CN111738043A - Pedestrian re-identification method and device - Google Patents
Pedestrian re-identification method and device Download PDFInfo
- Publication number
- CN111738043A CN111738043A CN201911259371.0A CN201911259371A CN111738043A CN 111738043 A CN111738043 A CN 111738043A CN 201911259371 A CN201911259371 A CN 201911259371A CN 111738043 A CN111738043 A CN 111738043A
- Authority
- CN
- China
- Prior art keywords
- image set
- identified
- pedestrian
- identification
- target
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a pedestrian re-identification method and a device, wherein the pedestrian re-identification method comprises the following steps: acquiring an image set to be identified; extracting the image set to be identified according to a space-time model to obtain a first image set to be identified; obtaining a target image set to be identified according to the first image set to be identified; acquiring a first target feature of the target image set to be recognized; and carrying out pedestrian re-identification on the first target characteristic according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result. The method optimizes deep learning through the space-time model and the self-attention mechanism, can more effectively utilize video information by extracting the space-time information of the video, thereby improving the accuracy of pedestrian re-identification of the video, and can enable the pedestrian re-identification model to pay attention to the key frame information of the video content at each moment through the self-attention mechanism, thereby improving the accuracy of pedestrian re-identification.
Description
Technical Field
The invention relates to the field of video monitoring, in particular to a pedestrian re-identification method and device.
Background
The pedestrian re-identification is a technology for identifying the identity of a pedestrian under different camera scenes, is a very important part in a video monitoring analysis technology, and plays an important role in the aspects of intelligent video monitoring, crime prevention, social security maintenance and the like.
In recent years, a deep learning method is widely applied to a plurality of computer vision fields such as image classification and target identification, and compared with a traditional manual design method, the deep learning method can obtain better performance, however, due to the fact that a monitoring video is complex, the monitoring video is affected by factors such as illumination, weather, visual angle transformation and pedestrian posture which are changed violently, and the resolution of imaging equipment is poor, the same pedestrian is difficult to identify under different cameras, and the accuracy of pedestrian re-identification is low.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to overcome the defect of low accuracy of pedestrian re-identification in the prior art, and to provide a method and a device for pedestrian re-identification.
According to a first aspect, an embodiment of the present invention discloses a pedestrian re-identification method, including the following steps: acquiring an image set to be identified; extracting the image set to be identified according to a space-time model to obtain a first image set to be identified; obtaining a target image set to be identified according to the first image set to be identified; acquiring a first target feature of the target image set to be recognized; and carrying out pedestrian re-identification on the first target characteristic according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result.
With reference to the first aspect, in a first implementation manner of the first aspect, the obtaining a target image set to be recognized according to the first image set to be recognized includes: carrying out pedestrian detection on the first image set to be recognized to obtain a second image set to be recognized; and screening the second image set to be identified to obtain the target identification image set.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the spatio-temporal model is built by: acquiring space-time information according to the image to be identified, wherein the space-time information comprises space information of camera equipment and pedestrian time information; and constructing a space-time model according to the space-time information.
With reference to the second embodiment of the first aspect, in a third embodiment of the first aspect, the pedestrian re-identification model is established by: acquiring a training image set; acquiring a second target feature of the training image set; and training a neural network model according to the second target characteristic and the self-attention mechanism to obtain the pedestrian re-recognition model.
According to a second aspect, an embodiment of the present invention further discloses a pedestrian re-identification apparatus, including: the first acquisition module is used for acquiring an image set to be identified; the first image set to be identified acquisition module is used for extracting the image set to be identified according to the space-time model to obtain a first image set to be identified; the target image set to be identified acquisition module is used for acquiring a target image set to be identified according to the first image set to be identified; the second acquisition module is used for acquiring a first target feature of the target image set to be identified; and the identification module is used for carrying out pedestrian re-identification on the first target characteristic according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result.
With reference to the second aspect, in a first implementation manner of the second aspect, the target image set to be recognized acquisition module includes: the second image set to be identified acquisition module is used for carrying out pedestrian detection on the first image set to be identified to obtain a second image set to be identified; and the target image set sub-module to be identified is used for screening the second image set to be identified to obtain the target image set to be identified.
With reference to the first embodiment of the second aspect, in a second embodiment of the second aspect, the apparatus further comprises: the third acquisition module is used for acquiring space-time information according to the image set to be identified, wherein the space-time information comprises space information of camera equipment and pedestrian time information; and the construction module is used for constructing a space-time model according to the space-time information.
With reference to the second aspect, in a third embodiment of the second aspect, the apparatus further comprises: the fourth acquisition module is used for acquiring a training image set; a fifth obtaining module, configured to obtain a second target feature of the training image set; and the training module is used for training a neural network model according to the second target characteristic and the self-attention mechanism to obtain the pedestrian re-identification model.
According to a third aspect, an embodiment of the present invention further discloses an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the one processor to cause the at least one processor to perform the pedestrian re-identification method according to the first aspect or any of the embodiments of the first aspect.
According to a fourth aspect, an embodiment of the present invention further discloses a computer-readable storage medium, on which computer instructions are stored, and the computer instructions, when executed by a processor, implement the pedestrian re-identification method according to the first aspect or any one of the embodiments of the first aspect.
The technical scheme of the invention has the following advantages:
the invention provides a pedestrian re-identification method and a device, wherein an image set to be identified is obtained, the image set to be identified is extracted according to a space-time model to obtain a first image set to be identified, a target image set to be identified is obtained according to the first image set to be identified, a first target feature of the target image set to be identified is obtained, pedestrian re-identification is carried out on the first target feature according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result, deep learning is optimized through the space-time model and the self-attention mechanism, video information can be effectively utilized through extracting space-time information of a video, the accuracy of video pedestrian re-identification is improved, the pedestrian re-identification model can pay attention to key frame information of video content at each moment through the self-attention mechanism, and the accuracy of pedestrian re-identification is improved.
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 or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a specific example of a pedestrian re-identification method in embodiment 1 of the present invention;
fig. 2 is a schematic block diagram of a specific example of a pedestrian re-identification apparatus in embodiment 2 of the invention;
fig. 3 is a diagram of an embodiment of an electronic terminal in embodiment 3 of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. 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.
The terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment of the invention provides a pedestrian re-identification method, which is applied to an electronic purse net monitoring video and comprises the following steps as shown in figure 1:
s11: and acquiring an image set to be identified.
Illustratively, the image set to be identified may be a surveillance video acquired by an electronic purse net across a camera device, and the image set to be identified may be directly uploaded to a terminal by a user in a wired or wireless manner, or may be obtained by logging in the terminal. The acquisition mode of the image to be recognized is not particularly limited in the embodiment of the application, and a person skilled in the art can determine the acquisition mode according to actual use needs.
S12: and extracting the image set to be identified according to the space-time model to obtain a first image set to be identified.
For example, the first image set to be recognized may be a preliminary screening of the image set to be recognized according to a spatiotemporal model.
S13: and obtaining a target image set to be identified according to the first image set to be identified.
For example, the target image set to be recognized may be regarded as an unobstructed and clear image set including a pedestrian, and the pedestrian detection may be implemented in a manual labeling manner or an automatic labeling manner.
S14: and acquiring a first target characteristic of the target image set to be recognized.
The first target feature may include, for example, a color of clothes, accessories, a posture, a hairstyle, a posture, surrounding buildings, and the like of a pedestrian, and the embodiment of the present invention does not limit the first target feature, and may be set by a person skilled in the art according to actual circumstances.
S15: and carrying out pedestrian re-recognition on the first target characteristic according to the self-attention mechanism and the pedestrian re-recognition model to obtain a recognition result.
Illustratively, the attention mechanism mimics the internal process of biological observation behavior, a mechanism that aligns internal experience with external perception to increase the fineness of observation of a partial region. Attention mechanism can quickly extract important features of data, and thus is widely used for natural language processing tasks, particularly machine translation. While the autoflight mechanism is an improvement of the attentiveness mechanism, which reduces reliance on external information and is more adept at capturing internal correlations of data or features. And carrying out pedestrian re-identification on the first target characteristic according to a self-attention mechanism and a preset pedestrian re-identification model, so that the pedestrian re-identification model can pay attention to the key information of the video frame at each moment, and the accuracy of pedestrian re-identification is improved.
The invention provides a pedestrian re-identification method, which comprises the steps of obtaining an image set to be identified, extracting the image set to be identified according to a space-time model to obtain a first image set to be identified, obtaining a target image set to be identified according to the first image set to be identified, obtaining first target characteristics of the target image set to be identified, carrying out pedestrian re-identification on the first target characteristics according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result, optimizing deep learning through the space-time model and the self-attention mechanism, and effectively utilizing video information by extracting the space-time information of a video so as to improve the accuracy of video pedestrian re-identification.
As an alternative embodiment of the present application, the step S13, obtaining the target image set to be recognized according to the first image set to be recognized, includes:
firstly, pedestrian detection is carried out on a first image set to be recognized, and a second image set to be recognized is obtained.
For example, a video shot by the camera device may be divided into one frame and one frame of video frames, the first image refers to a video frame accurately marking a pedestrian, the video frame is subjected to pedestrian detection through a pedestrian detection algorithm, and the pedestrian detection may be realized through a manual marking or an automatic marking manner. The embodiment of the invention does not limit the pedestrian detection algorithm which is automatically marked, and the person skilled in the art can select the algorithm according to the actual situation.
And secondly, screening the second image set to be identified to obtain a target identification image set.
For example, the marked video frames are screened to obtain clear and non-occluded video frames, the application may regard an occlusion of less than or equal to 10% of pedestrians as no occlusion, and may regard an image with pixels greater than or equal to 1280 × 720 as a clear image. The standard of non-occlusion and clearness is not specifically limited in the embodiments of the present application, and those skilled in the art can determine the standard according to actual use requirements.
As an alternative embodiment of the present application, the spatio-temporal model is built by:
and acquiring space-time information according to the image to be recognized, wherein the space-time information comprises space information of the camera equipment and pedestrian time information.
Illustratively, taking a picture in mark 1501 as an example, the spatio-temporal information of the picture is written in the picture name, which may be 0007-c3-077419.jpg, wherein 0007 represents the identity of the target person, c3 represents the information captured by camera No. 3, i.e. spatial information, and 077419 represents the frame number, i.e. pedestrian time information. The space-time information is very easy to store, and the space-time information can be recorded and effectively utilized as long as the time when the picture is shot and which camera is shot is known.
And after the spatiotemporal information of the image is obtained through the steps, a spatiotemporal model is constructed according to the spatiotemporal information.
Exemplarily, the space-time model refers to the distribution of the migration time of pedestrians between two cameras in a camera network, and an outdoor map model of a positioning space is extracted by using a general map service, and the space-time model is constructed by performing space modeling on an electronic purse net by including the GPS coordinates of each point in the map, the geographic GPS coordinates of camera deployment, the deployment scene, the height and the like, and combining the space-time information with the maximum likelihood estimation.
As an alternative embodiment of the present application, the pedestrian re-identification model is established by the following steps:
first, a training image set is acquired.
Illustratively, in order to improve the accuracy of pedestrian re-identification, the selection of the training image set should be various, and may include, for example, pedestrian posture diversity, pedestrian scale diversity, background diversity, etc., the training image set may employ DukeMTMC-reID, CUHK03 or mark-1501, and the image set may be represented by 100: 1, taking an image set with a large proportion as a training image set, and taking an image set with a small proportion as a verification image set, wherein the verification image set can be used for verifying a pedestrian re-identification model. The training image set is not particularly limited by the embodiment of the present invention, and those skilled in the art can select the training image set according to actual situations.
Second, a second target feature of the training image set is obtained.
The second target feature may include, for example, a color of clothes, accessories, a posture, a hairstyle, a posture, surrounding buildings, and the like of the pedestrian, and the embodiment of the present invention does not limit the target feature, and may be set by a person skilled in the art according to actual circumstances. The second target feature and the first target feature can be set to be the same, and accuracy of pedestrian re-identification is improved.
And thirdly, training the neural network model according to the second target characteristic and the self-attention mechanism to obtain a pedestrian re-identification model.
Exemplarily, a second target feature is input into a neural network model, a self-attention mechanism focuses on key video frame information, weight of the neural network model is continuously adjusted according to the second target feature for training to obtain a pedestrian re-identification model, then the pedestrian re-identification model is verified, the pedestrian re-identification model can be verified by adopting a verification image set, a Rank evaluation system can be adopted in the application, Rank-1 is a first-order hit rate, namely whether a graph arranged at a first order hits the pedestrian or not, Rank-n indicates the probability that a correct result exists in n highest graphs in search results, Rank-5 can be adopted in the embodiment of the application, and 4 of 5 highest graphs in the search results are used as correct evaluations. The evaluation system is not limited in the embodiment of the invention, and can be set by a person skilled in the art according to actual conditions.
Example 2
An embodiment of the present invention further provides a pedestrian re-identification apparatus, as shown in fig. 2, including:
a first obtaining module 21, configured to obtain an image set to be identified; the specific implementation manner is shown in step S11 in embodiment 1, and details are not described here.
The first to-be-identified image set acquisition module 22 is configured to extract an image set to be identified according to the spatio-temporal model to obtain a first to-be-identified image set; the specific implementation manner is shown in step S12 in embodiment 1, and details are not described here.
The target image set to be recognized acquisition module 23 is configured to obtain a target image set to be recognized according to the first image set to be recognized; the specific implementation manner is shown in step S13 in embodiment 1, and details are not described here.
The second obtaining module 24 is configured to obtain a target feature of the target image set to be recognized; the specific implementation manner is shown in step S14 in embodiment 1, and details are not described here.
And the identification module 25 is used for carrying out pedestrian re-identification on the target characteristics according to the self-attention mechanism and the pedestrian re-identification model to obtain an identification result. The specific implementation manner is shown in step S15 in embodiment 1, and details are not described here.
The invention provides a pedestrian re-identification device, which is characterized in that an image set to be identified is obtained, the image set to be identified is extracted according to a space-time model to obtain a first image set to be identified, a target image set to be identified is obtained according to the first image set to be identified, a first target feature of the target image set to be identified is obtained, pedestrian re-identification is carried out on the first target feature according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result, deep learning is optimized through the space-time model and the self-attention mechanism, video information can be effectively utilized through extracting space-time information of a video, the accuracy of video pedestrian re-identification is improved, and the pedestrian re-identification model can pay attention to key frame information of video content at each moment through the self-attention mechanism, so that the accuracy of pedestrian re-identification is improved.
As an optional implementation manner of the application, the target image set to be recognized acquisition module comprises:
the second image set to be identified acquisition module is used for carrying out pedestrian detection on the first image set to be identified to obtain a second image set to be identified; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
And the target image set sub-module to be identified is used for screening the second image set to be identified to obtain a target image set to be identified. The specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
As an alternative embodiment of the present application, the apparatus comprises:
the third acquisition module is used for acquiring space-time information according to the image set to be identified, wherein the space-time information comprises space information of the camera equipment and pedestrian time information; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
And the construction module is used for constructing a space-time model according to the space-time information. The specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
As an alternative embodiment of the present application, the apparatus comprises:
the fourth acquisition module is used for acquiring a training image set; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
The fifth acquisition module is used for acquiring target characteristics of the training image set; the specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
And the training module is used for training the neural network model according to the training image set and the self-attention mechanism to obtain a pedestrian re-identification model. The specific implementation manner is shown in the corresponding steps in embodiment 1, and is not described herein again.
Example 3
An embodiment of the present invention further provides an electronic device, as shown in fig. 3, the electronic device may include a processor 31 and a memory 32, where the processor 31 and the memory 32 may be connected by a bus or in another manner, and fig. 3 takes the connection by the bus as an example.
The processor 31 may be a Central Processing Unit (CPU). The Processor 31 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 32 is a non-transitory computer readable storage medium, and can be used for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the pedestrian re-identification method in the embodiment of the present invention (for example, the first acquisition module 21, the first to-be-identified image set acquisition module 22, the target to-be-identified image set acquisition module 23, the second acquisition module 24, and the identification module 25 shown in fig. 2). The processor 31 executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory 32, that is, implements the pedestrian re-identification method in the above-described method embodiment.
The memory 32 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 31, and the like. Further, the memory 32 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 32 may optionally include memory located remotely from the processor 31, and these remote memories may be connected to the processor 31 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 32 and, when executed by the processor 31, perform the pedestrian re-identification method in the embodiment shown in fig. 1.
The details of the electronic device may be understood with reference to the corresponding related description and effects in the embodiment shown in fig. 1, and are not described herein again.
Example 4
An embodiment of the present invention further provides a computer storage medium, where a computer-executable instruction is stored, and the computer-executable instruction may execute the method for determining the position of the passive target in any of the above method embodiments. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard disk (Hard disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A pedestrian re-identification method is characterized by comprising the following steps:
acquiring an image set to be identified;
extracting the image set to be identified according to a space-time model to obtain a first image set to be identified;
obtaining a target image set to be identified according to the first image set to be identified;
acquiring a first target feature of the target image set to be recognized;
and carrying out pedestrian re-identification on the first target characteristic according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result.
2. The method of claim 1, wherein obtaining a target image set to be identified from the first image set to be identified comprises:
carrying out pedestrian detection on the first image set to be recognized to obtain a second image set to be recognized;
and screening the second image set to be identified to obtain the target identification image set.
3. The method of claim 2, wherein the spatio-temporal model is built by:
acquiring space-time information according to the image to be identified, wherein the space-time information comprises space information of camera equipment and pedestrian time information;
and constructing a space-time model according to the space-time information.
4. The method of claim 3, wherein the pedestrian re-identification model is established by:
acquiring a training image set;
acquiring a second target feature of the training image set;
and training a neural network model according to the second target characteristic and the self-attention mechanism to obtain the pedestrian re-recognition model.
5. A pedestrian re-recognition apparatus, comprising:
the first acquisition module is used for acquiring an image set to be identified;
the first image set to be identified acquisition module is used for extracting the image set to be identified according to the space-time model to obtain a first image set to be identified;
the target image set to be identified acquisition module is used for acquiring a target image set to be identified according to the first image set to be identified;
the second acquisition module is used for acquiring a first target feature of the target image set to be identified;
and the identification module is used for carrying out pedestrian re-identification on the first target characteristic according to a self-attention mechanism and a pedestrian re-identification model to obtain an identification result.
6. The apparatus of claim 5, wherein the target image set to be identified acquisition module comprises:
the second image set to be identified acquisition module is used for carrying out pedestrian detection on the first image set to be identified to obtain a second image set to be identified;
and the target image set sub-module to be identified is used for screening the second image set to be identified to obtain the target image set to be identified.
7. The apparatus of claim 6, further comprising:
the third acquisition module is used for acquiring space-time information according to the image set to be identified, wherein the space-time information comprises space information of camera equipment and pedestrian time information;
and the construction module is used for constructing a space-time model according to the space-time information.
8. The apparatus of claim 7, further comprising:
the fourth acquisition module is used for acquiring a training image set;
a fifth obtaining module, configured to obtain a second target feature of the training image set;
and the training module is used for training a neural network model according to the second target characteristic and the self-attention mechanism to obtain the pedestrian re-identification model.
9. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the pedestrian re-identification method of any one of claims 1 to 4.
10. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, carry out the pedestrian re-identification method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911259371.0A CN111738043A (en) | 2019-12-10 | 2019-12-10 | Pedestrian re-identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911259371.0A CN111738043A (en) | 2019-12-10 | 2019-12-10 | Pedestrian re-identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738043A true CN111738043A (en) | 2020-10-02 |
Family
ID=72646203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911259371.0A Pending CN111738043A (en) | 2019-12-10 | 2019-12-10 | Pedestrian re-identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738043A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113221800A (en) * | 2021-05-24 | 2021-08-06 | 珠海大横琴科技发展有限公司 | Monitoring and judging method and system for target to be detected |
| CN115588170A (en) * | 2022-11-29 | 2023-01-10 | 城云科技（中国）有限公司 | Muck truck weight identification method and application thereof |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003296710A (en) * | 2002-04-01 | 2003-10-17 | Sumitomo Electric Ind Ltd | Identification method, identification device and traffic control system |
| CN105243356A (en) * | 2015-09-10 | 2016-01-13 | 北京大学 | Method of building pedestrian detection model and device and pedestrian detection method |
| CN105989369A (en) * | 2015-02-15 | 2016-10-05 | 中国科学院西安光学精密机械研究所 | Pedestrian Re-Identification Method Based on Metric Learning |
| CN107944340A (en) * | 2017-10-25 | 2018-04-20 | 宁波大学 | A kind of combination is directly measured and the pedestrian of indirect measurement recognition methods again |
| CN108133238A (en) * | 2017-12-29 | 2018-06-08 | 国信优易数据有限公司 | A kind of human face recognition model training method and device and face identification method and device |
| CN108764308A (en) * | 2018-05-16 | 2018-11-06 | 中国人民解放军陆军工程大学 | Pedestrian re-identification method based on convolution cycle network |
| CN108805040A (en) * | 2018-05-24 | 2018-11-13 | 复旦大学 | It is a kind of that face recognition algorithms are blocked based on piecemeal |
| CN109558831A (en) * | 2018-11-27 | 2019-04-02 | 成都索贝数码科技股份有限公司 | It is a kind of fusion space-time model across camera shooting head's localization method |
| CN110110601A (en) * | 2019-04-04 | 2019-08-09 | 深圳久凌软件技术有限公司 | Video pedestrian weight recognizer and device based on multi-space attention model |
| CN110119703A (en) * | 2019-05-07 | 2019-08-13 | 福州大学 | The human motion recognition method of attention mechanism and space-time diagram convolutional neural networks is merged under a kind of security protection scene |
| CN110162138A (en) * | 2019-04-10 | 2019-08-23 | 北京迈格威科技有限公司 | Folding angles adjusting method, device and collapsible terminal |
| CN110516586A (en) * | 2019-08-23 | 2019-11-29 | 深圳力维智联技术有限公司 | A kind of facial image clustering method, system, product and medium |
-
2019
- 2019-12-10 CN CN201911259371.0A patent/CN111738043A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003296710A (en) * | 2002-04-01 | 2003-10-17 | Sumitomo Electric Ind Ltd | Identification method, identification device and traffic control system |
| CN105989369A (en) * | 2015-02-15 | 2016-10-05 | 中国科学院西安光学精密机械研究所 | Pedestrian Re-Identification Method Based on Metric Learning |
| CN105243356A (en) * | 2015-09-10 | 2016-01-13 | 北京大学 | Method of building pedestrian detection model and device and pedestrian detection method |
| CN107944340A (en) * | 2017-10-25 | 2018-04-20 | 宁波大学 | A kind of combination is directly measured and the pedestrian of indirect measurement recognition methods again |
| CN108133238A (en) * | 2017-12-29 | 2018-06-08 | 国信优易数据有限公司 | A kind of human face recognition model training method and device and face identification method and device |
| CN108764308A (en) * | 2018-05-16 | 2018-11-06 | 中国人民解放军陆军工程大学 | Pedestrian re-identification method based on convolution cycle network |
| CN108805040A (en) * | 2018-05-24 | 2018-11-13 | 复旦大学 | It is a kind of that face recognition algorithms are blocked based on piecemeal |
| CN109558831A (en) * | 2018-11-27 | 2019-04-02 | 成都索贝数码科技股份有限公司 | It is a kind of fusion space-time model across camera shooting head's localization method |
| CN110110601A (en) * | 2019-04-04 | 2019-08-09 | 深圳久凌软件技术有限公司 | Video pedestrian weight recognizer and device based on multi-space attention model |
| CN110162138A (en) * | 2019-04-10 | 2019-08-23 | 北京迈格威科技有限公司 | Folding angles adjusting method, device and collapsible terminal |
| CN110119703A (en) * | 2019-05-07 | 2019-08-13 | 福州大学 | The human motion recognition method of attention mechanism and space-time diagram convolutional neural networks is merged under a kind of security protection scene |
| CN110516586A (en) * | 2019-08-23 | 2019-11-29 | 深圳力维智联技术有限公司 | A kind of facial image clustering method, system, product and medium |
Non-Patent Citations (6)
| Title |
|---|
| JEAN-PAUL AINAM 等: "Self Attention Grid for Person Re-Identification", 《ARXIV》 * |
| JIANMING LV 等: "Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns", 《ARXIV》 * |
| 刘紫燕 等: "基于注意力机制的行人重识别特征提取方法", 《计算机应用》 * |
| 梦里青盏: "CVPR2018: Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatio-temporal Patterns", 《HTTPS://WWW.CNBLOGS.COM/HELLOCWH/P/8616371.HTML》 * |
| 梦里风林: "CVPR2018: 基于时空模型无监督迁移学习的行人重识别", 《HTTP://WWW.ZHUANLAN.ZHIHU.COM/P/34778414》 * |
| 王经纬: "基于视频的行人再检索算法研究与设计", 《万方数据库》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113221800A (en) * | 2021-05-24 | 2021-08-06 | 珠海大横琴科技发展有限公司 | Monitoring and judging method and system for target to be detected |
| CN115588170A (en) * | 2022-11-29 | 2023-01-10 | 城云科技（中国）有限公司 | Muck truck weight identification method and application thereof |
| CN115588170B (en) * | 2022-11-29 | 2023-02-17 | 城云科技（中国）有限公司 | Muck truck weight identification method and application thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10896323B2 (en) | Method and device for image processing, computer readable storage medium, and electronic device | |
| CN109166261B (en) | Image processing method, device and equipment based on image recognition and storage medium | |
| WO2020078229A1 (en) | Target object identification method and apparatus, storage medium and electronic apparatus | |
| CN112166439A (en) | True-to-composite image domain transfer | |
| US20170213080A1 (en) | Methods and systems for automatically and accurately detecting human bodies in videos and/or images | |
| CN106682620A (en) | Human face image acquisition method and device | |
| CN112052815B (en) | Behavior detection method and device and electronic equipment | |
| US20130162867A1 (en) | Method and system for robust scene modelling in an image sequence | |
| CN111354024B (en) | Behavior prediction method of key target, AI server and storage medium | |
| CN111444758A (en) | Pedestrian re-identification method and device based on spatio-temporal information | |
| CN111666800A (en) | Pedestrian re-recognition model training method and pedestrian re-recognition method | |
| CN111161206A (en) | Image capturing method, monitoring camera and monitoring system | |
| CN111435437A (en) | PCB pedestrian re-recognition model training method and PCB pedestrian re-recognition method | |
| JP2018077807A (en) | Device, program and method for tracing body while taking multiple candidates into consideration at change point | |
| CN112733690A (en) | High-altitude parabolic detection method and device and electronic equipment | |
| CN112163545A (en) | Head feature extraction method and device, electronic equipment and storage medium | |
| CN107844774A (en) | Image display selection method and device, intelligent terminal and storage medium | |
| CN111738043A (en) | Pedestrian re-identification method and device | |
| CN115965934A (en) | Parking space detection method and device | |
| US11605220B2 (en) | Systems and methods for video surveillance | |
| CN111814617B (en) | Fire determination method and device based on video, computer equipment and storage medium | |
| CN110751163B (en) | Target positioning method and device, computer readable storage medium and electronic equipment | |
| CN112990156B (en) | Optimal target capturing method and device based on video and related equipment | |
| CN111325731A (en) | Installation detection method and device of remote control device | |
| CN116246200A (en) | Screen display information candid photographing detection method and system based on visual identification |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201002 |
|
| RJ01 | Rejection of invention patent application after publication |