WO2022213540A1 - Object detecting, attribute identifying and tracking method and system - Google Patents

Object detecting, attribute identifying and tracking method and system Download PDF

Info

Publication number
WO2022213540A1
WO2022213540A1 PCT/CN2021/117025 CN2021117025W WO2022213540A1 WO 2022213540 A1 WO2022213540 A1 WO 2022213540A1 CN 2021117025 W CN2021117025 W CN 2021117025W WO 2022213540 A1 WO2022213540 A1 WO 2022213540A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
tracking
feature map
attribute
network
Prior art date
Application number
PCT/CN2021/117025
Other languages
French (fr)
Chinese (zh)
Inventor
于鹏
高朋
刘辰飞
陈英鹏
许野平
刘明顺
Original Assignee
神思电子技术股份有限公司
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 神思电子技术股份有限公司 filed Critical 神思电子技术股份有限公司
Publication of WO2022213540A1 publication Critical patent/WO2022213540A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Definitions

  • the invention relates to the technical field of target detection, in particular to a method and system for target detection, attribute identification and tracking.
  • Patent CN 110188596 A "Real-time detection, attribute recognition and tracking method and system for pedestrians in surveillance video based on deep learning", relates to a method and system for real-time detection, attribute recognition and tracking of pedestrians in surveillance video based on deep learning. It mainly proposes efficient pedestrian detection, attribute recognition and tracking methods, and designs an efficient scheduling method, which schedules modules in series and parallel, so that it can perform real-time detection of multi-channel video pedestrians as much as possible on limited computing resources.
  • Property identification and tracking first uses a deep learning model to extract features in attribute recognition, and then trains 11 classifiers to classify these 11 attributes, and superimposes a model for deep learning to extract features. Increased the number of parameters for the overall framework.
  • the Kalman filter algorithm is used to predict, get the next position, and then perform matching. Multiple trajectory processes need to be stored, and the problem of position loss caused by frame skipping in video transmission cannot be solved. Missing key frames will cause the algorithm Match failed.
  • the patent CN 111274945 A "A recognition method, device, electronic device and storage medium for pedestrian attribute” discloses a pedestrian attribute identification method, device, electronic device and storage medium, which relates to the technical field of machine vision.
  • the specific implementation scheme is as follows: in the target monitoring picture, obtain at least one image of the human body recognition area; in each image of the human body recognition area, obtain the pedestrian attribute recognition result and the small object detection result; The recognition result is corrected, and the corrected pedestrian attribute recognition result matching the image of each human body recognition area is obtained.
  • the patent first performs attribute recognition and then uses a target detection algorithm to correct the attribute analysis results, and uses two deep learning models to superimpose. The amount of parameters has been increased, and the hardware requirements have been improved.
  • Patent CN 112232173 A discloses a pedestrian attribute identification method, deep learning model, equipment and medium, and obtains the target image for pedestrian attribute identification; Attribute color features and attribute position features in the target image; fuse attribute color features and attribute position features to obtain pixel-level features, and predict color information and position information based on pixel-level features; Perform splicing and segmentation to obtain the pedestrian feature map; fuse the pedestrian feature map to obtain the target feature; determine the pedestrian attribute recognition result based on the target feature.
  • the location information, color information and pictures of pedestrians are re-spliced and segmented. The spatial correlation of the original image is destroyed, and the tracking problem of the target is not solved.
  • the existing methods are basically spliced from separate algorithm architectures.
  • the splicing of multiple deep learning frameworks not only increases the difficulty of deep learning training, it is difficult to converge, the unknown situation increases, and the architecture is abandoned. The more, the larger the parameters of deep learning, the slower the running speed, and the higher the hardware requirements.
  • the purpose of the present invention is to address the above deficiencies, provide a target detection, attribute recognition and tracking method, reduce the number of deep learning used, only use one deep learning framework, reduce the difficulty of deep learning framework training, more easily converge, and improve the running rate, The requirement for hardware is reduced, and a target detection, attribute recognition and tracking system based on the above method is also provided.
  • the present invention provides a method for target detection, attribute identification and tracking, comprising the following steps:
  • the method of obtaining the original image of the target described in the present invention uses a high-definition video camera or a digital camera.
  • step S2 of the present invention feature analysis is performed on the acquired original image through a trained feature extraction network, and the target feature map includes target category information, target location information and target attribute information. .
  • step S3 of the present invention target detection is performed on the target feature map through a target detection network, and the target detection result includes target type information and target position information, and the target position information is used for attributes. identification and target tracking;
  • the target detection network adopts a deep learning network.
  • step S4 of the present invention the target feature map and the target detection result are input into the attribute recognition network for target attribute recognition, and the target attribute is a different representation of the common attribute of the target.
  • the target feature map, the target detection result and the target tracking information of the previous frame are input into the target tracking network for target tracking analysis, and the target tracking information of the previous frame is the previous frame.
  • the target detection, attribute recognition and tracking results of the frame including target location information, feature map information and the ID given to the target, the target feature map of this frame is matched with all target feature maps stored in the target tracking information of the previous frame.
  • the target position information is matched with the position information of all targets in the previous frame, and the matching value is used to determine whether the current target is a target in the previous frame.
  • the ID of the target is assigned to the corresponding target of the frame; when it is judged that there is no matching corresponding target, the target is assigned a new ID.
  • the feature extraction network of the present invention adopts the convolutional neural network algorithm.
  • the input information is the original three-dimensional prediction of RGB values, and the original image is marked
  • the labeling information includes target category label, target area label and target attribute label, and is trained through target detection network and attribute recognition network to obtain the optimal training model.
  • the present invention also provides a target detection, attribute recognition and tracking system, including an image acquisition device and a picture processing component, wherein:
  • the image acquisition device is used to acquire the original image of the target
  • the image processing component is used to process the collected target original image to track the target;
  • the image processing component includes a feature map extraction module, a target detection module, an attribute recognition module and a target tracking module, wherein:
  • the feature map extraction module is used to process the collected target original image into a target feature map
  • the target detection module is used to perform target detection from the processed target feature map, and obtain the target detection result
  • the attribute identification module is used to identify the attribute of the target through the target feature map and the target detection result, and obtain the target attribute identification result;
  • the target tracking module performs target tracking through the target detection result, the target tracking information of the previous frame and the feature map.
  • the feature map extraction module of the present invention includes a target feature extraction network
  • the target detection module includes a target detection network
  • the attribute identification module includes an attribute identification network
  • the target tracking module includes target tracking network
  • the target feature extraction network, the attribute recognition network and the target tracking network all use convolutional neural networks, and the target tracking network uses a deep neural network
  • the RGB three-dimensional image is used as the input, and the image is annotated. Extract the network for joint training to obtain the optimal model.
  • each target corresponds to a unique ID.
  • the target tracking module the target tracking information of the previous frame is compared and judged. When a target is the same target, the frame target inherits the ID of the corresponding target in the previous frame, and when it is judged that there is no corresponding target, a new ID is given to the target.
  • the present invention performs feature extraction on the acquired original image through a feature extraction network, and then performs subsequent target detection, attribute recognition and target tracking according to the extracted feature map, so that the target attribute processing is more reasonable, so that target detection, attribute The effect of identification and tracking is more prepared to avoid the occurrence of target loss;
  • the present invention only uses one deep learning framework, which reduces the training difficulty of the neural network, can correspondingly avoid difficult convergence, reduces deep learning parameters, improves operating efficiency, and reduces hardware requirements.
  • FIG. 1 is a schematic flow chart of the present invention.
  • This embodiment provides a method for target detection, attribute identification and tracking, as shown in FIG. 1 , including the following steps:
  • the target original image is generally acquired by an image acquisition device.
  • the used image acquisition device is a high-definition surveillance camera or a digital camera.
  • the resolution of surveillance cameras and digital cameras can use high-resolution equipment, such as 40 million pixel imaging, and the higher ones include 60 million pixel imaging, 80 million pixel imaging and 100 million pixel imaging. , in actual use, the cost of image acquisition equipment should also be taken into account;
  • the target feature map performs feature analysis on the acquired original image through a trained feature extraction network, the feature extraction network needs to be trained by samples, and the sample input information of the feature extraction network is RGB three-dimensional original images, and the method of supervised learning is carried out.
  • label the image of the sample, and the labeling information includes the target category label, the target position label and the attribute information of the target, and the target detection network and the attribute recognition network for subsequent processing are jointly trained to obtain the optimal model;
  • the target feature map contains target category information, target location information and target attribute information
  • the target feature map is a (a, b, c) three-dimensional feature map
  • a is the number of targets detected in the image
  • b*c It is the target area feature map
  • the area feature map containing the portrait is used for the next pedestrian target detection, behavior attribute analysis and pedestrian target tracking;
  • Target detection on the target feature map through a target detection network, and the target detection result includes target type information and target position information, and the target position information is used for attribute identification and target tracking;
  • the target detection network is a deep learning network, and the target detection network includes a classification part and a positioning part, which are used to separate the target category information and target location information from the above-mentioned target feature map, and use the target positioning information for follow-up. Attribute identification and target tracking;
  • Target attribute is the different manifestations of the common attribute of the target, such as the age of the person, clothing style, hair and clothing color, etc.;
  • the target tracking information of the previous frame is the target detection, attribute identification and tracking results of the previous frame, including the target position information. , feature map information and the ID given to the target, the target feature map of this frame is matched with all target feature maps stored in the target tracking information of the previous frame, and the target position information of this frame is matched with the position information of all targets in the previous frame, and Judging whether the current target is a target in the previous frame by the matching value, when it is judged that the current target and a target in the previous frame are the same target, the ID of the target in the previous frame is assigned to the corresponding target in the frame; when it is judged that there is no match After corresponding to the target, assign the target a new ID;
  • the processing information is saved as the judgment basis for the target tracking processing of the next frame;
  • this embodiment also provides a target detection, attribute recognition and tracking system, including an image acquisition device and a picture processing component, wherein:
  • the image acquisition device is used to acquire the original image of the target
  • the image processing component is used to process the collected target original image to track the target;
  • the picture processing component includes a feature map extraction module, a target detection module, an attribute recognition module and a target tracking module, wherein:
  • the feature map extraction module is used to process the collected target original image into a target feature map
  • the target detection module is used to perform target detection from the processed target feature map, and obtain the target detection result
  • the attribute identification module is used to identify the attribute of the target through the target feature map and the target detection result, and obtain the target attribute identification result;
  • the target tracking module performs target tracking through the target detection result, the target tracking information of the previous frame and the feature map.
  • the feature map extraction module includes a target feature extraction network
  • the target detection module includes a target detection network
  • the attribute identification module includes an attribute identification network
  • the target tracking module includes a target tracking network
  • the target The feature extraction network, the attribute recognition network and the target tracking network all use convolutional neural networks, and the target tracking network uses a deep neural network;
  • the RGB three-dimensional image is used as the input, and the image is annotated. Extract the network for joint training to obtain the optimal model.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

Disclosed in the present invention are an object detecting, attribute identifying and tracking method and system. The method of the present invention comprises: S1, obtaining an original image of an object; S2, obtaining an object feature map by performing feature analysis on the obtained original image of the object; S3, obtaining an object detection result by performing object detection on the obtained object feature map; S4, obtaining an object attribute identifying result by performing attribute identification on the obtained object feature map and object detection result; and S5, obtaining an object tracking result by performing object tracking analysis on the obtained object feature map and object detection result, and object tracking information of a previous frame. According to the present invention, feature extraction is first performed on an obtained original image by means of a feature extraction network, and subsequent object detecting, attribute identifying and object tracking are carried out according to the extracted feature map, so that the object attribute processing is more reasonable, the object detecting, attribute identifying and tracking effects are more accurate, and the occurrence of object loss is avoided.

Description

目标检测、属性识别与跟踪方法及***Object detection, attribute recognition and tracking method and system 技术领域technical field
本发明涉及目标检测相关技术领域，具体地说是一种目标检测、属性识别与跟踪方法及***。The invention relates to the technical field of target detection, in particular to a method and system for target detection, attribute identification and tracking.
背景技术Background technique
随着社会的发展，人们对公共安防的关注越来越多，公共场所的摄像头数量也越来越多，安防的死角越来越少，随着这些海量数据的提供，除了基本的目标的检测，如果在此基础上能对目标的属性，例如性别、年龄、衣服样式、服装颜色、发型等进行识别得出属性特征，并且将不同时刻的图像进行对比得出目标的轨迹信息，将对个别人员的追踪识别提供极大的方便。With the development of society, people pay more and more attention to public security, the number of cameras in public places is also increasing, and there are fewer and fewer dead spots in security. With the provision of these massive data, in addition to the detection of basic objects , if the attributes of the target, such as gender, age, clothing style, clothing color, hairstyle, etc., can be identified on this basis to obtain attribute characteristics, and the images at different times can be compared to obtain the trajectory information of the target, the individual Personnel tracking identification provides great convenience.
专利CN 110188596 A《基于深度学习的监控视频行人实时检测、属性识别与跟踪方法及***》，涉及一种基于深度学习的监控视频行人实时检测、属性识别与跟踪方法及***。主要提出高效的行人检测、属性识别以及跟踪方法，并设计一种高效的调度方法，将模块之间进行串并联调度，使其在有限计算资源上尽可能多地进行多路视频行人实时检测，属性识别以及跟踪。但该专利在属性识别上首先采用深度学习模型提取特征，然后训练了11个分类器，对这11个属性进行分类，又叠加了深度学习提取特征的模型。增加了整体框架的参数量。在跟踪算法上使用了卡尔曼滤波算法进行预测，得到下个位置，然后再进行匹配，需要存储多个轨迹进程，并且无法解决视频传输中跳帧出现的位置丢失问题，缺失关键帧会导致算法匹配失败。Patent CN 110188596 A "Real-time detection, attribute recognition and tracking method and system for pedestrians in surveillance video based on deep learning", relates to a method and system for real-time detection, attribute recognition and tracking of pedestrians in surveillance video based on deep learning. It mainly proposes efficient pedestrian detection, attribute recognition and tracking methods, and designs an efficient scheduling method, which schedules modules in series and parallel, so that it can perform real-time detection of multi-channel video pedestrians as much as possible on limited computing resources. Property identification and tracking. However, this patent first uses a deep learning model to extract features in attribute recognition, and then trains 11 classifiers to classify these 11 attributes, and superimposes a model for deep learning to extract features. Increased the number of parameters for the overall framework. In the tracking algorithm, the Kalman filter algorithm is used to predict, get the next position, and then perform matching. Multiple trajectory processes need to be stored, and the problem of position loss caused by frame skipping in video transmission cannot be solved. Missing key frames will cause the algorithm Match failed.
专利CN 111274945 A《一种行人属性的识别方法、装置、电子设备和存储介质》，公开了一种行人属性的识别方法、装置、电子设备和存储介质，涉及机器视觉技术领域。具体实现方案为：在目标监控图片中，获取至少一个人体识 别区域图像；分别在每个人体识别区域图像中，获取行人属性识别结果，以及小物体检测结果；根据小物体检测结果，对行人属性识别结果进行修正，得到与各人体识别区域图像匹配的修正后行人属性识别结果。该专利先进行属性识别又使用目标检测算法对属性分析结果进行修正，使用了两个深度学习模型进行叠加。增加了参数量，提高了硬件的要求。The patent CN 111274945 A "A recognition method, device, electronic device and storage medium for pedestrian attribute" discloses a pedestrian attribute identification method, device, electronic device and storage medium, which relates to the technical field of machine vision. The specific implementation scheme is as follows: in the target monitoring picture, obtain at least one image of the human body recognition area; in each image of the human body recognition area, obtain the pedestrian attribute recognition result and the small object detection result; The recognition result is corrected, and the corrected pedestrian attribute recognition result matching the image of each human body recognition area is obtained. The patent first performs attribute recognition and then uses a target detection algorithm to correct the attribute analysis results, and uses two deep learning models to superimpose. The amount of parameters has been increased, and the hardware requirements have been improved.
专利CN 112232173 A《一种行人属性识别方法、深度学习模型、设备及介质》，公开了一种行人属性识别方法、深度学习模型、设备及介质，获取待进行行人属性识别的目标图片；提取出目标图片中的属性颜色特征和属性位置特征；将属性颜色特征和属性位置特征进行融合，得到像素级特征，并基于像素级特征预测出颜色信息和位置信息；将颜色信息、位置信息和目标图片进行拼接、切分，得到行人特征图；对行人特征图进行融合，得到目标特征；基于目标特征确定行人属性识别结果。该方法将行人的位置信息和颜色信息、图片进行了重新的拼接、切分。破坏了原图像的空间相关性，并且也没有解决目标的跟踪问题。Patent CN 112232173 A "A Pedestrian Attribute Recognition Method, Deep Learning Model, Equipment and Medium", discloses a pedestrian attribute identification method, deep learning model, equipment and medium, and obtains the target image for pedestrian attribute identification; Attribute color features and attribute position features in the target image; fuse attribute color features and attribute position features to obtain pixel-level features, and predict color information and position information based on pixel-level features; Perform splicing and segmentation to obtain the pedestrian feature map; fuse the pedestrian feature map to obtain the target feature; determine the pedestrian attribute recognition result based on the target feature. In this method, the location information, color information and pictures of pedestrians are re-spliced and segmented. The spatial correlation of the original image is destroyed, and the tracking problem of the target is not solved.
针对所检索的相关专利申请，现有的方法基本都是分离的算法架构拼接而成，多个深度学习框架的拼接，不仅使深度学习训练的难度加大，难收敛，未知情况增加，摒弃架构越多，深度学习的参数越大，运行的速度越低，对硬件的要求也会越高。For the relevant patent applications retrieved, the existing methods are basically spliced from separate algorithm architectures. The splicing of multiple deep learning frameworks not only increases the difficulty of deep learning training, it is difficult to converge, the unknown situation increases, and the architecture is abandoned. The more, the larger the parameters of deep learning, the slower the running speed, and the higher the hardware requirements.
发明内容SUMMARY OF THE INVENTION
本发明的目的是针对以上不足，提供一种目标检测、属性识别与跟踪方法，降低深度学习的使用数量，仅使用一个深度学习框架，降低深度学习框架训练的难度，更易收敛，提升运行速率，降低对硬件的要求，还提供一种基于上述方法的目标检测、属性识别与跟踪***。The purpose of the present invention is to address the above deficiencies, provide a target detection, attribute recognition and tracking method, reduce the number of deep learning used, only use one deep learning framework, reduce the difficulty of deep learning framework training, more easily converge, and improve the running rate, The requirement for hardware is reduced, and a target detection, attribute recognition and tracking system based on the above method is also provided.
本发明所采用技术方案是：The technical scheme adopted in the present invention is:
本发明提供一种目标检测、属性识别与跟踪方法，包括如下步骤：The present invention provides a method for target detection, attribute identification and tracking, comprising the following steps:
S1、获取目标原始图像；S1. Obtain the original image of the target;
S2、通过对获取目标的原始图像进行特征分析获取目标特征图；S2. Obtain the target feature map by performing feature analysis on the original image of the obtained target;
S3、通过对获取的目标特征图进行目标检测获取目标检测结果；S3. Obtain a target detection result by performing target detection on the obtained target feature map;
S4、通过对获取的目标特征图与目标检测结果进行属性识别获取目标属性识别结果；S4. Obtain the target attribute identification result by performing attribute identification on the obtained target feature map and the target detection result;
S5、通过对获取的目标特征图、目标检测结果以及上帧目标跟踪信息进行目标跟踪分析获取目标跟踪结果；S5. Obtain the target tracking result by performing target tracking analysis on the obtained target feature map, the target detection result and the target tracking information of the previous frame;
S6、对目标赋予ID后，并将获取的目标检测结果、目标属性识别结果和目标跟踪结果进行汇总输出。S6 , after assigning an ID to the target, summarize and output the obtained target detection result, target attribute recognition result and target tracking result.
作为对本发明方法的进一步的优化，本发明所述获取目标原始图像的方式通过高清摄像机或数码照相机。As a further optimization of the method of the present invention, the method of obtaining the original image of the target described in the present invention uses a high-definition video camera or a digital camera.
作为对本发明方法的进一步的优化，本发明步骤S2中，通过训练好的特征提取网络对获取的原始图像进行特征分析，所述的目标特征图中包含目标类别信息、目标位置信息和目标属性信息。As a further optimization of the method of the present invention, in step S2 of the present invention, feature analysis is performed on the acquired original image through a trained feature extraction network, and the target feature map includes target category information, target location information and target attribute information. .
作为对本发明方法的进一步的优化，本发明步骤S3中，通过目标检测网络对目标特征图进行目标检测，所述目标检测结果包括目标类型信息和目标位置信息，且所述目标位置信息用于属性识别和目标跟踪；As a further optimization of the method of the present invention, in step S3 of the present invention, target detection is performed on the target feature map through a target detection network, and the target detection result includes target type information and target position information, and the target position information is used for attributes. identification and target tracking;
所述目标检测网络采用深度学习网络。The target detection network adopts a deep learning network.
作为对本发明方法的进一步的优化，本发明步骤S4中，将目标特征图和目标检测结果输入到属性识别网络中进行目标属性识别，且所述目标属性为目标的共有属性的不同表现形式。As a further optimization of the method of the present invention, in step S4 of the present invention, the target feature map and the target detection result are input into the attribute recognition network for target attribute recognition, and the target attribute is a different representation of the common attribute of the target.
作为对本发明方法的进一步的优化，本发明步骤S5中，将目标特征图、目标检测结果以及上帧目标跟踪信息输入到目标跟踪网络中进行目标跟踪分析，所述上帧目标跟踪信息为上一帧的目标检测、属性识别与跟踪结果，包括目标位置信息、特征图信息和赋予该目标的ID，该帧的目标特征图与上帧目标跟踪信息存储的所有目标特征图进行匹配，该帧的目标位置信息与上帧所有目标的位置信息进行匹配，并通过匹配值判断当前目标是否为上帧中的某一目标，当判断当前目标与上帧某一目标为同一目标时，将上帧该目标的ID赋予到该帧对应目标上；当判断无匹配对应目标后，将该目标赋予新的ID。As a further optimization of the method of the present invention, in step S5 of the present invention, the target feature map, the target detection result and the target tracking information of the previous frame are input into the target tracking network for target tracking analysis, and the target tracking information of the previous frame is the previous frame. The target detection, attribute recognition and tracking results of the frame, including target location information, feature map information and the ID given to the target, the target feature map of this frame is matched with all target feature maps stored in the target tracking information of the previous frame. The target position information is matched with the position information of all targets in the previous frame, and the matching value is used to determine whether the current target is a target in the previous frame. When it is judged that the current target and a target in the previous frame are the same target, The ID of the target is assigned to the corresponding target of the frame; when it is judged that there is no matching corresponding target, the target is assigned a new ID.
作为对本发明方法的进一步的优化，本发明所述特征提取网络采用卷积神经网络算法，在对特征提取网络进行训练时，输入信息为RGB值的三位原始预想，并对原始图像进行标注，标注信息包括目标类别标签、目标区域标签和目标属性标签，并通过目标检测网络和属性识别网络进行训练，获取优选训练模型。As a further optimization of the method of the present invention, the feature extraction network of the present invention adopts the convolutional neural network algorithm. When training the feature extraction network, the input information is the original three-dimensional prediction of RGB values, and the original image is marked, The labeling information includes target category label, target area label and target attribute label, and is trained through target detection network and attribute recognition network to obtain the optimal training model.
本发明还提供一种目标检测、属性识别与跟踪***，包括图像采集设备和图片处理组件，其中：The present invention also provides a target detection, attribute recognition and tracking system, including an image acquisition device and a picture processing component, wherein:
所述图像采集设备用于采集目标原始图像；The image acquisition device is used to acquire the original image of the target;
所述图片处理组件用于对采集的目标原始图像进行处理，以进行目标跟踪；The image processing component is used to process the collected target original image to track the target;
所述图片处理组件包括特征图提取模块、目标检测模块、属性识别模块和目标跟踪模块，其中：The image processing component includes a feature map extraction module, a target detection module, an attribute recognition module and a target tracking module, wherein:
所述特征图提取模块用于将采集的目标原始图像进行处理成目标特征图；The feature map extraction module is used to process the collected target original image into a target feature map;
所述目标检测模块用于从处理的目标特征图中进行目标检测，获取目标检测结果；The target detection module is used to perform target detection from the processed target feature map, and obtain the target detection result;
所述属性识别模块用于通过目标特征图与目标检测结果进行目标的属性识 别，获取目标属性识别结果；The attribute identification module is used to identify the attribute of the target through the target feature map and the target detection result, and obtain the target attribute identification result;
所述目标跟踪模块通过目标检测结果、上帧目标跟踪信息和特征图进行目标跟踪。The target tracking module performs target tracking through the target detection result, the target tracking information of the previous frame and the feature map.
作为对本发明***的进一步优化，本发明所述特征图提取模块包括目标特征提取网络，所述目标检测模块包括目标检测网络，所述属性识别模块包括属性识别网络，所述目标跟踪模块包括目标跟踪网络，且所述目标特征提取网络、属性识别网络和目标跟踪网络均采用卷积神经网络，所述目标跟踪网络采用深度神经网络；As a further optimization of the system of the present invention, the feature map extraction module of the present invention includes a target feature extraction network, the target detection module includes a target detection network, the attribute identification module includes an attribute identification network, and the target tracking module includes target tracking network, and the target feature extraction network, the attribute recognition network and the target tracking network all use convolutional neural networks, and the target tracking network uses a deep neural network;
对目标特征提取网络进行训练时，以RGB三维图像作为输入，并对图像进行标注，标注信息包括目标类别标签、目标位置标签和目标属性标签，然后再用目标检测网络和属性识别网络对目标特征提取网络进行联合训练，获取最优模型。When training the target feature extraction network, the RGB three-dimensional image is used as the input, and the image is annotated. Extract the network for joint training to obtain the optimal model.
作为对本发明***的进一步优化，本发明所述图片处理组件中，每个目标均对应唯一一个ID，在目标跟踪模块中，通过与上帧目标跟踪信息进行对比判断，当判断为与上帧某一目标为同一目标时，该帧目标继承上帧对应目标的ID，当判断不存在对应目标时，赋予该目标新的ID。As a further optimization of the system of the present invention, in the picture processing component of the present invention, each target corresponds to a unique ID. In the target tracking module, the target tracking information of the previous frame is compared and judged. When a target is the same target, the frame target inherits the ID of the corresponding target in the previous frame, and when it is judged that there is no corresponding target, a new ID is given to the target.
本发明具有以下优点：The present invention has the following advantages:
1、本发明通过先通过特征提取网络对获取的原始图像进行特征提取后，并根据提取的特征图进行后续的目标检测、属性识别和目标跟踪，对目标属性处理更加合理，使得目标检测、属性识别与跟踪的效果更加准备，避免出现目标丢失的情况发生；1. The present invention performs feature extraction on the acquired original image through a feature extraction network, and then performs subsequent target detection, attribute recognition and target tracking according to the extracted feature map, so that the target attribute processing is more reasonable, so that target detection, attribute The effect of identification and tracking is more prepared to avoid the occurrence of target loss;
2、本发明仅使用一个深度学习框架，降低了神经网络的训练难度，能够相应避免难收敛的情况，降低深度学习的参数，提升运行效率，降低对硬件的要求。2. The present invention only uses one deep learning framework, which reduces the training difficulty of the neural network, can correspondingly avoid difficult convergence, reduces deep learning parameters, improves operating efficiency, and reduces hardware requirements.
3、本发明中只涉及一个深度学习框架，方便后续的算法升级，可方便的根据实际场景的应用以及实际的软硬件需求进行模型的更换以及修改。3. Only one deep learning framework is involved in the present invention, which facilitates subsequent algorithm upgrades, and can easily replace and modify models according to the application of actual scenarios and actual software and hardware requirements.
附图说明Description of drawings
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例中描述中所需要使用的附图作简要介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.
下面结合附图对本发明进一步说明：Below in conjunction with accompanying drawing, the present invention is further described:
图1为本发明的流程示意图。FIG. 1 is a schematic flow chart of the present invention.
具体实施方式Detailed ways
下面结合附图和具体实施例对本发明作进一步说明，以使本领域的技术人员可以更好地理解本发明并能予以实施，但所举实施例不作为对本发明的限定，在不冲突的情况下，本发明实施例以及实施例中的技术特征可以相互结合。The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention, and in the case of no conflict Hereinafter, the embodiments of the present invention and the technical features in the embodiments may be combined with each other.
需要理解的是，在本发明实施例的描述中，“第一”、“第二”等词汇，仅用于区分描述的目的，而不能理解为指示或暗示相对重要性，也不能理解为指示或暗示顺序。在本发明实施例中的“多个”，是指两个或两个以上。It should be understood that, in the description of the embodiments of the present invention, words such as "first" and "second" are only used for the purpose of distinguishing the description, and should not be understood as indicating or implying relative importance, nor should it be understood as indicating or implied order. In the embodiments of the present invention, "a plurality" refers to two or more.
本发明实施例中的属于“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，单独存在B，同时存在A和B这三种情况。另外，本文中字符“/”一般表示前后关联对象是一种“或”关系。In this embodiment of the present invention, "and/or" is only an association relationship describing associated objects, indicating that three relationships may exist, for example, A and/or B may indicate that A exists alone, B exists alone, There are three cases A and B at the same time. In addition, the character "/" in this document generally indicates that the contextual objects are an "or" relationship.
本实施例提供一种目标检测、属性识别与跟踪方法，如图1所示，包括如下步骤：This embodiment provides a method for target detection, attribute identification and tracking, as shown in FIG. 1 , including the following steps:
S1、获取目标原始图像；S1. Obtain the original image of the target;
所述目标原始图像一般通过图像采集设备进行获取，根据本实施例所具体的使用场景，所使用的图像采集设备为高清监控摄像机或数码照相机，其中为了保证其原始图像的成像质量，方便后续的对图片的处理，其监控摄像机以及数码相机的分辨率均可采用高分辨率设备，如四千万像素成像，再高者还有六千万像素成像、八千万像素成像以及一亿像素成像，在实际使用时，还应同时兼顾图像采集设备的成本；The target original image is generally acquired by an image acquisition device. According to the specific usage scenario of this embodiment, the used image acquisition device is a high-definition surveillance camera or a digital camera. In order to ensure the imaging quality of the original image, it is convenient for subsequent For the processing of pictures, the resolution of surveillance cameras and digital cameras can use high-resolution equipment, such as 40 million pixel imaging, and the higher ones include 60 million pixel imaging, 80 million pixel imaging and 100 million pixel imaging. , in actual use, the cost of image acquisition equipment should also be taken into account;
S2、通过对获取目标原始图像的进行特征分析获取目标特征图；S2. Obtain the target feature map by analyzing the features of the obtained target original image;
所述目标特征图通过训练好的特征提取网络对获取的原始图像进行特征分析，所述特征提取网络需要通过样本进行训练，特征提取网络的样本输入信息为RGB三维原始图像，通过监督学习的方式，对样本的图像进行标注，且标注信息包括目标类别标签、目标位置标签以及目标的属性信息，并通过用于后续处理的目标检测网络和属性识别网络进行联合训练，得出最优的模型；The target feature map performs feature analysis on the acquired original image through a trained feature extraction network, the feature extraction network needs to be trained by samples, and the sample input information of the feature extraction network is RGB three-dimensional original images, and the method of supervised learning is carried out. , label the image of the sample, and the labeling information includes the target category label, the target position label and the attribute information of the target, and the target detection network and the attribute recognition network for subsequent processing are jointly trained to obtain the optimal model;
所述的目标特征图中包含目标类别信息、目标位置信息和目标属性信息，该目标特征图为(a，b，c)三维特征图，a为图像中检测到的目标个数，b*c为目标区域特征图，含有人像的区域特征图用于接下来的行人目标检测、行为属性分析以及行人目标跟踪；The target feature map contains target category information, target location information and target attribute information, the target feature map is a (a, b, c) three-dimensional feature map, a is the number of targets detected in the image, b*c It is the target area feature map, and the area feature map containing the portrait is used for the next pedestrian target detection, behavior attribute analysis and pedestrian target tracking;
S3、通过对获取的目标特征图进行目标检测获取目标检测结果；S3. Obtain a target detection result by performing target detection on the obtained target feature map;
通过目标检测网络对目标特征图进行目标检测，所述目标检测结果包括目标类型信息和目标位置信息，且所述目标位置信息用于属性识别和目标跟踪；Perform target detection on the target feature map through a target detection network, and the target detection result includes target type information and target position information, and the target position information is used for attribute identification and target tracking;
所述目标检测网络为深度学习网络，且所述目标检测网络包括分类部分和定位部分，用于从上述目标特征图中分出目标类别信息以及目标位置信息，并将目标定位信息用于后续的属性识别以及目标跟踪；The target detection network is a deep learning network, and the target detection network includes a classification part and a positioning part, which are used to separate the target category information and target location information from the above-mentioned target feature map, and use the target positioning information for follow-up. Attribute identification and target tracking;
S4、通过对获取的目标特征图与目标检测结果进行属性识别获取目标属性 识别结果；S4. Obtain the target attribute identification result by performing attribute identification on the obtained target feature map and the target detection result;
将目标特征图和目标检测结果输入到属性识别网络中进行目标属性识别，且所述目标属性为目标的共有属性的不同表现形式，如人的年龄、服饰款式、发以及服饰颜色等；Input the target feature map and the target detection result into the attribute recognition network for target attribute identification, and the target attribute is the different manifestations of the common attribute of the target, such as the age of the person, clothing style, hair and clothing color, etc.;
S5、通过对获取的目标特征图、目标检测结果以及上帧目标跟踪信息进行目标跟踪分析获取目标跟踪结果；S5. Obtain the target tracking result by performing target tracking analysis on the obtained target feature map, the target detection result and the target tracking information of the previous frame;
将目标特征图、目标检测结果以及上帧目标跟踪信息输入到目标跟踪网络中进行目标跟踪分析，所述上帧目标跟踪信息为上一帧的目标检测、属性识别与跟踪结果，包括目标位置信息、特征图信息和赋予该目标的ID，该帧的目标特征图与上帧目标跟踪信息存储的所有目标特征图进行匹配，该帧的目标位置信息与上帧所有目标的位置信息进行匹配，并通过匹配值判断当前目标是否为上帧中的某一目标，当判断当前目标与上帧某一目标为同一目标时，将上帧该目标的ID赋予到该帧对应目标上；当判断无匹配对应目标后，将该目标赋予新的ID；Input the target feature map, the target detection result and the target tracking information of the previous frame into the target tracking network for target tracking analysis. The target tracking information of the previous frame is the target detection, attribute identification and tracking results of the previous frame, including the target position information. , feature map information and the ID given to the target, the target feature map of this frame is matched with all target feature maps stored in the target tracking information of the previous frame, and the target position information of this frame is matched with the position information of all targets in the previous frame, and Judging whether the current target is a target in the previous frame by the matching value, when it is judged that the current target and a target in the previous frame are the same target, the ID of the target in the previous frame is assigned to the corresponding target in the frame; when it is judged that there is no match After corresponding to the target, assign the target a new ID;
该帧处理完成后，保存处理信息，作为下一帧的目标跟踪处理的判断依据；After the frame processing is completed, the processing information is saved as the judgment basis for the target tracking processing of the next frame;
S6、对目标赋予ID后，并将获取的目标检测结果、目标属性识别结果和目标跟踪结果进行汇总输出。S6 , after assigning an ID to the target, summarize and output the obtained target detection result, target attribute recognition result and target tracking result.
基于上述方法，本实施例还提供一种目标检测、属性识别与跟踪***，包括图像采集设备和图片处理组件，其中：Based on the above method, this embodiment also provides a target detection, attribute recognition and tracking system, including an image acquisition device and a picture processing component, wherein:
所述图像采集设备用于采集目标原始图像；The image acquisition device is used to acquire the original image of the target;
所述图片处理组件用于对采集的目标原始图像进行处理，以进行目标跟踪；The image processing component is used to process the collected target original image to track the target;
所述图片处理组件包括特征图提取模块、目标检测模块、属性识别模块和 目标跟踪模块，其中：The picture processing component includes a feature map extraction module, a target detection module, an attribute recognition module and a target tracking module, wherein:
所述特征图提取模块用于将采集的目标原始图像进行处理成目标特征图；The feature map extraction module is used to process the collected target original image into a target feature map;
所述目标检测模块用于从处理的目标特征图中进行目标检测，获取目标检测结果；The target detection module is used to perform target detection from the processed target feature map, and obtain the target detection result;
所述属性识别模块用于通过目标特征图与目标检测结果进行目标的属性识别，获取目标属性识别结果；The attribute identification module is used to identify the attribute of the target through the target feature map and the target detection result, and obtain the target attribute identification result;
所述目标跟踪模块通过目标检测结果、上帧目标跟踪信息和特征图进行目标跟踪。The target tracking module performs target tracking through the target detection result, the target tracking information of the previous frame and the feature map.
本实施例中所述特征图提取模块包括目标特征提取网络，所述目标检测模块包括目标检测网络，所述属性识别模块包括属性识别网络，所述目标跟踪模块包括目标跟踪网络，且所述目标特征提取网络、属性识别网络和目标跟踪网络均采用卷积神经网络，所述目标跟踪网络采用深度神经网络；In this embodiment, the feature map extraction module includes a target feature extraction network, the target detection module includes a target detection network, the attribute identification module includes an attribute identification network, the target tracking module includes a target tracking network, and the target The feature extraction network, the attribute recognition network and the target tracking network all use convolutional neural networks, and the target tracking network uses a deep neural network;
对目标特征提取网络进行训练时，以RGB三维图像作为输入，并对图像进行标注，标注信息包括目标类别标签、目标位置标签和目标属性标签，然后再用目标检测网络和属性识别网络对目标特征提取网络进行联合训练，获取最优模型。When training the target feature extraction network, the RGB three-dimensional image is used as the input, and the image is annotated. Extract the network for joint training to obtain the optimal model.
以上所述实施例仅是为充分说明本发明而所举的较佳的实施例，本发明的保护范围不限于此。本技术领域的技术人员在本发明基础上所作的等同替代或变换，均在本发明的保护范围之内。本发明的保护范围以权利要求书为准。The above-mentioned embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or transformations made by those skilled in the art on the basis of the present invention are all within the protection scope of the present invention. The protection scope of the present invention is subject to the claims.

Claims (10)

  1. 一种目标检测、属性识别与跟踪方法，其特征在于：包括如下步骤：A method for target detection, attribute identification and tracking, characterized in that it comprises the following steps:
    S1、获取目标原始图像；S1. Obtain the original image of the target;
    S2、通过对获取的目标原始图像进行特征分析获取目标特征图；S2. Obtain a target feature map by performing feature analysis on the obtained target original image;
    S3、通过对获取的目标特征图进行目标检测获取目标检测结果；S3. Obtain a target detection result by performing target detection on the obtained target feature map;
    S4、通过对获取的目标特征图与目标检测结果进行属性识别获取目标属性识别结果；S4. Obtain the target attribute identification result by performing attribute identification on the obtained target feature map and the target detection result;
    S5、通过对获取的目标特征图、目标检测结果以及上帧目标跟踪信息进行目标跟踪分析获取目标跟踪结果；S5. Obtain the target tracking result by performing target tracking analysis on the obtained target feature map, the target detection result and the target tracking information of the previous frame;
    S6、对目标赋予ID后，并将获取的目标检测结果、目标属性识别结果和目标跟踪结果进行汇总输出。S6 , after assigning an ID to the target, summarize and output the obtained target detection result, target attribute recognition result and target tracking result.
  2. 根据权利要求1所述的方法，其特征在于：所述获取目标原始图像的方式通过高清摄像机或数码照相机。The method according to claim 1, wherein the method of acquiring the original image of the target is through a high-definition video camera or a digital camera.
  3. 根据权利要求1所述的方法，其特征在于：步骤S2中，通过训练好的特征提取网络对获取的原始图像进行特征分析，所述的目标特征图中包含目标类别信息、目标位置信息和目标属性信息。The method according to claim 1, wherein: in step S2, feature analysis is performed on the acquired original image through a trained feature extraction network, and the target feature map includes target category information, target location information and target property information.
  4. 根据权利要求3所述的方法，其特征在于：步骤S3中，通过目标检测网络对目标特征图进行目标检测，所述目标检测结果包括目标类型信息和目标位置信息，且所述目标位置信息用于属性识别和目标跟踪；The method according to claim 3, wherein: in step S3, target detection is performed on the target feature map through a target detection network, and the target detection result includes target type information and target position information, and the target position information uses for attribute identification and target tracking;
    所述目标检测网络采用深度学习网络。The target detection network adopts a deep learning network.
  5. 根据权利要求4所述的方法，其特征在于：步骤S4中，将目标特征图和目标检测结果输入到属性识别网络中进行目标属性识别，且所述目标属性为 目标的共有属性的不同表现形式。The method according to claim 4, wherein: in step S4, the target feature map and the target detection result are input into the attribute recognition network to identify the target attribute, and the target attribute is a different representation of the common attribute of the target .
  6. 根据权利要求5所述的方法，其特征在于：步骤S5中，将目标特征图、目标检测结果以及上帧目标跟踪信息输入到目标跟踪网络中进行目标跟踪分析，所述上帧目标跟踪信息为上一帧的目标检测、属性识别与跟踪结果，包括目标位置信息、特征图信息和赋予该目标的ID，该帧的目标特征图与上帧目标跟踪信息存储的所有目标特征图进行匹配，该帧的目标位置信息与上帧所有目标的位置信息进行匹配，并通过匹配值判断当前目标是否为上帧中的某一目标，当判断当前目标与上帧某一目标为同一目标时，将上帧该目标的ID赋予到该帧对应目标上；当判断无匹配对应目标后，将该目标赋予新的ID。The method according to claim 5, wherein: in step S5, the target feature map, the target detection result and the target tracking information of the previous frame are input into the target tracking network for target tracking analysis, and the target tracking information of the previous frame is: The target detection, attribute recognition and tracking results of the previous frame, including target location information, feature map information and the ID given to the target, the target feature map of this frame is matched with all target feature maps stored in the target tracking information of the previous frame. The target position information of the frame is matched with the position information of all targets in the previous frame, and the matching value is used to determine whether the current target is a target in the previous frame. The ID of the target of the frame is assigned to the corresponding target of the frame; when it is judged that there is no matching corresponding target, the target is given a new ID.
  7. 根据权利要求6所述的方法，其特征在于：所述特征提取网络采用卷积神经网络算法，在对特征提取网络进行训练时，输入信息为RGB值的三维原始图像，并对原始图像进行标注，标注信息包括目标类别标签、目标区域标签和目标属性标签，并通过目标检测网络和属性识别网络进行训练，获取优选训练模型。The method according to claim 6, wherein the feature extraction network adopts a convolutional neural network algorithm, and when training the feature extraction network, the input information is a three-dimensional original image of RGB values, and the original image is labeled , the labeling information includes target category label, target area label and target attribute label, and is trained through target detection network and attribute recognition network to obtain the optimal training model.
  8. 一种目标检测、属性识别与跟踪***，其特征在于：包括图像采集设备和图片处理组件，其中：A target detection, attribute recognition and tracking system, characterized in that it includes an image acquisition device and a picture processing component, wherein:
    所述图像采集设备用于采集目标原始图像；The image acquisition device is used to acquire the original image of the target;
    所述图片处理组件用于对采集的目标原始图像进行处理，以进行目标跟踪；The image processing component is used to process the collected target original image to track the target;
    所述图片处理组件包括特征图提取模块、目标检测模块、属性识别模块和目标跟踪模块，其中：The image processing component includes a feature map extraction module, a target detection module, an attribute recognition module and a target tracking module, wherein:
    所述特征图提取模块用于将采集的目标原始图像进行处理成目标特征图；The feature map extraction module is used to process the collected target original image into a target feature map;
    所述目标检测模块用于从处理的目标特征图中进行目标检测，获取目标检测结果；The target detection module is used to perform target detection from the processed target feature map, and obtain the target detection result;
    所述属性识别模块用于通过目标特征图与目标检测结果进行目标的属性识别，获取目标属性识别结果；The attribute identification module is used to identify the attribute of the target through the target feature map and the target detection result, and obtain the target attribute identification result;
    所述目标跟踪模块通过目标检测结果、上帧目标跟踪信息和特征图进行目标跟踪。The target tracking module performs target tracking through the target detection result, the target tracking information of the previous frame and the feature map.
  9. 根据权利要求8所述的***，其特征在于：所述特征图提取模块包括目标特征提取网络，所述目标检测模块包括目标检测网络，所述属性识别模块包括属性识别网络，所述目标跟踪模块包括目标跟踪网络，且所述目标特征提取网络、属性识别网络和目标跟踪网络均采用卷积神经网络；The system according to claim 8, wherein the feature map extraction module comprises a target feature extraction network, the target detection module comprises a target detection network, the attribute recognition module comprises an attribute recognition network, and the target tracking module Including a target tracking network, and the target feature extraction network, attribute recognition network and target tracking network all use convolutional neural networks;
    对目标特征提取网络进行训练时，以RGB三维图像作为输入，并对图像进行标注，标注信息包括目标类别标签、目标位置标签和目标属性标签，然后再用目标检测网络和属性识别网络对目标特征提取网络进行联合训练，获取最优模型。When training the target feature extraction network, the RGB three-dimensional image is used as the input, and the image is annotated. Extract the network for joint training to obtain the optimal model.
  10. 根据权利要求9所述的***，其特征在于：所述图片处理组件中，每个目标均对应唯一一个ID，在目标跟踪模块中，通过与上帧目标跟踪信息进行对比判断，当判断为与上帧某一目标为同一目标时，该帧目标继承上帧对应目标的ID，当判断不存在对应目标时，赋予该目标新的ID。The system according to claim 9, wherein: in the picture processing component, each target corresponds to a unique ID, and in the target tracking module, the target tracking information of the previous frame is compared and judged. When a target in the previous frame is the same target, the target in the frame inherits the ID of the corresponding target in the previous frame, and when it is judged that there is no corresponding target, a new ID is given to the target.
PCT/CN2021/117025 2021-04-09 2021-09-07 Object detecting, attribute identifying and tracking method and system WO2022213540A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110380619.X 2021-04-09
CN202110380619.XA CN113065568A (en) 2021-04-09 2021-04-09 Target detection, attribute identification and tracking method and system

Publications (1)

Publication Number Publication Date
WO2022213540A1 true WO2022213540A1 (en) 2022-10-13

Family

ID=76566244

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/117025 WO2022213540A1 (en) 2021-04-09 2021-09-07 Object detecting, attribute identifying and tracking method and system

Country Status (2)

Country Link
CN (1) CN113065568A (en)
WO (1) WO2022213540A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113065568A (en) * 2021-04-09 2021-07-02 神思电子技术股份有限公司 Target detection, attribute identification and tracking method and system
CN113610362B (en) * 2021-07-20 2023-08-08 苏州超集信息科技有限公司 Deep learning assembly line-based product tracing method and system
CN114898108B (en) * 2022-03-30 2023-01-06 哈尔滨工业大学 CNN model lightweight method based on FPGA, target detection method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109711320A (en) * 2018-12-24 2019-05-03 兴唐通信科技有限公司 A kind of operator on duty's unlawful practice detection method and system
CN110188596A (en) * 2019-01-04 2019-08-30 北京大学 Monitor video pedestrian real-time detection, Attribute Recognition and tracking and system based on deep learning
CN111460926A (en) * 2020-03-16 2020-07-28 华中科技大学 Video pedestrian detection method fusing multi-target tracking clues
US20200272902A1 (en) * 2017-09-04 2020-08-27 Huawei Technologies Co., Ltd. Pedestrian attribute identification and positioning method and convolutional neural network system
CN113065568A (en) * 2021-04-09 2021-07-02 神思电子技术股份有限公司 Target detection, attribute identification and tracking method and system

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107066953B (en) * 2017-03-22 2019-06-07 北京邮电大学 A kind of vehicle cab recognition towards monitor video, tracking and antidote and device
CN108875456B (en) * 2017-05-12 2022-02-18 北京旷视科技有限公司 Object detection method, object detection apparatus, and computer-readable storage medium
KR101941994B1 (en) * 2018-08-24 2019-01-24 전북대학교산학협력단 System for pedestrian detection and attribute extraction based on a joint deep network
CN112507835B (en) * 2020-12-01 2022-09-20 燕山大学 Method and system for analyzing multi-target object behaviors based on deep learning technology
CN112528977B (en) * 2021-02-10 2021-07-02 北京优幕科技有限责任公司 Target detection method, target detection device, electronic equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200272902A1 (en) * 2017-09-04 2020-08-27 Huawei Technologies Co., Ltd. Pedestrian attribute identification and positioning method and convolutional neural network system
CN109711320A (en) * 2018-12-24 2019-05-03 兴唐通信科技有限公司 A kind of operator on duty's unlawful practice detection method and system
CN110188596A (en) * 2019-01-04 2019-08-30 北京大学 Monitor video pedestrian real-time detection, Attribute Recognition and tracking and system based on deep learning
CN111460926A (en) * 2020-03-16 2020-07-28 华中科技大学 Video pedestrian detection method fusing multi-target tracking clues
CN113065568A (en) * 2021-04-09 2021-07-02 神思电子技术股份有限公司 Target detection, attribute identification and tracking method and system

Also Published As

Publication number Publication date
CN113065568A (en) 2021-07-02

Similar Documents

Publication Publication Date Title
WO2022213540A1 (en) Object detecting, attribute identifying and tracking method and system
CN108596277B (en) Vehicle identity recognition method and device and storage medium
US10089556B1 (en) Self-attention deep neural network for action recognition in surveillance videos
Fernandes et al. Predicting heart rate variations of deepfake videos using neural ode
WO2021047232A1 (en) Interaction behavior recognition method, apparatus, computer device, and storage medium
CN109644255B (en) Method and apparatus for annotating a video stream comprising a set of frames
US9560323B2 (en) Method and system for metadata extraction from master-slave cameras tracking system
CN109145759B (en) Vehicle attribute identification method, device, server and storage medium
Bonomi et al. Dynamic texture analysis for detecting fake faces in video sequences
Liu et al. Weakly-supervised salient object detection with saliency bounding boxes
CN111797653A (en) Image annotation method and device based on high-dimensional image
CN108280426B (en) Dark light source expression identification method and device based on transfer learning
WO2012139228A1 (en) Video-based detection of multiple object types under varying poses
CN111209818A (en) Video individual identification method, system, equipment and readable storage medium
US20220301317A1 (en) Method and device for constructing object motion trajectory, and computer storage medium
CN110096945B (en) Indoor monitoring video key frame real-time extraction method based on machine learning
CN109068145A (en) Distribution type intelligent video analysis system, method, apparatus, equipment and storage medium
CN111815528A (en) Bad weather image classification enhancement method based on convolution model and feature fusion
CN109002776B (en) Face recognition method, system, computer device and computer-readable storage medium
CN111428664A (en) Real-time multi-person posture estimation method based on artificial intelligence deep learning technology for computer vision
CN110969173B (en) Target classification method and device
WO2022205329A1 (en) Object detection method, object detection apparatus, and object detection system
CN112488165A (en) Infrared pedestrian identification method and system based on deep learning model
CN112836682A (en) Method and device for identifying object in video, computer equipment and storage medium
WO2022228325A1 (en) Behavior detection method, electronic device, and computer readable storage medium

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: 21935759

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: 21935759

Country of ref document: EP

Kind code of ref document: A1