CN112417946A - Boundary crossing detection method and system for designated area of power construction site - Google Patents
Boundary crossing detection method and system for designated area of power construction site Download PDFInfo
- Publication number
- CN112417946A CN112417946A CN202010979709.6A CN202010979709A CN112417946A CN 112417946 A CN112417946 A CN 112417946A CN 202010979709 A CN202010979709 A CN 202010979709A CN 112417946 A CN112417946 A CN 112417946A
- Authority
- CN
- China
- Prior art keywords
- area
- construction site
- frame
- power construction
- target detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 238000010276 construction Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000004804 winding Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000012163 sequencing technique Methods 0.000 claims abstract description 7
- 241000699666 Mus <mouse, genus> Species 0.000 claims description 7
- 241000282326 Felis catus Species 0.000 claims description 5
- 241001504654 Mustela nivalis Species 0.000 claims description 5
- 230000006399 behavior Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 2
- 241000009328 Perro Species 0.000 claims 2
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 239000003550 marker Substances 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 241000282472 Canis lupus familiaris Species 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 241000699670 Mus sp. Species 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
Abstract
The invention relates to a border crossing detection method and a system for a specified area of a power construction site, which are used for detecting related targets in each frame of image of a video by combining a deep neural network and marking the targets through rectangles; combining the coordinates input by the user into a closed forbidden region; and checking whether a target enters a specified area or not according to the relative information of the target coordinate point and the forbidden area, and indicating the occurrence of abnormity. The invention adopts the YOLOv3 detection framework to ensure the speed and the precision of target detection; training is carried out through 8000 marked pictures to achieve the image detection task of the marker; by combining the rapid sequencing, binary search and winding methods, the speed of judging the boundary crossing is improved.
Description
Technical Field
The invention belongs to the field of electronic fences, relates to a boundary crossing detection method based on an electronic fence for a specified area of an electric power construction site, and particularly relates to a boundary crossing detection method and system for the specified area of the electric power construction site based on a deep neural network.
Background
With the development of scientific technology, the electronic fence is used to replace the traditional physical fence. The re-search in the image processing based electronic fence is more and more popular due to its low cost, low power consumption and intelligence.
In an electric power construction site, the physical fence has the following problems: the actual height of the fence is not high enough so it is easy to cross over through an intruder's physical fence without monitoring functions and therefore it is not possible to record which intruders cross over the fence. The physical fence has no automatic alarm function, so that the intrusion behavior cannot be prevented.
In this scenario, the image processing based electronic fence has five main advantages compared to the traditional physical fence: first, a key technology of image processing based electronic fences is to analyze images in a monitored area scene, which may be an algorithm for analyzing a specific area to achieve area-based intrusion detection without changing physical devices; secondly, the electronic fence based on image processing does not need a large amount of intrusion detection equipment, only a monitoring point needs to be established to analyze the collected images, and the camera can be arranged in a secret place so as to reduce the risk of equipment damage and realize remote detection; thirdly, the electronic fence based on image processing analyzes the captured image target area, and an alarm sounds no matter which direction an intruder enters the monitoring system to detect the intrusion, so that any form of bypassing the detector can be eliminated, and no alarm is missed; fourth, the monitoring area can be arbitrarily designated in the image processing-based electronic fence, and thus the monitoring area cost can be easily modified without any additional operation; finally, compared to traditional physical barriers, image processing based electronic fences can not only detect intrusion, but also enable tracking of objects.
However, in the existing technical solutions, it can be found through practice that it is difficult for the detection of multiple specific objects in the power construction site to meet the requirements on precision and speed at the same time, and how to quickly detect the boundary-crossing phenomenon of multiple objects in the designated area becomes a problem that technicians need to solve.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a depth neural network-based border crossing detection method for a specified area of an electric power construction site.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
the border crossing detection method for the designated area of the power construction site comprises the following steps:
firstly, marking a specified area which is forbidden to enter in an electric power construction site by a user;
step two, modifying a YOLOv3 target detection framework according to the type of the target to be detected and retraining so that the YOLOv3 target detection framework can detect a plurality of specified objects;
step three, detecting each frame of image in the input video file by using a retrained Yolov3 target detection frame, and detecting and marking related targets to form a target detection frame;
taking out specific position points of the target detection frame, quickly sequencing, and taking out position points meeting the corresponding threshold value requirement through binary search;
judging whether the position points which are taken out and meet the corresponding threshold value requirements are in the designated area or not by using a winding method;
and step six, if the border crossing behavior occurs, changing the color of the frame selection area in the image.
Moreover, the method for marking the designated area which is forbidden to enter by the power construction site by the user comprises the following steps: calling a first image output by a video file, and drawing a polygon area to be detected in the called first image through a mouse, wherein the area is any polygon.
Also, the specified various objects include a person, an automobile, a motorcycle, a bicycle, a cat, a dog, a mouse, a weasel.
And the content of judging whether the extracted position points meeting the corresponding threshold value requirements are in the designated area by the winding method is as follows: whether the generated midpoint coordinate is above or below the upper boundary of the rectangular frame, to the left or right of the left boundary, to the left or right of the right boundary, or to the upper or lower of the lower boundary is determined, thereby determining whether the midpoint is within the drawn rectangular frame.
The border crossing detection system for the designated area of the power construction site comprises a designated area marking module, a target frame training module, a target detection frame forming module, a position point extracting module, a designated area judging module and a border crossing marking module,
the designated area marking module is used for marking a designated area which is forbidden to enter in the electric power construction site by a user;
the target frame training module is used for modifying the YOLOv3 target detection frame according to the type of the target to be detected and retraining the YOLOv3 target detection frame so that the YOLOv3 target detection frame can detect a plurality of specified objects;
the target detection frame forming module is used for detecting each frame of image in the input video file by using a retrained Yolov3 target detection frame, and marking related targets to form a target detection frame;
the position point extraction module is used for taking out specific position points of the target detection frame, performing rapid sequencing and taking out the position points meeting the corresponding threshold value requirements through binary search;
the specified area judging module is used for judging whether the taken position point meeting the corresponding threshold value requirement is in the specified area by a winding method;
the border crossing marking module is used for changing the color of the frame selection area in the image when border crossing behaviors occur.
Moreover, the method for marking the designated area which is forbidden to enter by the power construction site by the user through the designated area marking module comprises the following steps: calling a first image output by a video file, and drawing a polygon area to be detected in the called first image through a mouse, wherein the area is any polygon.
Also, the specified various objects include a person, an automobile, a motorcycle, a bicycle, a cat, a dog, a mouse, a weasel.
And the specified area judging module is used for judging whether the extracted position points meeting the corresponding threshold value requirements are in the specified area by a winding method, and the content is as follows: whether the generated midpoint coordinate is above or below the upper boundary of the rectangular frame, to the left or right of the left boundary, to the left or right of the right boundary, or to the upper or lower of the lower boundary is determined, thereby determining whether the midpoint is within the drawn rectangular frame.
The invention has the advantages and positive effects that:
the border crossing detection method and system for the designated area of the power construction site detect related targets in each frame of image of a video by combining a deep neural network, and mark the targets through rectangles; combining the coordinates input by the user into a closed forbidden region; and checking whether a target enters a specified area or not according to the relative information of the target coordinate point and the forbidden area, and indicating the occurrence of abnormity. The invention adopts the YOLOv3 detection framework to ensure the speed and the precision of target detection; training is carried out through 8000 marked pictures to achieve the image detection task of the marker; by combining the rapid sequencing, binary search and winding methods, the speed of judging the boundary crossing is improved.
Drawings
FIG. 1 is a flow chart of the detection of a marker according to the present invention;
FIG. 2 is a system screenshot of the delinquent region framing of the present invention;
FIG. 3 is a diagram showing a frame generated by a character target of the present invention not entering a drawn forbidden region;
FIG. 4 is a diagram showing the entrance of a frame generated by a character target into a forbidden area.
Detailed Description
The embodiments of the invention are described in further detail below with reference to the following figures:
the overall flow chart of the border crossing detection method of the designated area of the power construction site is shown in figure 1, and the method comprises the following steps:
step one, marking a specified area which is forbidden to enter in the electric power construction site by a user
The user inputs a plurality of vertexes of the forbidden area through a mouse, and the vertexes are connected to form a closed polygon as the forbidden area. This set of vertices is recorded in the array Points and is expressed as follows:
Points[(x1,y1),(x2,y2),(x3,y3),(x4,y4)…]。
the maximum values ymax and ymin of y are recorded.
Step two, modifying the target detection network and training
The related objects contained in the target detection task comprise 8 objects of people, automobiles, motorcycles, bicycles, cats, dogs, mice and weasel, the last layer of the YOLOv3 detection frame is modified, the output category is changed into 8, the modified frame is retrained by training 8000 marked pictures, so that the related requirements of specific object detection can be met, and the precision and the speed of target detection can be ensured by using the modified network.
Step three, detecting and marking the target
Putting each frame in the video into a network which is modified and trained again, detecting targets, marking different targets as rectangular frames with different colors, wherein each target comprises four position coordinate points:
Object[(x1,y1)，(x2,y1)，(x1,y2)，(x2,y2)]；
step four, finding out relevant candidate points
All the detected points on the two vertical edges in the rectangular frame are taken out, the points in the container are sorted by using a fast algorithm, and the points which are larger than ymin and smaller than ymax are stored by adopting binary search.
Step five, judging whether the point is in the polygon by the winding method
The screened coordinates are represented by Object (xr, yr), and the break-in of the forbidden area is used for judging whether the point Pr is in the polygon of Points; the problem is to determine whether the point Pr is in the Points polygon by a winding method, that is, whether the generated midpoint coordinate is above or below the upper boundary of the rectangular frame, to the left or right of the left boundary, to the left or right of the right boundary, or to the upper or lower of the lower boundary, thereby determining whether the midpoint is in the drawn rectangular frame.
Step six, whether an object enters the designated area or not is marked
If the point is detected to be inside the polygon, the polygon is marked as green in the image, otherwise, the polygon is marked as red.
The border crossing detection method and system for the designated area of the power construction site detect related targets in each frame of image of a video by combining a deep neural network, and mark the targets through rectangles; combining the coordinates input by the user into a closed forbidden region; and checking whether a target enters a specified area or not according to the relative information of the target coordinate point and the forbidden area, and indicating the occurrence of abnormity. The invention adopts the YOLOv3 detection framework to ensure the speed and the precision of target detection; training is carried out through 8000 marked pictures to achieve the image detection task of the marker; by combining the rapid sequencing, binary search and winding methods, the speed of judging the boundary crossing is improved.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (8)
1. The border crossing detection method for the designated area of the power construction site is characterized by comprising the following steps of: the method comprises the following steps:
firstly, marking a specified area which is forbidden to enter in an electric power construction site by a user;
step two, modifying a YOLOv3 target detection framework according to the type of the target to be detected and retraining so that the YOLOv3 target detection framework can detect a plurality of specified objects;
step three, detecting each frame of image in the input video file by using a retrained Yolov3 target detection frame, and detecting and marking related targets to form a target detection frame;
taking out specific position points of the target detection frame, quickly sequencing, and taking out position points meeting the corresponding threshold value requirement through binary search;
judging whether the position points which are taken out and meet the corresponding threshold value requirements are in the designated area or not by using a winding method;
and step six, if the border crossing behavior occurs, changing the color of the frame selection area in the image.
2. The method for detecting the boundary crossing of the specified area of the power construction site according to claim 1, wherein: the method for marking the specified area which is forbidden to enter in the electric power construction site by the user comprises the following steps: calling a first image output by a video file, and drawing a polygon area to be detected in the called first image through a mouse, wherein the area is any polygon.
3. The method for detecting the boundary crossing of the specified area of the power construction site according to claim 1, wherein: the designated objects include human, automobile, motorcycle, bicycle, cat, dog, mouse, and weasel.
4. The method for detecting the boundary crossing of the specified area of the power construction site according to claim 1, wherein: the content of judging whether the extracted position point meeting the corresponding threshold value requirement is in the designated area by using the winding method is as follows: whether the generated midpoint coordinate is above or below the upper boundary of the rectangular frame, to the left or right of the left boundary, to the left or right of the right boundary, or to the upper or lower of the lower boundary is determined, thereby determining whether the midpoint is within the drawn rectangular frame.
5. Electric power construction site appointed area's border crossing detection system, its characterized in that: comprises a designated area marking module, a target frame training module, a target detection frame forming module, a position point extracting module, a designated area judging module and an out-of-range marking module,
the designated area marking module is used for marking a designated area which is forbidden to enter in the electric power construction site by a user;
the target frame training module is used for modifying the YOLOv3 target detection frame according to the type of the target to be detected and retraining the YOLOv3 target detection frame so that the YOLOv3 target detection frame can detect a plurality of specified objects;
the target detection frame forming module is used for detecting each frame of image in the input video file by using a retrained Yolov3 target detection frame, detecting and marking related targets and forming a target detection frame;
the position point extraction module is used for taking out specific position points of the target detection frame, performing rapid sequencing and taking out the position points meeting the corresponding threshold value requirements through binary search;
the specified area judging module is used for judging whether the taken position point meeting the corresponding threshold value requirement is in the specified area by a winding method;
the border crossing marking module is used for changing the color of the frame selection area in the image when border crossing behaviors occur.
6. The power construction site specified area border crossing detection system according to claim 5, wherein: the method for marking the designated area which is forbidden to enter in the electric power construction site by the user through the designated area marking module comprises the following steps: calling a first image output by a video file, and drawing a polygon area to be detected in the called first image through a mouse, wherein the area is any polygon.
7. The power construction site specified area border crossing detection system according to claim 5, wherein: the designated objects include human, automobile, motorcycle, bicycle, cat, dog, mouse, and weasel.
8. The power construction site specified area border crossing detection system according to claim 5, wherein: the specified area judging module is used for judging whether the extracted position points meeting the corresponding threshold value requirements are in the specified area by a winding method, and the content is as follows: whether the generated midpoint coordinate is above or below the upper boundary of the rectangular frame, to the left or right of the left boundary, to the left or right of the right boundary, or to the upper or lower of the lower boundary is determined, thereby determining whether the midpoint is within the drawn rectangular frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010979709.6A CN112417946A (en) | 2020-09-17 | 2020-09-17 | Boundary crossing detection method and system for designated area of power construction site |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010979709.6A CN112417946A (en) | 2020-09-17 | 2020-09-17 | Boundary crossing detection method and system for designated area of power construction site |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417946A true CN112417946A (en) | 2021-02-26 |
Family
ID=74855386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010979709.6A Pending CN112417946A (en) | 2020-09-17 | 2020-09-17 | Boundary crossing detection method and system for designated area of power construction site |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417946A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792665A (en) * | 2021-09-16 | 2021-12-14 | 山东大学 | Method for detecting intrusion of forbidden region aiming at different role authorities |
| CN113920535A (en) * | 2021-10-12 | 2022-01-11 | 广东电网有限责任公司广州供电局 | Electronic region detection method based on YOLOv5 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100064367A1 (en) * | 2005-02-02 | 2010-03-11 | Universitetet I Oslo | Intrusion detection for computer programs |
| CN109068099A (en) * | 2018-09-05 | 2018-12-21 | 济南大学 | Virtual electronic fence monitoring method and system based on video monitoring |
| CN111126152A (en) * | 2019-11-25 | 2020-05-08 | 国网信通亿力科技有限责任公司 | Video-based multi-target pedestrian detection and tracking method |
| CN111144291A (en) * | 2019-12-25 | 2020-05-12 | 中铁信(北京)网络技术研究院有限公司 | Method and device for distinguishing personnel invasion in video monitoring area based on target detection |
| CN111144232A (en) * | 2019-12-09 | 2020-05-12 | 国网智能科技股份有限公司 | Transformer substation electronic fence monitoring method based on intelligent video monitoring, storage medium and equipment |
| CN111461080A (en) * | 2020-05-18 | 2020-07-28 | 江苏电力信息技术有限公司 | Intelligent fence building and identifying method based on image |
-
2020
- 2020-09-17 CN CN202010979709.6A patent/CN112417946A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100064367A1 (en) * | 2005-02-02 | 2010-03-11 | Universitetet I Oslo | Intrusion detection for computer programs |
| CN109068099A (en) * | 2018-09-05 | 2018-12-21 | 济南大学 | Virtual electronic fence monitoring method and system based on video monitoring |
| CN111126152A (en) * | 2019-11-25 | 2020-05-08 | 国网信通亿力科技有限责任公司 | Video-based multi-target pedestrian detection and tracking method |
| CN111144232A (en) * | 2019-12-09 | 2020-05-12 | 国网智能科技股份有限公司 | Transformer substation electronic fence monitoring method based on intelligent video monitoring, storage medium and equipment |
| CN111144291A (en) * | 2019-12-25 | 2020-05-12 | 中铁信(北京)网络技术研究院有限公司 | Method and device for distinguishing personnel invasion in video monitoring area based on target detection |
| CN111461080A (en) * | 2020-05-18 | 2020-07-28 | 江苏电力信息技术有限公司 | Intelligent fence building and identifying method based on image |
Non-Patent Citations (1)
| Title |
|---|
| 王迎春等: "多边形内外点判断算法在电力智慧工地中的应用", 《黑龙江电力》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792665A (en) * | 2021-09-16 | 2021-12-14 | 山东大学 | Method for detecting intrusion of forbidden region aiming at different role authorities |
| CN113792665B (en) * | 2021-09-16 | 2023-08-08 | 山东大学 | Forbidden area intrusion detection method aiming at different role authorities |
| CN113920535A (en) * | 2021-10-12 | 2022-01-11 | 广东电网有限责任公司广州供电局 | Electronic region detection method based on YOLOv5 |
| CN113920535B (en) * | 2021-10-12 | 2023-11-17 | 广东电网有限责任公司广州供电局 | Electronic region detection method based on YOLOv5 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103069434B (en) | For the method and system of multi-mode video case index | |
| KR101180887B1 (en) | Apparatus and method for detecting abnormal behavior | |
| CN112216049A (en) | Construction warning area monitoring and early warning system and method based on image recognition | |
| CN103092930B (en) | Method of generation of video abstract and device of generation of video abstract | |
| US20130243343A1 (en) | Method and device for people group detection | |
| KR101824446B1 (en) | A reinforcement learning based vehicle number recognition method for CCTV | |
| CN107992819A (en) | A kind of definite method and apparatus of vehicle attribute structured features | |
| CN104662585B (en) | The method and the event monitoring device using the method for event rules are set | |
| CN112417946A (en) | Boundary crossing detection method and system for designated area of power construction site | |
| JP4764172B2 (en) | Method for detecting moving object candidate by image processing, moving object detecting method for detecting moving object from moving object candidate, moving object detecting apparatus, and moving object detecting program | |
| Salehi et al. | An automatic video-based drowning detection system for swimming pools using active contours | |
| CN110781844B (en) | Security patrol monitoring method and device | |
| CN115100732A (en) | Fishing detection method and device, computer equipment and storage medium | |
| CN114140745A (en) | Method, system, device and medium for detecting personnel attributes of construction site | |
| CN112633157A (en) | AGV working area safety real-time detection method and system | |
| KR101826669B1 (en) | System and method for video searching | |
| Sitara et al. | Automated camera sabotage detection for enhancing video surveillance systems | |
| CN113989858B (en) | Work clothes identification method and system | |
| CN114782883A (en) | Abnormal behavior detection method, device and equipment based on group intelligence | |
| Zhang et al. | What makes for good multiple object trackers? | |
| CN113191273A (en) | Oil field well site video target detection and identification method and system based on neural network | |
| WO2020139071A1 (en) | System and method for detecting aggressive behaviour activity | |
| CN114241397B (en) | Frontier defense video intelligent analysis method and system | |
| CN112597924A (en) | Electric bicycle track tracking method, camera device and server | |
| Masood et al. | Identification of Anomaly Scenes in Videos Using Graph Neural Networks |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |