CN110942003A - Personnel track searching method and system - Google Patents
Personnel track searching method and system Download PDFInfo
- Publication number
- CN110942003A CN110942003A CN201911140827.1A CN201911140827A CN110942003A CN 110942003 A CN110942003 A CN 110942003A CN 201911140827 A CN201911140827 A CN 201911140827A CN 110942003 A CN110942003 A CN 110942003A
- Authority
- CN
- China
- Prior art keywords
- identity
- human body
- face
- target
- features
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a personnel trajectory searching method and a personnel trajectory searching system. The person track searching method comprises the following steps: extracting a plurality of pictures from the acquired video stream; generating a face feature and a human body feature corresponding to each identity ID according to the optimal picture extracted from the plurality of pictures; when the maximum value in the similarity corresponding to the face features is larger than a preset face threshold value, recording the identity ID corresponding to the face features; when the maximum value in the similarity corresponding to the human body features is larger than a preset human body threshold value, recording the identity ID corresponding to the human body features; determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features; and acquiring a personnel track corresponding to the target identity ID. The invention can improve the searching precision and expand the application scene.
Description
Technical Field
The invention relates to the technical field of trajectory search, in particular to a personnel trajectory search method and a personnel trajectory search system.
Background
With the development of the artificial intelligence deep learning technology and the improvement of the parallel computing capability of the GPU, the development of the artificial intelligence technology in the security field makes a breakthrough progress, wherein representative technologies comprise face recognition technology, target tracking technology and pedestrian re-recognition technology.
For the track searching technology based on face recognition, higher recognition accuracy can be achieved on the premise that the face can be captured. In an actual application scene, pedestrians often cannot always face the camera, and if the pedestrians wear a hat, wear a mask, wear an umbrella, face sideways, head down, shield and the like, the pedestrians cannot catch the face, and therefore the application area of the track search technology based on face recognition is extremely narrow.
Disclosure of Invention
The embodiment of the invention mainly aims to provide a personnel track searching method and a personnel track searching system so as to improve the searching precision and expand the application scene.
In order to achieve the above object, an embodiment of the present invention provides a method for searching a person trajectory, including:
extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID;
generating a face feature and a human body feature corresponding to each identity ID according to the optimal picture extracted from the plurality of pictures;
calculating the similarity between the human face features and each target human face feature to be searched;
when the maximum value in the similarity corresponding to the face features is larger than a preset face threshold value, recording the identity ID corresponding to the face features;
calculating the similarity between the human body features and each target human body feature to be searched;
when the maximum value in the similarity corresponding to the human body features is larger than a preset human body threshold value, recording the identity ID corresponding to the human body features;
determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features;
and acquiring a personnel track corresponding to the target identity ID.
The embodiment of the present invention further provides a personnel trajectory searching system, including:
the extraction unit is used for extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID;
the feature generation unit is used for generating the face features and the human body features corresponding to each identity ID according to the optimal picture extracted from the multiple pictures;
the face calculation unit is used for calculating the similarity between the face features and each target face feature to be searched;
the face recording unit is used for recording the identity ID corresponding to the face feature when the maximum value of the similarity corresponding to the face feature is larger than a preset face threshold value;
the human body calculating unit is used for calculating the similarity between the human body characteristics and each target human body characteristic to be searched;
the human body recording unit is used for recording the identity ID corresponding to the human body characteristic when the maximum value in the similarity corresponding to the human body characteristic is larger than a preset human body threshold value;
the target determining unit is used for determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features;
and the personnel track unit is used for acquiring the personnel track corresponding to the target identity ID.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the steps of the personnel trajectory searching method are realized when the processor executes the computer program.
The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the person trajectory searching method are implemented.
The personnel track searching method and the personnel track searching system firstly extract a plurality of pictures from the acquired video stream, then generate the face characteristics and the human body characteristics corresponding to each identity ID according to a plurality of optimal pictures, then determine the target identity ID according to the similarity between the face characteristics and the face characteristics of each target to be searched and the similarity between the human body characteristics and the human body characteristics of each target to be searched, and finally acquire the personnel track corresponding to the target identity ID, so that the searching precision can be improved, and the application scene can be enlarged.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for searching a trajectory of a person in an embodiment of the present invention;
fig. 2 is a block diagram of a human trajectory search system in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
In view of the low search precision and the narrow application range in the prior art, the embodiment of the invention provides a personnel trajectory search method to improve the search precision and expand the application scenarios. The present invention will be described in detail below with reference to the accompanying drawings.
FIG. 1 is a flowchart of a method for searching a trajectory of a person in an embodiment of the present invention. As shown in fig. 1, the method for searching a person trajectory includes:
s101: extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID.
In specific implementation, it is necessary to decode a video stream first and then extract a plurality of pictures from the decoded video stream.
In an embodiment, before performing S101, the method further includes: determining the persons in each picture according to the YOLOV3 algorithm; the person in each picture is assigned an identity ID according to the DeepSort algorithm.
S102: and generating the face features and the human body features corresponding to each identity ID according to the optimal pictures extracted from the multiple pictures.
Wherein, the optimal picture can be extracted through the MTCNN algorithm. The optimal pictures are pictures which are free of blocking of human bodies and human faces and clear in pixels, and part of the optimal pictures comprise side pictures, front pictures or back pictures. One picture can be taken as the optimal picture from each of the left, middle, right, top, and bottom of the camera that takes the video stream. The human face features and the human body features are generated according to a small number of optimal pictures, so that the size of a feature library can be reduced, and the search response speed is increased.
S103: and calculating the similarity between the face features and each target face feature to be searched.
The similarity between the face features and each target face feature to be searched can be calculated through a convolutional neural network of a FaceNet algorithm.
S104: and when the maximum value in the similarity corresponding to the face features is larger than a preset face threshold value, recording the identity ID corresponding to the face features.
S105: and calculating the similarity between the human body features and each target human body feature to be searched.
The similarity between the human body features and each target human body feature to be searched can be calculated through a multi-granularity network. The multi-granularity network can firstly carry out three-level granularity segmentation on a human body, then carry out feature extraction through the three-branch deep neural network and integrate all features to form final features, not only can be compatible with the overall body shape, contour and color features of the human body, but also can grasp various detailed features (such as hairstyle, glasses, shoes, clothing trademarks, accessories and the like), and the human body identification precision is greatly improved.
S106: and when the maximum value in the similarity corresponding to the human body features is larger than a preset human body threshold value, recording the identity ID corresponding to the human body features.
S107: and determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features.
In one embodiment, S107 includes: acquiring a union set of an identity ID corresponding to the human face features and an identity ID corresponding to the human body features; the identity ID in the union is taken as the target identity ID.
S108: and acquiring a personnel track corresponding to the target identity ID.
Each picture corresponds to one region position point and one shooting time;
s108 includes: sequencing the multiple pictures according to the shooting time of the multiple pictures corresponding to the target identity ID; and sequentially connecting the area position points corresponding to the sequenced pictures to obtain the personnel track.
The execution subject of the person trajectory search method shown in fig. 1 may be a computer. As can be seen from the flow shown in fig. 1, the person trajectory searching method according to the embodiment of the present invention extracts a plurality of pictures from the acquired video stream, generates a face feature and a body feature corresponding to each identity ID according to a plurality of optimal pictures, determines a target identity ID according to the similarity between the face feature and each target face feature to be searched and the similarity between the body feature and each target body feature to be searched, and finally acquires a person trajectory corresponding to the target identity ID, which can improve the searching accuracy and expand the application scenarios.
The specific process of the embodiment of the invention is as follows:
1. and decoding the acquired video stream, and extracting a plurality of pictures from the decoded video stream.
2. Determining the persons in each picture according to the YOLOV3 algorithm; the person in each picture is assigned an identity ID according to the DeepSort algorithm.
3. And extracting an optimal picture through an MTCNN algorithm.
4. And generating the face features and the human body features corresponding to each identity ID according to the optimal picture.
5. And calculating the similarity between the face features and each target face feature to be searched through a convolution neural network of a faceNet algorithm. And when the maximum value in the similarity corresponding to the face features is larger than a preset face threshold value, recording the identity ID corresponding to the face features.
6. And calculating the similarity between the human body characteristics and each target human body characteristic to be searched through a multi-granularity network. And when the maximum value in the similarity corresponding to the human body features is larger than a preset human body threshold value, recording the identity ID corresponding to the human body features.
7. And taking the union of the identity ID corresponding to the human face features and the identity ID corresponding to the human body features as the target identity ID.
8. And sequencing the plurality of pictures according to the shooting time of the plurality of pictures corresponding to the target identity ID.
9. And sequentially connecting the area position points corresponding to the sequenced pictures to obtain the personnel track.
To sum up, the person trajectory searching method of the embodiment of the present invention extracts a plurality of pictures from the acquired video stream, generates a face feature and a body feature corresponding to each identity ID according to a plurality of optimal pictures, determines a target identity ID according to the similarity between the face feature and each target face feature to be searched and the similarity between the body feature and each target body feature to be searched, and finally acquires a person trajectory corresponding to the target identity ID, which can improve the searching accuracy and expand the application scenarios. In addition, the invention can also improve the search response speed.
Based on the same inventive concept, the embodiment of the invention also provides a personnel trajectory searching system, and as the principle of solving the problems of the system is similar to the personnel trajectory searching method, the implementation of the system can refer to the implementation of the method, and repeated parts are not repeated.
Fig. 2 is a block diagram of a human trajectory search system in an embodiment of the present invention. As shown in fig. 2, the person trajectory search system includes:
the extraction unit is used for extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID;
the feature generation unit is used for generating the face features and the human body features corresponding to each identity ID according to the optimal picture extracted from the multiple pictures;
the face calculation unit is used for calculating the similarity between the face features and each target face feature to be searched;
the face recording unit is used for recording the identity ID corresponding to the face feature when the maximum value of the similarity corresponding to the face feature is larger than a preset face threshold value;
the human body calculating unit is used for calculating the similarity between the human body characteristics and each target human body characteristic to be searched;
the human body recording unit is used for recording the identity ID corresponding to the human body characteristic when the maximum value in the similarity corresponding to the human body characteristic is larger than a preset human body threshold value;
the target determining unit is used for determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features;
and the personnel track unit is used for acquiring the personnel track corresponding to the target identity ID.
In one embodiment, the method further comprises the following steps:
a determining unit, which is used for determining the person in each picture according to the Yolov3 algorithm;
and the identity distribution unit is used for distributing the identity ID to the personnel in each picture according to the Deepsort algorithm.
In one embodiment, each picture corresponds to one region position point and one shooting time;
the person trajectory unit is specifically configured to:
sequencing the multiple pictures according to the shooting time of the multiple pictures corresponding to the target identity ID;
and sequentially connecting the area position points corresponding to the sequenced pictures to obtain the personnel track.
In one embodiment, the target determination unit is specifically configured to:
acquiring a union set of an identity ID corresponding to the human face features and an identity ID corresponding to the human body features;
the identity ID in the union is taken as the target identity ID.
To sum up, the personnel trajectory search system of the embodiment of the invention extracts a plurality of pictures from the acquired video stream, generates the face features and the body features corresponding to each identity ID according to a plurality of optimal pictures, determines the target identity ID according to the similarity between the face features and the face features of each target to be searched and the similarity between the body features and the body features of each target to be searched, and finally acquires the personnel trajectory corresponding to the target identity ID, thereby improving the search precision and expanding the application scene.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the computer program to implement all or part of the contents of the person trajectory search method, for example, the processor executes the computer program to implement the following contents:
extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID;
generating a face feature and a human body feature corresponding to each identity ID according to the optimal picture extracted from the plurality of pictures;
calculating the similarity between the human face features and each target human face feature to be searched;
when the maximum value in the similarity corresponding to the face features is larger than a preset face threshold value, recording the identity ID corresponding to the face features;
calculating the similarity between the human body features and each target human body feature to be searched;
when the maximum value in the similarity corresponding to the human body features is larger than a preset human body threshold value, recording the identity ID corresponding to the human body features;
determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features;
and acquiring a personnel track corresponding to the target identity ID.
To sum up, the computer device of the embodiment of the present invention extracts a plurality of pictures from the acquired video stream, generates a face feature and a body feature corresponding to each identity ID according to a plurality of optimal pictures, determines a target identity ID according to a similarity between the face feature and each target face feature to be searched and a similarity between the body feature and each target body feature to be searched, and finally acquires a staff track corresponding to the target identity ID, thereby improving the search accuracy and expanding the application scenarios.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, may implement all or part of the content of the person trajectory search method, for example, when the processor executes the computer program, the following content may be implemented:
extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID;
generating a face feature and a human body feature corresponding to each identity ID according to the optimal picture extracted from the plurality of pictures;
calculating the similarity between the human face features and each target human face feature to be searched;
when the maximum value in the similarity corresponding to the face features is larger than a preset face threshold value, recording the identity ID corresponding to the face features;
calculating the similarity between the human body features and each target human body feature to be searched;
when the maximum value in the similarity corresponding to the human body features is larger than a preset human body threshold value, recording the identity ID corresponding to the human body features;
determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features;
and acquiring a personnel track corresponding to the target identity ID.
To sum up, the computer-readable storage medium according to the embodiment of the present invention extracts a plurality of pictures from the acquired video stream, generates a face feature and a body feature corresponding to each identity ID according to a plurality of optimal pictures, determines a target identity ID according to a similarity between the face feature and each target face feature to be searched and a similarity between the body feature and each target body feature to be searched, and finally acquires a staff track corresponding to the target identity ID, so that the search accuracy can be improved, and the application scenario can be expanded.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Those of skill in the art will further appreciate that the various illustrative logical blocks, units, and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, elements, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.
The various illustrative logical blocks, or elements, or devices described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be located in a user terminal. In the alternative, the processor and the storage medium may reside in different components in a user terminal.
In one or more exemplary designs, the functions described above in connection with the embodiments of the invention may be implemented in hardware, software, firmware, or any combination of the three. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media that facilitate transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store program code in the form of instructions or data structures and which can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Additionally, any connection is properly termed a computer-readable medium, and, thus, is included if the software is transmitted from a website, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wirelessly, e.g., infrared, radio, and microwave. Such discs (disk) and disks (disc) include compact disks, laser disks, optical disks, DVDs, floppy disks and blu-ray disks where disks usually reproduce data magnetically, while disks usually reproduce data optically with lasers. Combinations of the above may also be included in the computer-readable medium.
Claims (10)
1. A person trajectory search method is characterized by comprising the following steps:
extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID;
generating a face feature and a human body feature corresponding to each identity ID according to the optimal picture extracted from the plurality of pictures;
calculating the similarity between the face features and each target face feature to be searched;
when the maximum value in the similarity corresponding to the face features is larger than a preset face threshold value, recording the identity ID corresponding to the face features;
calculating the similarity between the human body features and each target human body feature to be searched;
when the maximum value in the similarity corresponding to the human body features is larger than a preset human body threshold value, recording the identity ID corresponding to the human body features;
determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features;
and acquiring a personnel track corresponding to the target identity ID.
2. The person trajectory search method according to claim 1, further comprising:
determining the persons in each picture according to the YOLOV3 algorithm;
the person in each picture is assigned an identity ID according to the DeepSort algorithm.
3. The person trajectory search method according to claim 1, wherein each picture corresponds to one region position point and one shooting time;
acquiring the staff track corresponding to the target identity ID comprises the following steps:
sequencing the multiple pictures according to the shooting time of the multiple pictures corresponding to the target identity ID;
and sequentially connecting the area position points corresponding to the sequenced pictures to obtain the personnel track.
4. The person trajectory searching method according to claim 1, wherein determining the target identity ID includes:
acquiring a union set of the identity ID corresponding to the face feature and the identity ID corresponding to the human body feature;
and taking the identity ID in the union set as a target identity ID.
5. A person trajectory search system, comprising:
the extraction unit is used for extracting a plurality of pictures from the acquired video stream; each person in each picture corresponds to an identity ID;
the feature generation unit is used for generating the face feature and the human body feature corresponding to each identity ID according to the optimal picture extracted from the multiple pictures;
the face calculation unit is used for calculating the similarity between the face features and each target face feature to be searched;
the face recording unit is used for recording the identity ID corresponding to the face feature when the maximum value in the similarity corresponding to the face feature is larger than a preset face threshold value;
the human body calculating unit is used for calculating the similarity between the human body characteristics and each target human body characteristic to be searched;
the human body recording unit is used for recording the identity ID corresponding to the human body characteristic when the maximum value in the similarity corresponding to the human body characteristic is larger than a preset human body threshold value;
the target determining unit is used for determining a target identity ID according to the identity ID corresponding to the human face features and the identity ID corresponding to the human body features;
and the personnel track unit is used for acquiring the personnel track corresponding to the target identity ID.
6. The person trajectory search system according to claim 5, further comprising:
a determining unit, which is used for determining the person in each picture according to the Yolov3 algorithm;
and the identity distribution unit is used for distributing the identity ID to the personnel in each picture according to the Deepsort algorithm.
7. The person trajectory search system according to claim 5, wherein each picture corresponds to one region position point and one shooting time;
the person trajectory unit is specifically configured to:
sequencing the multiple pictures according to the shooting time of the multiple pictures corresponding to the target identity ID;
and sequentially connecting the area position points corresponding to the sequenced pictures to obtain the personnel track.
8. The person trajectory search system according to claim 5, wherein the target determination unit is specifically configured to:
acquiring a union set of the identity ID corresponding to the face feature and the identity ID corresponding to the human body feature;
and taking the identity ID in the union set as a target identity ID.
9. Computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor realizes the steps of the person trajectory searching method of any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the person trajectory search method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911140827.1A CN110942003A (en) | 2019-11-20 | 2019-11-20 | Personnel track searching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911140827.1A CN110942003A (en) | 2019-11-20 | 2019-11-20 | Personnel track searching method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110942003A true CN110942003A (en) | 2020-03-31 |
Family
ID=69906983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911140827.1A Pending CN110942003A (en) | 2019-11-20 | 2019-11-20 | Personnel track searching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110942003A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476820A (en) * | 2020-04-01 | 2020-07-31 | 深圳力维智联技术有限公司 | Method and device for positioning tracked target |
| CN112148909A (en) * | 2020-09-18 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for searching similar pictures |
| CN112329521A (en) * | 2020-09-24 | 2021-02-05 | 上海品览数据科技有限公司 | Multi-target tracking video shop-patrol method based on deep learning |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016374A (en) * | 2017-04-12 | 2017-08-04 | 电子科技大学 | Intelligent Measurement tracking and the generation method of space-time track towards specific objective |
| CN107644204A (en) * | 2017-09-12 | 2018-01-30 | 南京凌深信息科技有限公司 | A kind of human bioequivalence and tracking for safety-protection system |
| CN109102531A (en) * | 2018-08-21 | 2018-12-28 | 北京深瞐科技有限公司 | A kind of target trajectory method for tracing and device |
| CN109214276A (en) * | 2018-07-23 | 2019-01-15 | 武汉虹信技术服务有限责任公司 | A kind of system and method for the target person track following based on face recognition technology |
| CN109327683A (en) * | 2018-10-29 | 2019-02-12 | 重庆中科云丛科技有限公司 | A kind of method for tracing, system, unmanned plane and server |
| CN109426787A (en) * | 2017-08-31 | 2019-03-05 | 杭州海康威视数字技术股份有限公司 | A kind of human body target track determines method and device |
| CN109753920A (en) * | 2018-12-29 | 2019-05-14 | 深圳市商汤科技有限公司 | A kind of pedestrian recognition method and device |
| CN109815829A (en) * | 2018-12-28 | 2019-05-28 | 上海依图网络科技有限公司 | A kind of method and device of determining passerby track |
| CN109858354A (en) * | 2018-12-27 | 2019-06-07 | 厦门市美亚柏科信息股份有限公司 | A kind of face identity library, the foundation of track table and face track querying method and system |
| WO2019109246A1 (en) * | 2017-12-05 | 2019-06-13 | 深圳前海达闼云端智能科技有限公司 | Picture lookup method and device |
| CN109978918A (en) * | 2019-03-21 | 2019-07-05 | 腾讯科技（深圳）有限公司 | A kind of trajectory track method, apparatus and storage medium |
| CN110163146A (en) * | 2019-05-21 | 2019-08-23 | 银河水滴科技（北京）有限公司 | A kind of monitoring method and device based on characteristics of human body |
| CN110310164A (en) * | 2019-07-30 | 2019-10-08 | 广州云从信息科技有限公司 | Image processing system, method, platform, machine readable media and equipment |
| CN110427905A (en) * | 2019-08-08 | 2019-11-08 | 北京百度网讯科技有限公司 | Pedestrian tracting method, device and terminal |
-
2019
- 2019-11-20 CN CN201911140827.1A patent/CN110942003A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016374A (en) * | 2017-04-12 | 2017-08-04 | 电子科技大学 | Intelligent Measurement tracking and the generation method of space-time track towards specific objective |
| CN109426787A (en) * | 2017-08-31 | 2019-03-05 | 杭州海康威视数字技术股份有限公司 | A kind of human body target track determines method and device |
| CN107644204A (en) * | 2017-09-12 | 2018-01-30 | 南京凌深信息科技有限公司 | A kind of human bioequivalence and tracking for safety-protection system |
| WO2019109246A1 (en) * | 2017-12-05 | 2019-06-13 | 深圳前海达闼云端智能科技有限公司 | Picture lookup method and device |
| CN109214276A (en) * | 2018-07-23 | 2019-01-15 | 武汉虹信技术服务有限责任公司 | A kind of system and method for the target person track following based on face recognition technology |
| CN109102531A (en) * | 2018-08-21 | 2018-12-28 | 北京深瞐科技有限公司 | A kind of target trajectory method for tracing and device |
| CN109327683A (en) * | 2018-10-29 | 2019-02-12 | 重庆中科云丛科技有限公司 | A kind of method for tracing, system, unmanned plane and server |
| CN109858354A (en) * | 2018-12-27 | 2019-06-07 | 厦门市美亚柏科信息股份有限公司 | A kind of face identity library, the foundation of track table and face track querying method and system |
| CN109815829A (en) * | 2018-12-28 | 2019-05-28 | 上海依图网络科技有限公司 | A kind of method and device of determining passerby track |
| CN109753920A (en) * | 2018-12-29 | 2019-05-14 | 深圳市商汤科技有限公司 | A kind of pedestrian recognition method and device |
| CN109978918A (en) * | 2019-03-21 | 2019-07-05 | 腾讯科技（深圳）有限公司 | A kind of trajectory track method, apparatus and storage medium |
| CN110163146A (en) * | 2019-05-21 | 2019-08-23 | 银河水滴科技（北京）有限公司 | A kind of monitoring method and device based on characteristics of human body |
| CN110310164A (en) * | 2019-07-30 | 2019-10-08 | 广州云从信息科技有限公司 | Image processing system, method, platform, machine readable media and equipment |
| CN110427905A (en) * | 2019-08-08 | 2019-11-08 | 北京百度网讯科技有限公司 | Pedestrian tracting method, device and terminal |
Non-Patent Citations (2)
| Title |
|---|
| THANH DUC NGO 等: "Face Retrieval in Large-Scale New Video Datasets", 《IEICE TRANS INF&SYST》 * |
| XU ZHANG 等: "Multi-target Tracking of Surveillance Video with Differential YOLO and DeepSort", 《ELEVENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2019)》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476820A (en) * | 2020-04-01 | 2020-07-31 | 深圳力维智联技术有限公司 | Method and device for positioning tracked target |
| CN111476820B (en) * | 2020-04-01 | 2023-11-03 | 深圳力维智联技术有限公司 | Method and device for positioning tracked target |
| CN112148909A (en) * | 2020-09-18 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for searching similar pictures |
| CN112148909B (en) * | 2020-09-18 | 2024-03-29 | 微梦创科网络科技（中国）有限公司 | Method and system for searching similar pictures |
| CN112329521A (en) * | 2020-09-24 | 2021-02-05 | 上海品览数据科技有限公司 | Multi-target tracking video shop-patrol method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110235138B (en) | System and method for appearance search | |
| US10733421B2 (en) | Method for processing video, electronic device and storage medium | |
| US20170300744A1 (en) | Method and apparatus for determining identity identifier of face in face image, and terminal | |
| US11908238B2 (en) | Methods and systems for facial point-of-recognition (POR) provisioning | |
| CN110942003A (en) | Personnel track searching method and system | |
| CN109829396B (en) | Face recognition motion blur processing method, device, equipment and storage medium | |
| CN108664526B (en) | Retrieval method and device | |
| CN112016353B (en) | Method and device for carrying out identity recognition on face image based on video | |
| Huang et al. | Spontaneous facial micro-expression analysis using spatiotemporal local radon-based binary pattern | |
| CN112487886A (en) | Method and device for identifying face with shielding, storage medium and terminal | |
| CN113705290A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN113780243B (en) | Training method, device, equipment and storage medium for pedestrian image recognition model | |
| CN109858354A (en) | A kind of face identity library, the foundation of track table and face track querying method and system | |
| CN111597910A (en) | Face recognition method, face recognition device, terminal equipment and medium | |
| CN112132103A (en) | Video face detection and recognition method and system | |
| CN111444817B (en) | Character image recognition method and device, electronic equipment and storage medium | |
| KR20220042335A (en) | Automatic Sign Language Recognition Method and System | |
| Chen et al. | Efficient activity detection in untrimmed video with max-subgraph search | |
| CN105844204B (en) | Human behavior recognition method and device | |
| Ke et al. | Human action recognition based on 3d human modeling and cyclic HMMs | |
| KR102277929B1 (en) | Real time face masking system based on face recognition and real time face masking method using the same | |
| Mi et al. | Recognizing actions in wearable-camera videos by training classifiers on fixed-camera videos | |
| CN111414959A (en) | Image recognition method and device, computer readable medium and electronic equipment | |
| CN113628248B (en) | Pedestrian residence time length determining method and device and computer readable storage medium | |
| Morerio et al. | Optimizing superpixel clustering for real-time egocentric-vision applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220915 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200331 |