquiring images of pedestrians, such as a video camera and a camera.
  • the pedestrian identification information in step 1 above can also be called pedestrian identification information, which is a type of information used to identify the identity of a pedestrian.
  • Each pedestrian can correspond to unique pedestrian identification information.
  • the pedestrian identification information may specifically be a pedestrian identity (identity, ID), that is, a unique ID can be assigned to each pedestrian.
  • the network parameters of the pedestrian re-identification network can be randomly set to obtain the initial values of the network parameters of the pedestrian re-identification network.
  • the above batch of training images may include N anchor point images, where the N anchor point images are any N training images in the above batch of training images, and each of the N anchor point images Each anchor point image corresponds to a most difficult positive sample image, a first most difficult negative sample image and a second most difficult negative sample image.
  • the following describes the most difficult positive sample image corresponding to each anchor point image, the first most difficult negative sample image, and the second most difficult negative sample image.
  • the most difficult positive sample image corresponding to each anchor point image the training image that has the same pedestrian identification information as each anchor point image and the farthest distance from the feature vector of each anchor point image in the above batch of training images ;
  • the first most difficult negative sample image corresponding to each anchor point image the above batch of training images and each anchor point image come from the same image capture device, and are different from the pedestrian identification information of each anchor point image and are different from each anchor point image.
  • the second most difficult negative sample image corresponding to each anchor point image the above batch of training images and each anchor point image come from different image capture equipment, and are different from the pedestrian identification information of each anchor point image and are different from each anchor point image.
  • the training image with the closest distance between the feature vectors of the point image.
  • the above N is a positive integer, and the above N is less than M.
  • the function value of the first loss function can be directly used as the function value of the loss function in step 4.
  • the function value of each of the foregoing first loss functions is the sum of the first difference and the second difference corresponding to each anchor point image.
  • the second most difficult negative sample distance corresponding to each anchor point image the distance between the feature vector of the second most difficult negative sample image corresponding to each anchor point image and the feature vector of each anchor point image;
  • the distance of the first most difficult negative sample corresponding to each anchor point image the distance between the feature vector of the first most difficult negative sample image corresponding to each anchor point image and the feature vector of each anchor point image.
  • the most difficult negative sample images from different image capturing devices and the same image capturing device are considered in the process of constructing the loss function, and the first difference and the second difference are reduced as much as possible during the training process.
  • Small which can eliminate as much as possible the interference of the image capturing device's own information on the image information, so that the trained pedestrian re-recognition network can more accurately extract features from the image.
  • the network parameters of the pedestrian re-recognition network are optimized to make the first difference and the second difference as small as possible, so that the distance between the most difficult positive sample and the second hardest
  • the difference between the distance of the negative sample and the distance between the second most difficult negative sample and the distance of the first most difficult negative sample are as small as possible, so that the pedestrian re-recognition network can distinguish the most difficult image from the second most difficult negative as much as possible.
  • the pedestrian re-identification network meets preset requirements, including: when at least one of the following conditions (1) to (3) is met, the pedestrian re-identification network Meet the preset requirements:
  • the number of training times of the pedestrian re-identification network is greater than or equal to the preset number
  • the value range of the foregoing preset threshold is [0, 0.01].
  • the function value of the loss function is less than or equal to a preset threshold, including: the first difference is less than the first preset threshold, and the second difference is less than the second preset Set the threshold.
  • both the first preset threshold and the second threshold may be 0.1.
  • the images of each image capturing device can be marked separately, regardless of whether the same pedestrian will appear between different image capturing devices, specifically, if the multiple images captured by the image capturing device A include pedestrians.
  • X then, after marking the M training images captured by image capture device A, there is no need to look for images of pedestrian X from the images captured by other image capture devices, thus avoiding the need to use different image capture devices
  • the process of finding the same pedestrian in the captured image can save a lot of marking time and reduce the complexity of marking.
  • a pedestrian re-recognition method includes: acquiring an image to be recognized; using a pedestrian re-recognition network to process the image to be recognized to obtain a feature vector of the image to be recognized, wherein the pedestrian re-recognition network is based on the above
  • the training method of the first aspect is obtained by training; according to the feature vector of the image to be recognized and the feature vector of the existing pedestrian image, the recognition result of the image to be recognized is obtained.
  • the above-mentioned comparison is performed based on the feature vector of the image to be recognized with the feature vector of the existing pedestrian image to obtain the recognition result of the image to be recognized, including: outputting the target pedestrian Image and attribute information of the target pedestrian image.
  • the above-mentioned target pedestrian image may be a pedestrian image whose feature vector is most similar to the feature vector of the image to be recognized in the existing pedestrian image, and the attribute information of the target pedestrian image includes the shooting time and shooting location of the target pedestrian image.
  • the attribute information of the target pedestrian image may also include the identity information of the pedestrian and the like.
  • a pedestrian re-identification device in a fourth aspect, includes modules for executing the method in the second aspect.
  • a training device for a pedestrian re-identification network includes: a memory for storing a program; a processor for executing the program stored in the memory, and when the program stored in the memory is executed , The processor is configured to execute the method in the above-mentioned first aspect.
  • a pedestrian re-identification device in a sixth aspect, includes: a memory for storing a program; a processor for executing the program stored in the memory, and when the program stored in the memory is executed, the The processor is used to execute the method in the second aspect described above.
  • the computer device may specifically be a server or a cloud device or the like.
  • an electronic device includes the pedestrian re-identification device of the fourth aspect.
  • the electronic device may specifically be a mobile terminal (for example, a smart phone), a tablet computer, a notebook computer, an augmented reality/virtual reality device, a vehicle-mounted terminal device, and so on.
  • a mobile terminal for example, a smart phone
  • a tablet computer for example, a tablet computer
  • a notebook computer for example, a tablet computer
  • an augmented reality/virtual reality device for example, a vehicle-mounted terminal device, and so on.
  • a computer-readable storage medium stores program code, and the program code includes instructions for executing steps in any one of the first aspect or the second aspect.
  • a chip in an eleventh aspect, includes a processor and a data interface.
  • the processor reads instructions stored in a memory through the data interface, and executes any one of the first aspect or the second aspect.
  • Kind of method is provided.
  • the method in the first aspect may specifically refer to the method in the first aspect and any one of the various implementation manners in the first aspect
  • the method in the second aspect may specifically refer to the second aspect. Aspect and the method in any one of the various implementation manners in the second aspect.
  • FIG. 1 is a schematic structural diagram of a system architecture provided by an embodiment of the present application.
  • FIG. 11 is a schematic block diagram of a training device for a pedestrian re-identification network according to an embodiment of the present application.
  • the intelligent monitoring system can collect the images of pedestrians captured by various image capturing devices to form an image library.
  • the pedestrian re-recognition network also called a pedestrian re-recognition model
  • the pedestrian re-recognition network can be trained using the images in the image library to obtain a trained pedestrian re-recognition network.
  • a neural network can be composed of neural units.
  • a neural unit can refer to an arithmetic unit that takes x s and intercept 1 as inputs.
  • the output of the arithmetic unit can be as shown in formula (1):
  • the above-mentioned target model/rule 101 can be used to implement the pedestrian re-identification method of the embodiment of the present application, that is, the pedestrian image (the pedestrian image may be an image that requires pedestrian recognition) is input into the target model/rule 101 to obtain the pedestrian re-identification method.
  • the image extracts feature vectors, and performs pedestrian recognition based on the extracted feature vectors to determine the pedestrian recognition results.
  • the target model/rule 101 in the embodiment of the present application may specifically be a neural network. It should be noted that, in actual applications, the training data maintained in the database 130 may not all come from the collection of the data collection device 160, and may also be received from other devices.
  • the target model/rule 101 trained according to the training device 120 can be applied to different systems or devices, such as the execution device 110 shown in FIG. 1, which can be a terminal, such as a mobile phone terminal, a tablet computer, notebook computers, augmented reality (AR)/virtual reality (VR), in-vehicle terminals, etc., can also be servers or clouds.
  • the execution device 110 is configured with an input/output (input/output, I/O) interface 112 for data interaction with external devices.
  • the user can input data to the I/O interface 112 through the client device 140.
  • the input data in the embodiment of the present application may include: a pedestrian image input by the client device.
  • the client device 140 here may specifically be a monitoring device.
  • the multiple weight matrices have the same size (row ⁇ column), the size of the convolution feature maps extracted by the multiple weight matrices of the same size are also the same, and then the multiple extracted convolution feature maps of the same size are merged to form The output of the convolution operation.
  • the arithmetic circuit 503 includes multiple processing units (process engines, PE). In some implementations, the arithmetic circuit 503 is a two-dimensional systolic array. The arithmetic circuit 503 may also be a one-dimensional systolic array or other electronic circuit capable of performing mathematical operations such as multiplication and addition. In some implementations, the arithmetic circuit 503 is a general-purpose matrix processor.
  • each layer in the convolutional neural network shown in FIG. 2 may be executed by the arithmetic circuit 503 or the vector calculation unit 507.
  • an embodiment of the present application provides a system architecture 300.
  • the system architecture includes a local device 301, a local device 302, an execution device 210 and a data storage system 250, where the local device 301 and the local device 302 are connected to the execution device 210 through a communication network.
  • Each local device can represent any computing device, such as personal computers, computer workstations, smart phones, tablets, smart cameras, smart cars or other types of cellular phones, media consumption devices, wearable devices, set-top boxes, game consoles, etc.
  • the local device of each user can interact with the execution device 210 through a communication network of any communication mechanism/communication standard.
  • the communication network can be a wide area network, a local area network, a point-to-point connection, etc., or any combination thereof.
  • the pedestrian re-recognition network can be trained through the single-image shooting device annotation data, and a trained pedestrian re-recognition network can be obtained.
  • the trained pedestrian re-recognition network can process pedestrian images. Obtain the feature vector of the pedestrian image. Next, by comparing the feature vector of the pedestrian image with the feature vector in the image library, the person you are looking for can be obtained. Specifically, through feature comparison, the target pedestrian image that is most similar to the feature vector of the pedestrian image can be found, and basic information such as the shooting time and location of the target pedestrian image can be output.
  • each pedestrian only appears in one image capture device (or one image capture device group). In this way, after pedestrian detection and tracking are used to obtain the pedestrian image in the video, only a small amount is required. Human power can associate several pictures of the same person in similar frames to form annotations. Moreover, the labels of each image capturing device are relatively independent, and there will be no overlap in the number of pedestrians of different image capturing devices. By setting different collection time periods for different image capturing devices, the number of people recurring in the video captured by each image capturing device can be reduced, thereby achieving the requirement of labeling data for a single image capturing device.
  • the training data in the above step 1002 includes M (M is an integer greater than 1) training images and the annotation data of M training images.
  • M is an integer greater than 1
  • each training image includes pedestrians
  • the annotation data includes the bounding box and pedestrian identification information of the pedestrian in each training image. Different pedestrians correspond to different pedestrian identification information.
  • the training images with the same pedestrian identification information are taken from the same image. equipment.
  • the aforementioned image capturing device may specifically be a device capable of acquiring images of pedestrians, such as a video camera and a camera.
  • Input a batch of training images among the M training images to the pedestrian recognition network to perform feature extraction, and obtain a feature vector of each training image in the batch of training images.
  • the foregoing batch of training images may include N anchor point images, where the N anchor point images are any N training images in the foregoing batch of training images, and each anchor point image in the N anchor point images corresponds to one
  • the most difficult positive sample image, a first most difficult negative sample image and a second most difficult negative sample image, N is a positive integer, and N is less than M.
  • the most difficult positive sample image corresponding to each anchor point image the training image that has the same pedestrian identification information as each anchor point image and the farthest distance from the feature vector of each anchor point image in the above batch of training images ;
  • the second most difficult negative sample image corresponding to each anchor point image the above batch of training images and each anchor point image come from different image capture equipment, and are different from the pedestrian identification information of each anchor point image and are different from each anchor point image.
  • the training image with the closest distance between the feature vectors of the point image.
  • the function value of each first loss function in the above N first loss functions is calculated according to the first difference and the second difference corresponding to each of the N anchor point images.
  • the second difference value corresponding to each anchor point image the difference between the distance of the second most difficult negative sample corresponding to each anchor point image and the distance of the first most difficult negative sample corresponding to each anchor point image.
  • step 1007 when the pedestrian re-identification network meets at least one of the above conditions (1) to (3), it can be determined that the pedestrian re-identification network meets the preset requirements, and step 1008 is executed, and the training process of the pedestrian re-identification network ends;
  • the pedestrian re-recognition network does not meet any of the above conditions (1) to (3), it means that the pedestrian re-recognition network has not yet met the preset requirements, and the pedestrian re-recognition network needs to continue to be trained, that is, step 1004 is re-executed To 1007, the network will not be recognized until pedestrians meeting the preset requirements are obtained.
  • the most difficult negative sample images from different image capturing devices and the same image capturing device are considered in the process of constructing the loss function, and the first difference and the second difference are reduced as much as possible during the training process.
  • Small which can eliminate as much as possible the interference of the image capturing device's own information on the image information, so that the trained pedestrian re-recognition network can more accurately extract features from the image.
  • the pedestrian re-identification network in this application can use the existing residual network (for example, ResNet50) as the main body of the network, remove the last fully connected layer, and add the global mean after the last layer of residual block (ResBlock) Pooling (global average pooling) layer, and obtain the feature vector of 2048 dimensions (or other values) as the output of the network model.
  • ResNet50 residual network
  • ResBlock global mean after the last layer of residual block Pooling (global average pooling) layer
  • the input training image can be scaled to a size of 256x128 pixels, the adaptive moment estimation (Adam) optimizer can be used to train the network parameters during training, and the learning rate can be set to 2 ⁇ 10 -4 . After 100 rounds of training, the learning rate decays exponentially, until after 200 rounds of learning, the learning rate can be set to 2 ⁇ 10 -7 , then training can be stopped.
  • Adam adaptive moment estimation
  • the memory 9001 may be a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).
  • the memory 9001 may store a program.
  • the processor 9002 is configured to execute each step of the pedestrian re-identification network training method in the embodiment of the present application.
  • the bus 9004 may include a path for transferring information between various components of the device 9000 (for example, the memory 9001, the processor 9002, and the communication interface 9003).
  • the acquiring unit 10001 may perform the foregoing step 6001, and the identifying unit 10002 may perform the foregoing step 6002.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disks or optical disks and other media that can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un procédé d'entraînement de réseau de ré-identification de personnes et un procédé et un appareil de ré-identification de personnes. La présente invention se rapporte au domaine de l'intelligence artificielle, et en particulier au domaine de la vision par ordinateur. Le procédé consiste à : obtenir M images d'entraînement et des données d'annotation des M images d'entraînement ; exécuter un traitement d'initialisation sur un paramètre de réseau d'un réseau de ré-identification de personnes de façon à obtenir une valeur initiale du paramètre de réseau du réseau de ré-identification de personnes ; introduire un lot d'images d'entraînement parmi les M images d'entraînement dans le réseau de ré-identification de personnes pour effectuer une extraction de caractéristiques de façon à obtenir un vecteur de caractéristiques de chaque image d'entraînement du lot d'images d'entraînement ; puis déterminer une fonction de perte selon les vecteurs de caractéristiques du lot d'images d'entraînement ; et obtenir, selon une valeur de fonction de la fonction de perte, un réseau de ré-identification de personnes qui satisfait à une exigence prédéfinie. Dans la présente invention, un réseau de ré-identification de personnes ayant de bonnes performances peut être entraîné lorsque des données sont étiquetées à l'aide d'un seul dispositif de photographie d'image.
PCT/CN2020/113041 2019-09-05 2020-09-02 Procédé d'entraînement de réseau de ré-identification de personnes et procédé et appareil de ré-identification de personnes WO2021043168A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910839017.9 2019-09-05
CN201910839017.9A CN112446270B (zh) 2019-09-05 2019-09-05 行人再识别网络的训练方法、行人再识别方法和装置

Publications (1)

Publication Number Publication Date
WO2021043168A1 true WO2021043168A1 (fr) 2021-03-11

Family

ID=74733092

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/113041 WO2021043168A1 (fr) 2019-09-05 2020-09-02 Procédé d'entraînement de réseau de ré-identification de personnes et procédé et appareil de ré-identification de personnes

Country Status (2)

Country Link
CN (1) CN112446270B (fr)
WO (1) WO2021043168A1 (fr)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112861825A (zh) * 2021-04-07 2021-05-28 北京百度网讯科技有限公司 模型训练方法、行人再识别方法、装置和电子设备
CN113095174A (zh) * 2021-03-29 2021-07-09 深圳力维智联技术有限公司 重识别模型训练方法、装置、设备及可读存储介质
CN113096080A (zh) * 2021-03-30 2021-07-09 四川大学华西第二医院 图像分析方法及系统
CN113177469A (zh) * 2021-04-27 2021-07-27 北京百度网讯科技有限公司 人体属性检测模型的训练方法、装置、电子设备及介质
CN113408492A (zh) * 2021-07-23 2021-09-17 四川大学 一种基于全局-局部特征动态对齐的行人重识别方法
CN113449601A (zh) * 2021-05-28 2021-09-28 国家计算机网络与信息安全管理中心 基于渐进性平滑损失的行人重识别模型训练和识别方法与装置
CN113536891A (zh) * 2021-05-10 2021-10-22 新疆爱华盈通信息技术有限公司 一种行人流量统计方法、存储介质及电子设备
CN113591545A (zh) * 2021-06-11 2021-11-02 北京师范大学珠海校区 一种基于深度学习的多级特征提取网络行人再识别方法
CN113762153A (zh) * 2021-09-07 2021-12-07 北京工商大学 一种基于遥感数据的新型尾矿库检测方法及系统
CN114240997A (zh) * 2021-11-16 2022-03-25 南京云牛智能科技有限公司 一种智慧楼宇在线跨摄像头多目标追踪方法
CN114359665A (zh) * 2021-12-27 2022-04-15 北京奕斯伟计算技术有限公司 全任务人脸识别模型的训练方法及装置、人脸识别方法
CN114494930A (zh) * 2021-09-09 2022-05-13 马上消费金融股份有限公司 语音与图像同步性衡量模型的训练方法及装置
CN115147871A (zh) * 2022-07-19 2022-10-04 北京龙智数科科技服务有限公司 遮挡环境下行人再识别方法
WO2023272994A1 (fr) * 2021-06-29 2023-01-05 苏州浪潮智能科技有限公司 Procédé et appareil de ré-identification de personne basés sur un réseau d'apprentissage profond, dispositif et support
CN115641559A (zh) * 2022-12-23 2023-01-24 深圳佑驾创新科技有限公司 一种环视摄像头组的目标匹配方法、装置及存储介质
CN113449966B (zh) * 2021-06-03 2023-04-07 湖北北新建材有限公司 一种石膏板设备巡检方法及系统
CN115952731A (zh) * 2022-12-20 2023-04-11 哈尔滨工业大学 一种风力机叶片主动振动控制方法、装置及设备
CN116824695A (zh) * 2023-06-07 2023-09-29 南通大学 一种基于特征去噪的行人再识别非局部防御方法
CN115147871B (zh) * 2022-07-19 2024-06-11 北京龙智数科科技服务有限公司 遮挡环境下行人再识别方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114943909B (zh) * 2021-03-31 2023-04-18 华为技术有限公司 运动区域识别的方法、装置、设备及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108108754A (zh) * 2017-12-15 2018-06-01 北京迈格威科技有限公司 重识别网络的训练、重识别方法、装置和系统
US20180374233A1 (en) * 2017-06-27 2018-12-27 Qualcomm Incorporated Using object re-identification in video surveillance
CN109344787A (zh) * 2018-10-15 2019-02-15 浙江工业大学 一种基于人脸识别与行人重识别的特定目标跟踪方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109784166A (zh) * 2018-12-13 2019-05-21 北京飞搜科技有限公司 行人重识别的方法及装置
CN109800794B (zh) * 2018-12-27 2021-10-22 上海交通大学 一种外观相似目标的跨相机重识别融合方法及系统
CN109977798B (zh) * 2019-03-06 2021-06-04 中山大学 用于行人重识别的掩膜池化模型训练和行人重识别方法
CN110046579B (zh) * 2019-04-18 2023-04-07 重庆大学 一种深度哈希的行人再识别方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180374233A1 (en) * 2017-06-27 2018-12-27 Qualcomm Incorporated Using object re-identification in video surveillance
CN108108754A (zh) * 2017-12-15 2018-06-01 北京迈格威科技有限公司 重识别网络的训练、重识别方法、装置和系统
CN109344787A (zh) * 2018-10-15 2019-02-15 浙江工业大学 一种基于人脸识别与行人重识别的特定目标跟踪方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
FUQING ZHU, XIANGWEI KONG, HAIYAN FU, QI TIAN: "Two-stream complementary symmetrical CNN architecture for person re-identification", JOURNAL OF IMAGE AND GRAPHICS, vol. 23, no. 7, 1 January 2018 (2018-01-01), pages 1052 - 1060, XP055787514, DOI: 10.11834 /jig.170557 *
TIANYU ZHANG; LINGXI XIE; LONGHUI WEI; YONGFEI ZHANG; BO LI; QI TIAN: "Single Camera Training for Person Re-identification", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 September 2019 (2019-09-24), 201 Olin Library Cornell University Ithaca, NY 14853, XP081481046 *

Cited By (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113095174A (zh) * 2021-03-29 2021-07-09 深圳力维智联技术有限公司 重识别模型训练方法、装置、设备及可读存储介质
CN113096080A (zh) * 2021-03-30 2021-07-09 四川大学华西第二医院 图像分析方法及系统
CN113096080B (zh) * 2021-03-30 2024-01-16 四川大学华西第二医院 图像分析方法及系统
CN112861825B (zh) * 2021-04-07 2023-07-04 北京百度网讯科技有限公司 模型训练方法、行人再识别方法、装置和电子设备
CN112861825A (zh) * 2021-04-07 2021-05-28 北京百度网讯科技有限公司 模型训练方法、行人再识别方法、装置和电子设备
CN113177469B (zh) * 2021-04-27 2024-04-12 北京百度网讯科技有限公司 人体属性检测模型的训练方法、装置、电子设备及介质
CN113177469A (zh) * 2021-04-27 2021-07-27 北京百度网讯科技有限公司 人体属性检测模型的训练方法、装置、电子设备及介质
CN113536891B (zh) * 2021-05-10 2023-01-03 新疆爱华盈通信息技术有限公司 一种行人流量统计方法、存储介质及电子设备
CN113536891A (zh) * 2021-05-10 2021-10-22 新疆爱华盈通信息技术有限公司 一种行人流量统计方法、存储介质及电子设备
CN113449601B (zh) * 2021-05-28 2023-05-16 国家计算机网络与信息安全管理中心 基于渐进性平滑损失的行人重识别模型训练和识别方法与装置
CN113449601A (zh) * 2021-05-28 2021-09-28 国家计算机网络与信息安全管理中心 基于渐进性平滑损失的行人重识别模型训练和识别方法与装置
CN113449966B (zh) * 2021-06-03 2023-04-07 湖北北新建材有限公司 一种石膏板设备巡检方法及系统
CN113591545B (zh) * 2021-06-11 2024-05-24 北京师范大学珠海校区 一种基于深度学习的多级特征提取网络行人再识别方法
CN113591545A (zh) * 2021-06-11 2021-11-02 北京师范大学珠海校区 一种基于深度学习的多级特征提取网络行人再识别方法
US11810388B1 (en) 2021-06-29 2023-11-07 Inspur Suzhou Intelligent Technology Co., Ltd. Person re-identification method and apparatus based on deep learning network, device, and medium
WO2023272994A1 (fr) * 2021-06-29 2023-01-05 苏州浪潮智能科技有限公司 Procédé et appareil de ré-identification de personne basés sur un réseau d'apprentissage profond, dispositif et support
CN113408492A (zh) * 2021-07-23 2021-09-17 四川大学 一种基于全局-局部特征动态对齐的行人重识别方法
CN113408492B (zh) * 2021-07-23 2022-06-14 四川大学 一种基于全局-局部特征动态对齐的行人重识别方法
CN113762153A (zh) * 2021-09-07 2021-12-07 北京工商大学 一种基于遥感数据的新型尾矿库检测方法及系统
CN113762153B (zh) * 2021-09-07 2024-04-02 北京工商大学 一种基于遥感数据的新型尾矿库检测方法及系统
CN114494930B (zh) * 2021-09-09 2023-09-22 马上消费金融股份有限公司 语音与图像同步性衡量模型的训练方法及装置
CN114494930A (zh) * 2021-09-09 2022-05-13 马上消费金融股份有限公司 语音与图像同步性衡量模型的训练方法及装置
CN114240997B (zh) * 2021-11-16 2023-07-28 南京云牛智能科技有限公司 一种智慧楼宇在线跨摄像头多目标追踪方法
CN114240997A (zh) * 2021-11-16 2022-03-25 南京云牛智能科技有限公司 一种智慧楼宇在线跨摄像头多目标追踪方法
CN114359665B (zh) * 2021-12-27 2024-03-26 北京奕斯伟计算技术股份有限公司 全任务人脸识别模型的训练方法及装置、人脸识别方法
CN114359665A (zh) * 2021-12-27 2022-04-15 北京奕斯伟计算技术有限公司 全任务人脸识别模型的训练方法及装置、人脸识别方法
CN115147871A (zh) * 2022-07-19 2022-10-04 北京龙智数科科技服务有限公司 遮挡环境下行人再识别方法
CN115147871B (zh) * 2022-07-19 2024-06-11 北京龙智数科科技服务有限公司 遮挡环境下行人再识别方法
CN115952731A (zh) * 2022-12-20 2023-04-11 哈尔滨工业大学 一种风力机叶片主动振动控制方法、装置及设备
CN115952731B (zh) * 2022-12-20 2024-01-16 哈尔滨工业大学 一种风力机叶片主动振动控制方法、装置及设备
CN115641559A (zh) * 2022-12-23 2023-01-24 深圳佑驾创新科技有限公司 一种环视摄像头组的目标匹配方法、装置及存储介质
CN116824695A (zh) * 2023-06-07 2023-09-29 南通大学 一种基于特征去噪的行人再识别非局部防御方法

Also Published As

Publication number Publication date
CN112446270B (zh) 2024-05-14
CN112446270A (zh) 2021-03-05

Similar Documents

Publication Publication Date Title
WO2021043168A1 (fr) Procédé d'entraînement de réseau de ré-identification de personnes et procédé et appareil de ré-identification de personnes
US20220092351A1 (en) Image classification method, neural network training method, and apparatus
US20220108546A1 (en) Object detection method and apparatus, and computer storage medium
WO2020216227A9 (fr) Procédé et appareil de classification d'image et procédé et appareil de traitement de données
WO2021043112A1 (fr) Procédé et appareil de classification d'images
WO2021022521A1 (fr) Procédé de traitement de données et procédé et dispositif d'apprentissage de modèle de réseau neuronal
WO2021155792A1 (fr) Appareil de traitement, procédé et support de stockage
WO2021013095A1 (fr) Procédé et appareil de classification d'image, et procédé et appareil pour apprentissage de modèle de classification d'image
WO2020177607A1 (fr) Procédé et appareil de débruitage d'image
WO2021073311A1 (fr) Procédé et appareil de reconnaissance d'image, support d'enregistrement lisible par ordinateur et puce
CN110222718B (zh) 图像处理的方法及装置
WO2021018245A1 (fr) Procédé et appareil de classification d'images
CN113065645B (zh) 孪生注意力网络、图像处理方法和装置
CN111914997B (zh) 训练神经网络的方法、图像处理方法及装置
WO2021018251A1 (fr) Procédé et dispositif de classification d'image
WO2021227787A1 (fr) Procédé et appareil de formation de prédicteur de réseau neuronal, et procédé et appareil de traitement d'image
WO2021047587A1 (fr) Procédé de reconnaissance de geste, dispositif électronique, support de stockage lisible par ordinateur et puce
WO2021175278A1 (fr) Procédé de mise à jour de modèle et dispositif associé
CN113011562A (zh) 一种模型训练方法及装置
Grigorev et al. Depth estimation from single monocular images using deep hybrid network
CN113191489A (zh) 二值神经网络模型的训练方法、图像处理方法和装置
WO2022179606A1 (fr) Procédé de traitement d'image et appareil associé
WO2021042774A1 (fr) Procédé de récupération d'image, procédé d'entraînement de réseau de récupération d'image, dispositif, et support de stockage
CN113449550A (zh) 人体重识别数据处理的方法、人体重识别的方法和装置
CN113256556A (zh) 一种图像选择方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20859742

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20859742

Country of ref document: EP

Kind code of ref document: A1