CN114612932A - Gait big data retrieval method and system and terminal equipment - Google Patents
Gait big data retrieval method and system and terminal equipment Download PDFInfo
- Publication number
- CN114612932A CN114612932A CN202210225395.XA CN202210225395A CN114612932A CN 114612932 A CN114612932 A CN 114612932A CN 202210225395 A CN202210225395 A CN 202210225395A CN 114612932 A CN114612932 A CN 114612932A
- Authority
- CN
- China
- Prior art keywords
- gait
- target person
- local
- library
- retrieval
- 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
- 230000005021 gait Effects 0.000 title claims abstract description 171
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 230000009471 action Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a gait big data retrieval method, a gait big data retrieval system and terminal equipment, belongs to the technical field of gait recognition, and can realize that a user can use a gait retrieval technology normally and correctly to obtain the optimal retrieval effect, so that target figure track information can be drawn more abundantly and accurately based on a retrieval result, and the problem that the retrieval effect is different from person to person is solved. The method comprises the following steps: s1, acquiring a video image containing a target person, extracting a gait sample of the target person from the video image, and constructing a gait library of the target person according to the gait sample; s2, searching in the monitoring video data of the local area by using the gait library to obtain a local searching result, and updating the gait library by using the local searching result to obtain an updated gait library; s3, searching in the monitoring video data of the whole area by using the updated gait library to obtain a global searching result; and S4, generating the track of the target person according to the local search result and the global search result. The gait retrieval method is used for gait retrieval.
Description
Technical Field
The invention relates to a gait big data retrieval method, a gait big data retrieval system and terminal equipment, and belongs to the technical field of gait recognition.
Background
In the AI era, more and more biological characteristics can be extracted and identified, and face identification, fingerprint identification, voiceprint identification, iris identification, palm vein identification, gait identification and other technologies are applied in the market at present.
Gait recognition refers to identity recognition by analyzing the body structure and walking posture of a target person. Compared with other biological identification technologies, gait identification has the advantages of non-contact remote distance, difficulty in camouflage and the like, and is widely applied to scenes such as track query of lost children, dynamic control of target suspects, dynamic monitoring of key people and the like in fields such as safe cities and social governance.
Gait recognition is a new biological recognition technology in the current security industry, and has reached higher recognition accuracy in the academic world. However, in practical applications, when many users search data based on gait recognition technology, the problem that the search results are largely lost or the search results are mixed with noise data is increased, and the problem that the search results are inconsistent due to insufficient operation experience or irregular operation of the users is that the users do not obtain ideal results is increasingly serious as the applications are increased.
Disclosure of Invention
The invention provides a gait big data retrieval method, a system and terminal equipment thereof, which can realize that a user can use a gait retrieval technology regularly and correctly to obtain the optimal retrieval effect, thereby being capable of drawing target character track information based on the retrieval result more abundantly and accurately and solving the problem that the retrieval effect is different from person to person.
In one aspect, the invention provides a gait big data retrieval method, which comprises the following steps:
s1, acquiring a video image containing a target person, extracting a gait sample of the target person from the video image, and constructing a gait library of the target person according to the gait sample;
s2, searching in the monitoring video data of the local area by using the gait library to obtain a local searching result, and updating the gait library by using the local searching result to obtain an updated gait library;
s3, searching in the monitoring video data of the whole area by using the updated gait library to obtain a global searching result;
and S4, generating an action track of the target person according to the local retrieval result and the global retrieval result.
Optionally, the S2 specifically includes:
s21, acquiring an initial time and place of the target person as a central point;
s22, searching the monitoring video data in the preset range around the central point by using the gait library to obtain a local searching result;
s23, updating the gait library by using the local retrieval result to obtain an updated gait library;
s24, taking the new appearance time and place of the target person in the local retrieval result as an updated central point;
and S25, repeating the steps from S22 to S24 until the newly added track information of the target person is not searched in the local search result or the target person leaves the local search area.
Optionally, after S3, the method further includes:
s5, judging whether newly added track information of the target person is searched in the global search result; if yes, go to step S6, otherwise go to step S4;
and S6, taking the time and the place in the target person new track information in the global search result as an updated central point, and executing the step S22.
Optionally, the S23 specifically includes:
and adding the gait sample which accords with the preset rule in the local retrieval result as an excellent gait sample into the gait library to obtain an updated gait library.
Optionally, the monitoring video data in the preset range around the central point is all monitoring video data in a range that the central point is used as a center, the place is radiated outwards for 3 kilometers, and the time is expanded by 30 minutes.
Optionally, the S22 specifically includes:
s221, taking the gait database as a comparison object, and carrying out gait comparison on the gait database and the monitoring video data in the preset range around the central point to obtain comparison similarity of each section of monitoring video data;
s222, taking the gait sample with the comparison similarity larger than or equal to a preset threshold value and the corresponding time location as a local retrieval result.
Optionally, the S4 specifically includes:
and sequencing all time points where the target person appears in the local retrieval result and the global retrieval result according to time to form the action track of the target person.
In another aspect, the present invention provides a gait big data retrieval system, which includes:
the gait library construction unit is used for acquiring a video image containing a target person, extracting a gait sample of the target person from the video image, and constructing a gait library of the target person according to the gait sample;
the local retrieval unit is used for retrieving the gait database in the monitoring video data of the local area to obtain a local retrieval result, and updating the gait database by using the local retrieval result to obtain an updated gait database;
the global retrieval unit is used for retrieving the monitoring video data of the whole domain by utilizing the updated gait library to obtain a global retrieval result;
and the track generating unit is used for generating an action track of the target person according to the local retrieval result and the global retrieval result.
Optionally, the system further includes a data query unit and a data synchronization unit;
the data query unit is used for querying data in the gait database according to any one or more of the type of the database, the creation time, the gait sample grade and the identity information of the collected person;
the data synchronization unit is used for synchronizing the data in the gait library to a superior system or a third-party system according to a preset synchronization period or a preset synchronization strategy.
In yet another aspect, the present invention provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor;
the processor, when executing the computer program, performs the steps of any of the methods described above.
The invention can produce beneficial effects that:
(1) the gait big data retrieval method provided by the invention can dynamically build a database under the condition of insufficient gait samples, enrich the number of the gait samples of the target person and improve the gait sample quality of the target person. For example, when the registered target person gait sample is low in pixels and fuzzy in human figure outline, other excellent gait samples can be quickly found through low-threshold local retrieval.
(2) According to the gait big data retrieval method provided by the invention, time and place information of more target persons can be rapidly acquired through global retrieval, and missing track of the target persons in a local range can be avoided through local retrieval, so that the action track of the target persons in a large range can be finely drawn.
Drawings
Fig. 1 is a flowchart of a gait big data retrieval method provided by an embodiment of the invention;
fig. 2 is a schematic diagram illustrating a gait big data retrieval method according to an embodiment of the invention;
fig. 3 is a flowchart of a gait big data retrieval method according to another embodiment of the invention;
fig. 4 is a schematic diagram of a helper retrieval operation process according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to examples, but the present invention is not limited to these examples.
An embodiment of the present invention provides a gait big data retrieval method, as shown in fig. 1 and fig. 2, the method includes:
and S1, acquiring a video image containing the target person, extracting a gait sample of the target person from the video image, and constructing a gait library of the target person according to the gait sample.
The gait sample can be one or more continuous gait image sequences containing gait characteristics; the gait bank can also be called a gait base bank; step S1 is used for base database registration, specifically, uploading a video containing target person information to the system, and extracting a gait sample of the target person by using a gait algorithm to form a gait database of the target person.
And S2, searching the monitoring video data of the local area by using the gait library to obtain a local searching result, and updating the gait library by using the local searching result to obtain an updated gait library.
The S2 specifically includes:
and S21, acquiring the initial time point of the target person as the central point. The initial time and place of the target person may be a time and place of the target person inferred by the public security staff according to experience with a high probability, or a time and place inferred according to some relevant evidence materials. The embodiment of the present invention is not limited thereto.
And S22, searching the monitoring video data in the preset range around the central point by using the gait library to obtain a local searching result.
The S22 specifically includes:
and S221, taking the gait database as a comparison object, and comparing the gait database with the monitoring video data in the preset range around the central point to obtain the comparison similarity of each section of monitoring video data.
S222, taking the gait sample with the comparison similarity larger than or equal to a preset threshold value and the corresponding time location as a local retrieval result.
The preset threshold is a value preset by a person skilled in the art according to an actual situation, and is not limited in this embodiment of the present invention, and may be, for example, 80%, 85%, 90%, and the like.
The preset range is a preset duration and a preset geographical range, and a person skilled in the art or a user can set the preset range according to an actual situation, which is not limited in the embodiment of the present invention. For example, the monitoring video data in the preset range around the central point may be all monitoring video data in a range that the central point is used as a center, the location is radiated outward for 3 kilometers, and the time is extended by 30 minutes.
In practical applications, step S22 may also be referred to as helper retrieval; the method comprises the steps of taking a time place where a target person appears most frequently as a central point, radiating the place outwards for 3 kilometers, expanding the time for 30 minutes before and after, selecting related monitoring video data, taking a target person gait library as a comparison object, setting a gait comparison threshold value to be 80%, setting comparison results to be sorted according to the gait comparison similarity from high to low, and performing gait retrieval under the parameter configuration. The functions can be fixed in a software system to realize one-key retrieval.
And S23, updating the gait database by using the local retrieval result to obtain an updated gait database.
Specifically, the method comprises the following steps: and adding the gait sample which accords with the preset rule in the local retrieval result as an excellent gait sample into the gait library to obtain an updated gait library.
The preset rule is a preset determination rule, and a person skilled in the art can set the preset determination rule according to an actual situation, which is not limited in the embodiment of the present invention. For example, the predetermined rule for selecting the excellent gait sample may be that the gait sample shows a complete humanoid natural walking state, the gait sample pixels are greater than or equal to 60 × 100, the number of the gait sample frames is greater than or equal to 15, the gait sample includes more than 2 gait cycles, and the humanoid contour boundary in the gait sample is clear
S24, the time point at which the target person newly appears in the local search result is set as the updated center point.
And S25, repeatedly executing S22 to S24 until the newly added track information of the target person is not searched in the local search result or the target person leaves the local search area.
Selecting all related monitoring video data to perform helper retrieval by taking the time and place where the target person appears probably as a central point, selecting excellent gait samples from the retrieval result, adding the excellent gait samples into a gait library of the target person, taking the time and place where the target person appears newly as a new central point, taking the updated gait library of the target person as a new target comparison object, and selecting all related monitoring video data again to perform helper retrieval. And when the assistant searches that no new search result (namely no new track information) exists in the local area or the target person is found to leave the vehicle through the search result, determining that the local search is finished.
S3, searching in the monitoring video data of the whole area by using the updated gait library to obtain a global searching result; and selecting all related monitoring video data for the monitoring video data of the universe.
Further, after S3, the method further includes:
s5, judging whether newly added track information of the target person is searched in the global search result; if so, go to step S6, otherwise, go to step S4.
And S6, taking the time point in the target person new track information in the global search result as the updated central point, and executing the step S22.
And taking the updated gait database as a target comparison object, selecting all related monitoring video data in full to perform gait retrieval, and taking a new time and place where a target person appears in a retrieval result as an entry point for further local retrieval.
And S4, generating the action track of the target person according to the local search result and the global search result.
Specifically, the method comprises the following steps: and sequencing all time points of the target person in the local retrieval result and the global retrieval result according to time to form the action track of the target person.
Another embodiment of the present invention provides a gait big data retrieval method, as shown in fig. 3 and 4, the method includes:
s301, obtaining a video image containing a target person, extracting a gait sample of the target person from the video image, and constructing a gait library of the target person according to the gait sample.
S302, acquiring an initial time and place of the target person as a central point.
And S303, searching the monitoring video data in the preset range around the central point by using the gait library to obtain a local searching result.
And S304, adding the gait sample which accords with the preset rule in the local retrieval result as an excellent gait sample into a gait library to obtain an updated gait library.
S305, judging whether the local retrieval result contains the new appearance time and place of the target person; if yes, go to step 306; if not, go to step 307.
S306, the new time and place of the target person in the local search result is used as the updated center point, and step 303 is executed.
And S307, searching in the monitoring video data of the whole region by using the updated gait library to obtain a global searching result.
S308, judging whether the global retrieval result contains the new appearing time and place of the target person; if yes, go to step 309; if not, go to step 310.
S309, the time and place of the new appearance of the target person in the global search result is used as the updated center point, and step 303 is executed.
S310, sequencing all time points where the target person appears in the local search result and the global search result according to time to form the action track of the target person.
The method can dynamically build a library under the condition of insufficient gait samples, enrich the quantity of the gait samples of the target person and improve the quality of the gait samples of the target person. For example, when the registered target person gait sample is low in pixels and fuzzy in human figure outline, other excellent gait samples can be quickly found through low-threshold local retrieval. Meanwhile, time and place information of more target people can be rapidly acquired through global retrieval, missing track of the target people in a local range can be avoided through local retrieval, and therefore the action track of the target people in a large range can be drawn finely.
Another embodiment of the present invention provides a gait big data retrieval system, which includes:
and the gait library construction unit is used for acquiring the video image containing the target person, extracting a gait sample of the target person from the video image, and constructing the gait library of the target person according to the gait sample.
And the local retrieval unit is used for retrieving the monitoring video data in the local area by using the gait database to obtain a local retrieval result, and updating the gait database by using the local retrieval result to obtain an updated gait database.
And the global retrieval unit is used for retrieving the monitoring video data of the whole domain by utilizing the updated gait library to obtain a global retrieval result.
And the track generating unit is used for generating the action track of the target person according to the local retrieval result and the global retrieval result.
Further, the system also comprises a data query unit and a data synchronization unit;
the data query unit is used for querying data in the gait database according to any one or more of the type of the database, the creation time, the gait sample grade and the identity information of the collected person so as to browse information such as the identity of the person in the base database, the gait sample and the like.
The data synchronization unit is used for synchronizing the data in the gait library to a superior system or a third-party system according to a preset synchronization period or a preset synchronization strategy.
The retrieval system provided by the embodiment of the invention has the functions of helper retrieval, gait comparison, retrieval result summarization, trajectory drawing, gait base quality evaluation and the like.
The retrieval system provided by the embodiment of the invention has the functions of user management, role management and organization management; the system has different use authority management functions of common users and administrators, and has related authorization mechanisms in gait registration, deletion, inquiry and other operations. Meanwhile, the retrieval system of the invention also has a log management function, and for each event, the log record comprises the event occurrence time, the event type, the user, the event execution result or failure reason, the log effective time and the like.
A further embodiment of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the methods described above.
Although the present application has been described with reference to a few embodiments, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the application as defined by the appended claims.
Claims (10)
1. A gait big data retrieval method is characterized by comprising the following steps:
s1, acquiring a video image containing a target person, extracting a gait sample of the target person from the video image, and constructing a gait library of the target person according to the gait sample;
s2, searching in the monitoring video data of the local area by using the gait library to obtain a local searching result, and updating the gait library by using the local searching result to obtain an updated gait library;
s3, searching in the monitoring video data of the whole area by using the updated gait library to obtain a global searching result;
and S4, generating an action track of the target person according to the local retrieval result and the global retrieval result.
2. The method according to claim 1, wherein the S2 specifically includes:
s21, acquiring an initial time and place of the target person as a central point;
s22, searching the monitoring video data in the preset range around the central point by using the gait library to obtain a local searching result;
s23, updating the gait library by using the local retrieval result to obtain an updated gait library;
s24, taking the new appearance time and place of the target person in the local retrieval result as an updated central point;
and S25, repeating the steps from S22 to S24 until the newly added track information of the target person is not searched in the local search result or the target person leaves the local search area.
3. The method of claim 2, wherein after S3, the method further comprises:
s5, judging whether newly added track information of the target person is searched in the global search result; if yes, go to step S6, otherwise go to step S4;
and S6, taking the time and the place in the target person new track information in the global search result as an updated central point, and executing the step S22.
4. The method according to claim 2, wherein the S23 specifically includes:
and adding the gait sample which accords with a preset rule in the local retrieval result as an excellent gait sample into the gait library to obtain an updated gait library.
5. The method according to claim 2, wherein the surveillance video data within the predetermined range around the central point is all surveillance video data within a range of radiating a location outward for 3 km and extending 30 minutes around the central point.
6. The method according to claim 2, wherein S22 is specifically:
s221, the gait database is used as a comparison object, and gait comparison is carried out on the gait database and the monitoring video data in the preset range around the central point, so that the comparison similarity of each section of monitoring video data is obtained;
s222, taking the gait sample with the comparison similarity larger than or equal to a preset threshold value and the corresponding time location as a local retrieval result.
7. The method according to claim 1, wherein S4 is specifically:
and sequencing all time points where the target person appears in the local retrieval result and the global retrieval result according to time to form the action track of the target person.
8. A gait big data retrieval system, characterized in that the system comprises:
the gait library construction unit is used for acquiring a video image containing a target person, extracting a gait sample of the target person from the video image, and constructing a gait library of the target person according to the gait sample;
the local retrieval unit is used for retrieving the gait database in the monitoring video data of the local area to obtain a local retrieval result, and updating the gait database by using the local retrieval result to obtain an updated gait database;
the global retrieval unit is used for retrieving the monitoring video data of the whole domain by utilizing the updated gait library to obtain a global retrieval result;
and the track generating unit is used for generating an action track of the target person according to the local retrieval result and the global retrieval result.
9. The system of claim 8, further comprising a data query unit and a data synchronization unit;
the data query unit is used for querying data in the gait database according to any one or more of the type of the database, the creation time, the gait sample grade and the identity information of the collected person;
the data synchronization unit is used for synchronizing the data in the gait library to a superior system or a third-party system according to a preset synchronization period or a preset synchronization strategy.
10. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that,
the processor, when executing the computer program, realizes the steps of the method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210225395.XA CN114612932A (en) | 2022-03-07 | 2022-03-07 | Gait big data retrieval method and system and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210225395.XA CN114612932A (en) | 2022-03-07 | 2022-03-07 | Gait big data retrieval method and system and terminal equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114612932A true CN114612932A (en) | 2022-06-10 |
Family
ID=81861917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210225395.XA Pending CN114612932A (en) | 2022-03-07 | 2022-03-07 | Gait big data retrieval method and system and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114612932A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875548A (en) * | 2018-04-18 | 2018-11-23 | 科大讯飞股份有限公司 | Character track generation method and device, storage medium and electronic equipment |
| CN109446991A (en) * | 2018-10-30 | 2019-03-08 | 北京交通大学 | Gait recognition method based on global and local Fusion Features |
| CN110139075A (en) * | 2019-05-10 | 2019-08-16 | 银河水滴科技（北京）有限公司 | Video data handling procedure, device, computer equipment and storage medium |
| CN110532923A (en) * | 2019-08-21 | 2019-12-03 | 深圳供电局有限公司 | Figure track retrieval method and system |
| CN111539320A (en) * | 2020-04-22 | 2020-08-14 | 山东大学 | Multi-view gait recognition method and system based on mutual learning network strategy |
| CN112784740A (en) * | 2021-01-21 | 2021-05-11 | 上海市公安局刑事侦查总队 | Gait data acquisition and labeling method and application |
| US20210224524A1 (en) * | 2020-01-22 | 2021-07-22 | Board Of Trustees Of Michigan State University | Systems And Methods For Gait Recognition Via Disentangled Representation Learning |
| CN113963399A (en) * | 2021-09-09 | 2022-01-21 | 武汉众智数字技术有限公司 | Personnel trajectory retrieval method and device based on multi-algorithm fusion application |
-
2022
- 2022-03-07 CN CN202210225395.XA patent/CN114612932A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875548A (en) * | 2018-04-18 | 2018-11-23 | 科大讯飞股份有限公司 | Character track generation method and device, storage medium and electronic equipment |
| CN109446991A (en) * | 2018-10-30 | 2019-03-08 | 北京交通大学 | Gait recognition method based on global and local Fusion Features |
| CN110139075A (en) * | 2019-05-10 | 2019-08-16 | 银河水滴科技（北京）有限公司 | Video data handling procedure, device, computer equipment and storage medium |
| CN110532923A (en) * | 2019-08-21 | 2019-12-03 | 深圳供电局有限公司 | Figure track retrieval method and system |
| US20210224524A1 (en) * | 2020-01-22 | 2021-07-22 | Board Of Trustees Of Michigan State University | Systems And Methods For Gait Recognition Via Disentangled Representation Learning |
| CN111539320A (en) * | 2020-04-22 | 2020-08-14 | 山东大学 | Multi-view gait recognition method and system based on mutual learning network strategy |
| CN112784740A (en) * | 2021-01-21 | 2021-05-11 | 上海市公安局刑事侦查总队 | Gait data acquisition and labeling method and application |
| CN113963399A (en) * | 2021-09-09 | 2022-01-21 | 武汉众智数字技术有限公司 | Personnel trajectory retrieval method and device based on multi-algorithm fusion application |
Non-Patent Citations (1)
| Title |
|---|
| 廖嘉城;梁艳;王冰冰;潘家辉;: "视频监控场景下基于单视角步态的人体身份及属性识别系统", 计算机系统应用, no. 08, 15 August 2020 (2020-08-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110139075B (en) | Video data processing method, video data processing device, computer equipment and storage medium | |
| US8130285B2 (en) | Automated searching for probable matches in a video surveillance system | |
| KR20080063480A (en) | Semantic visual search engine | |
| CN109858354A (en) | A kind of face identity library, the foundation of track table and face track querying method and system | |
| CN114492590B (en) | Boundary channel generation method and device based on track clustering | |
| JP2004110448A (en) | Image object identifying/tracking device, its method, and its program | |
| CN115422479A (en) | Track association method and device, electronic equipment and machine-readable storage medium | |
| CN114612932A (en) | Gait big data retrieval method and system and terminal equipment | |
| CN112560711B (en) | Method, system, device and storage medium for judging traffic violation of non-motor vehicle | |
| CN113313062A (en) | Path acquisition method, device, system, electronic equipment and storage medium | |
| CN111160075A (en) | Large-scale face recognition system and method | |
| CN117351518B (en) | Method and system for identifying unsupervised cross-modal pedestrian based on level difference | |
| Nguyen et al. | Unsupervised inference of significant locations from wifi data for understanding human dynamics | |
| CN112364714B (en) | Face recognition method, device, computer equipment and storage medium | |
| CN115203477A (en) | Personnel track retrieval method and device, electronic equipment and storage medium | |
| CN113255703A (en) | Image recognition method, electronic device, and computer-readable storage medium | |
| Pandya et al. | Detection of Anomalous Value in Data Mining | |
| CN110795705B (en) | Track data processing method, device and equipment and storage medium | |
| JP3497713B2 (en) | Information classification method, apparatus and system | |
| Goh et al. | Mining parallel patterns from mobile users | |
| CN109934302B (en) | New category identification method and robot system based on fuzzy theory and deep learning | |
| CN111950352A (en) | Hierarchical face clustering method, system, equipment and storage medium | |
| CN113449130A (en) | Image retrieval method and device, computer readable storage medium and computing equipment | |
| Persia et al. | Fast learning and prediction of event sequences in a robotic system | |
| Sarker et al. | Parallel algorithms for mining association rules in time series data |
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 |