CN112380993A - Intelligent illegal behavior detection system and method based on target real-time tracking information - Google Patents
Intelligent illegal behavior detection system and method based on target real-time tracking information Download PDFInfo
- Publication number
- CN112380993A CN112380993A CN202011272730.9A CN202011272730A CN112380993A CN 112380993 A CN112380993 A CN 112380993A CN 202011272730 A CN202011272730 A CN 202011272730A CN 112380993 A CN112380993 A CN 112380993A
- Authority
- CN
- China
- Prior art keywords
- illegal
- data
- target
- module
- real
- 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 24
- 238000000034 method Methods 0.000 title abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 48
- 238000013075 data extraction Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000007726 management method Methods 0.000 claims description 42
- 230000006399 behavior Effects 0.000 claims description 36
- 238000005516 engineering process Methods 0.000 claims description 9
- 230000015572 biosynthetic process Effects 0.000 claims description 8
- 238000003786 synthesis reaction Methods 0.000 claims description 8
- 238000013523 data management Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses an intelligent illegal behavior detection system and method based on target real-time tracking information. The system comprises an interface module, a video deframing analysis tracking cluster, a message node cluster, a data extraction module and an illegal behavior judgment module; the video deframing analysis tracking cluster is used for analyzing, detecting and tracking the real-time video stream; the message node cluster is used for issuing a coordinate set and a frame number; the data extraction module is used for acquiring the release data of the message node cluster and processing the release data to obtain illegal data; and the illegal behavior judgment module is used for carrying out illegal judgment on the illegal data to obtain an illegal result. By implementing the embodiment of the invention, the target is identified by adopting a Cascade R-CNN method and tracked by adopting deepsort based on real-time video stream analysis, finally illegal behavior analysis is realized, the speed is high, the accuracy is high, and the time cost and the labor force can be greatly reduced.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to an intelligent illegal behavior detection system and method based on target real-time tracking information.
Background
With the continuous development of social economy and the continuous improvement of the living standard of people, vehicles are more and more, and the automatic checking of the traffic administration on the vehicle violation is more and more urgent. The existing illegal detection means mainly analyze illegal behaviors through manpower, and consume manpower and material resources.
Disclosure of Invention
In view of the above technical defects, an object of the embodiments of the present invention is to provide an intelligent illegal behavior detection system and method based on real-time target tracking information.
In order to achieve the above object, in a first aspect, an embodiment of the present invention provides an intelligent illegal behavior detection system based on target real-time tracking information, which includes an interface module, a video deframing analysis tracking cluster, a message node cluster, a data extraction module, and an illegal behavior determination module; the interface module is used for providing various interfaces so as to realize data transmission among the modules in the system;
the video deframing analysis tracking cluster is to:
acquiring a real-time video stream, and analyzing the real-time video stream by adopting an opencv technology to obtain a picture to be processed;
adopting Cascade R-CNN to identify and analyze the picture to be processed to obtain a target to be tracked;
tracking the track of the target to be tracked by adopting depsort to obtain a coordinate set, the whole track and the frame number corresponding to the whole track of the target to be tracked;
the message node cluster is used for publishing the coordinate set and the frame number;
the data extraction module is used for acquiring the release data of the message node cluster and processing the release data to obtain illegal data;
and the illegal behavior judgment module is used for carrying out illegal judgment on the illegal data to obtain an illegal result.
As a specific implementation manner of the present application, the data extraction module is configured to format and filter the release data; wherein, screening includes:
judging whether the initial position of the target to be tracked is in a lane or not;
judging whether the attribute of the target to be tracked accords with an analysis type;
selecting a preset number of pictures to analyze illegal behaviors to obtain illegal data;
performing four-picture-mosaic synthesis on the illegal data;
selecting pictures before, during and after the violation for synthesis;
and selecting pictures in a first preset time before and after the violation, and synthesizing the pictures into the violation video by using ffmepg.
Further, in certain preferred embodiments of the present application, the system further comprises:
and the picture storage medium is used for storing the picture to be processed obtained by the video analysis module.
And the database is used for storing the illegal data and the illegal types, the checkpoint information, the scene configuration information, the system user information and the log data which are obtained by the data extraction module.
Further, in some preferred embodiments of the present application, the system further includes a page management module, which specifically includes:
the checkpoint management unit is used for adding, deleting and modifying checkpoint positions;
the system comprises a marking management unit, a traffic light analysis unit and a traffic light analysis unit, wherein the marking management unit is used for marking the analysis violation types of the card interfaces, and the marked violation types comprise that a motor vehicle and a non-motor vehicle run through a traffic light, change lanes in a solid line, turn in a large curve and turn in a small curve, separate passengers and goods and occupy a bus lane;
the illegal data management unit is used for displaying four puzzles, illegal places and illegal events of the illegal data and playing illegal videos;
the checkpoint task management unit is used for displaying the checkpoint illegal type tasks and opening and closing the illegal type tasks;
and the user management unit is used for adding, modifying and deleting the user.
Further, in some preferred embodiments of the present application, the interface module is further configured to provide a video stream task distribution management interface, and the system further includes a task maintenance module configured to:
regularly acquiring tasks of each server in a video unframing analysis tracking cluster;
distributing the tasks in a load balancing mode;
and starting, closing and pausing the tasks on each server through the video stream task distribution management interface.
In a second aspect, an embodiment of the present invention provides another intelligent illegal behavior detection system based on target real-time tracking information, including:
the interface module is used for providing a real-time video stream acquisition interface;
the video analysis module is used for acquiring a real-time video stream through the real-time video stream acquisition interface and analyzing the real-time video stream by adopting an opencv technology to obtain a picture to be processed;
the detection module is used for identifying and analyzing the picture to be processed by using Cascade R-CNN to obtain a target to be tracked;
the tracking module is used for tracking the track of the target to be tracked by adopting depsort to obtain a coordinate set, a whole track and a corresponding frame number of the target to be tracked, and publishing the coordinate set and the frame number through the message node cluster;
the data extraction module is used for acquiring the release data of the message node cluster and processing the release data to obtain illegal data;
in a third aspect, an embodiment of the present invention provides an intelligent illegal behavior detection method based on target real-time tracking information, including:
an acquisition interface acquires a real-time video stream, and the real-time video stream is analyzed by adopting an opencv technology to obtain a picture to be processed;
adopting Cascade R-CNN to identify and analyze the picture to be processed to obtain a target to be tracked;
tracking the track of the target to be tracked by adopting depsort to obtain a coordinate set, the whole track and a frame number corresponding to the track of the target to be tracked, and publishing the coordinate set and the frame number through a message node cluster;
acquiring release data of the message node cluster, and processing the release data to obtain illegal data;
and carrying out illegal judgment on the illegal data to obtain an illegal result.
By implementing the embodiment of the invention, the target is identified by adopting a Cascade R-CNN method and tracked by adopting deepsort based on real-time video stream analysis, finally illegal behavior analysis is realized, the speed is high, the accuracy is high, and the time cost and the labor force can be greatly reduced.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below.
FIG. 1 is a block diagram of an intelligent illegal behavior detection system based on target real-time tracking information according to a first embodiment of the present invention;
FIG. 2 is a block diagram of an intelligent illegal behavior detection system based on target real-time tracking information according to a second embodiment of the present invention;
FIG. 3 is a flowchart of intelligent illegal behavior detection based on target real-time tracking information according to an embodiment of the present invention;
fig. 4 is a block diagram of an electronic device provided in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, 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.
Referring to fig. 1, an intelligent illegal activity detection system based on target real-time tracking information according to a first embodiment of the present invention includes an interface module 10, a video deframing analysis tracking cluster 11, a message node cluster 12, a picture storage medium 13, a data extraction module 14, an illegal activity determination module 15, a database 16, and a task maintenance module 17.
The interface module 10 is used to provide various interfaces to enable data transmission between modules within the system. The interface module comprises a real-time video stream acquisition picture interface and a video stream task distribution management interface. The real-time video stream acquiring picture interface uses opencv to unframe the real-time video stream to acquire pictures and user scene labels. And the video stream task distribution management interface is used for distributing the video stream tasks to the appropriate servers to start, close and pause the tasks.
The video deframing analysis tracking cluster 11 is mainly used for video parsing, detection and tracking, and specifically comprises:
acquiring a real-time video stream, and analyzing the real-time video stream by adopting an opencv technology to obtain a picture to be processed;
adopting Cascade R-CNN to identify and analyze the picture to be processed to obtain a target to be tracked, and acquiring the position, the attribute and the like of the target;
tracking the track of the target to be tracked by adopting depsort to obtain a coordinate set, the whole track and the corresponding frame number of the target to be tracked in the process of video appearing and leaving;
the coordinate set and the attribute frame number of the target occurrence are distributed to the message node cluster 12(kafka cluster), and the picture is stored in the picture storage medium 13(weed cluster).
The data extraction module 14 is configured to obtain release data of the message node cluster 12, and process the release data to obtain illegal data.
The illegal behavior judgment module 15 is configured to perform illegal judgment on the illegal data to obtain an illegal result.
The database 16 is used for storing the illegal data and the illegal type, the checkpoint information, the scene configuration information, the system user information, the log data and the like obtained by the data extraction module.
The task maintenance module 17 is mainly used for:
regularly acquiring tasks of each server in a video unframing analysis tracking cluster;
distributing the data to each server in a load balancing mode;
the hung services are removed periodically to carry out load balancing distribution on the tasks;
receiving a request of a task interface and distributing the request;
and starting, closing and pausing the tasks on each server through the video stream task distribution management interface.
Specifically, the data extraction module 14 is mainly configured to: acquiring data issued by the message node cluster 12, formatting the data, and screening the data mainly includes: the checkpoint analyzes matching of analysis types of illegal tasks, whether a target is initially in a lane or not and whether target attributes accord with the analysis types or not, selects a proper number of pictures to analyze illegal behaviors, synthesizes four jigsaw puzzle pieces of analyzed illegal data, synthesizes pictures after the illegal behaviors before and during the illegal behaviors, selects pictures before and after the illegal behaviors, synthesizes pictures in 5s before and after the illegal behaviors by using ffmepg to synthesize an illegal video, stores the illegal data in a warehouse and counts and stores the illegal data into a redis.
Preferably, the system further includes a page management module, configured to manage the checkpoint position, check display violation data, manage a violation analysis task, and the like, where the specific introduction is as follows:
the page management module mainly comprises a card port management unit, a label management unit, a card port task management unit, an illegal data management unit and a user management unit.
The card port management unit is used for adding, deleting and modifying card ports. The fields of the name, the number, the longitude and latitude and the video stream address of the modified card port are mainly added.
The marking management unit is mainly used for marking the traffic violation types through the checkpoint analysis, and the marked violation types mainly comprise motor vehicles and non-motor vehicles running traffic lights, changing lanes with solid lines, turning in large and small curves, separating passengers and goods, occupying bus lanes and the like. The page mainly comprises the steps of drawing a lane line, marking a traffic light position, drawing a reticule line position and drawing a solid line according to the selected illegal type and different marked objects.
The checkpoint task management unit is mainly used for displaying the checkpoint illegal type tasks and opening and closing the illegal task types.
The illegal data management unit is mainly used for displaying four puzzles of illegal data, illegal places and illegal time, and can play illegal videos.
The user management unit is mainly used for the addition, modification and deletion management of the user.
By implementing the embodiment of the invention, the target is identified by adopting a Cascade R-CNN method and tracked by adopting deepsort based on real-time video stream analysis, finally illegal behavior analysis is realized, the speed is high, the accuracy is high, and the time cost and the labor force can be greatly reduced.
Referring to fig. 2, an embodiment of the present invention provides another intelligent illegal behavior detection system based on target real-time tracking information, which mainly includes:
an interface module 20, configured to provide a real-time video stream acquisition interface;
the video analysis module 21 is configured to obtain a real-time video stream through the real-time video stream obtaining interface, and analyze the real-time video stream by using an opencv technology to obtain a to-be-processed picture;
the detection module 22 is configured to perform recognition analysis on the to-be-processed picture by using a Cascade R-CNN to obtain a to-be-tracked target;
the tracking module 23 is configured to track the target to be tracked by using a deepsort to obtain a coordinate set, an entire track, and a frame number corresponding to the coordinate set, the entire track, and the frame number, where the target to be tracked appears, and issue the coordinate set and the frame number through the message node cluster;
the data extraction module 24 is configured to obtain release data of the message node cluster, and process the release data to obtain illegal data;
and the illegal behavior judging module 25 is used for carrying out illegal judgment on the illegal data to obtain an illegal result.
Further, the data extraction module 24 is configured to format and filter the release data; wherein, screening includes:
judging whether the initial position of the target to be tracked is in a lane or not;
judging whether the attribute of the target to be tracked accords with an analysis type;
selecting a preset number of pictures to analyze illegal behaviors to obtain illegal data;
performing four-picture-mosaic synthesis on the illegal data;
selecting pictures before, during and after the violation for synthesis;
and selecting pictures in a first preset time before and after the violation, and synthesizing the pictures into the violation video by using ffmepg.
Further, the system further comprises:
and the picture storage medium is used for storing the picture to be processed obtained by the video analysis module.
And the database is used for storing the illegal data and the illegal types, the checkpoint information, the scene configuration information, the system user information and the log data which are obtained by the data extraction module.
Further, the system further comprises:
the page management module specifically comprises:
the checkpoint management unit is used for adding, deleting and modifying checkpoint positions;
the system comprises a marking management unit, a traffic light analysis unit and a traffic light analysis unit, wherein the marking management unit is used for marking the analysis violation types of the card interfaces, and the marked violation types comprise that a motor vehicle and a non-motor vehicle run through a traffic light, change lanes in a solid line, turn in a large curve and turn in a small curve, separate passengers and goods and occupy a bus lane;
the illegal data management unit is used for displaying four puzzles, illegal places and illegal events of the illegal data and playing illegal videos;
the checkpoint task management unit is used for displaying the checkpoint illegal type tasks and opening and closing the illegal type tasks;
and the user management unit is used for adding, modifying and deleting the user.
It should be noted that, regarding a more specific work flow of each functional module in the embodiment of the present system, please refer to the foregoing first embodiment, which is not described herein again.
Corresponding to the second system embodiment, the invention also provides an intelligent illegal behavior detection method based on the target real-time tracking information. As shown in fig. 3, the method includes:
s101, acquiring a real-time video stream by an acquisition interface, and analyzing the real-time video stream by adopting an opencv technology to obtain a picture to be processed;
s102, performing identification analysis on the picture to be processed by using Cascade R-CNN to obtain a target to be tracked;
s103, tracking the track of the target to be tracked by adopting deppsort to obtain a coordinate set, a whole track and a corresponding frame number of the target to be tracked, and publishing the coordinate set and the frame number through a message node cluster;
s104, acquiring release data of the message node cluster, and processing the release data to obtain illegal data;
s105, carrying out illegal judgment on the illegal data to obtain an illegal result.
Further, the method further comprises: and displaying the illegal data through a web page.
It should be noted that, for more detailed description of the method steps, please refer to the foregoing system embodiments, which are not repeated herein.
The detection method provided by the embodiment of the invention is implemented on the basis of real-time video stream analysis, the Cascade R-CNN method is adopted to identify the target, the deepsort is adopted to track the target, and finally illegal behavior analysis is realized, so that the speed is high, the accuracy is high, and the time cost and the labor power can be greatly reduced.
Corresponding to the embodiment of the method, the invention also provides electronic equipment. As shown in fig. 4, the electronic device may include: one or more processors 101, one or more input devices 102, one or more output devices 103, and memory 104, the processors 101, input devices 102, output devices 103, and memory 104 being interconnected via a bus 105. The memory 104 is used for storing a computer program comprising program instructions, the processor 101 being configured for invoking the program instructions for performing the methods of the above-described method embodiment parts.
It should be understood that, in the embodiment of the present invention, the Processor 101 may be a Central Processing Unit (CPU), a deep learning graphics card (e.g., NPU, england GPU, google TPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an FPGA (Field-Programmable Gate Array) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 102 may include a keyboard or the like, and the output device 103 may include a display (LCD or the like), a speaker, or the like.
The memory 104 may include read-only memory and random access memory, and provides instructions and data to the processor 101. A portion of the memory 104 may also include non-volatile random access memory. For example, the memory 104 may also store device type information.
In a specific implementation, the processor 101, the input device 102, and the output device 103 described in this embodiment of the present invention may execute the implementation manner described in the embodiment of the method for detecting an intelligent illegal behavior based on target real-time tracking information provided in this embodiment of the present invention, which is not described herein again.
Further, an embodiment of the present invention further provides a readable storage medium storing a computer program, where the computer program includes program instructions, and the program instructions, when executed by a processor, implement: the intelligent illegal behavior detection method based on the target real-time tracking information is disclosed.
The computer readable storage medium may be an internal storage unit of the system according to any of the foregoing embodiments, for example, a hard disk or a memory of the system. The computer readable storage medium may also be an external storage device of the system, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) Card, Flash memory Card (Flash Card), etc. provided on the system. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the system. The computer-readable storage medium is used for storing the computer program and other programs and data required by the system. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.
The foregoing storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent illegal behavior detection system based on target real-time tracking information is characterized by comprising an interface module, a video deframing analysis tracking cluster, a message node cluster, a data extraction module and an illegal behavior judgment module; the interface module is used for providing various interfaces so as to realize data transmission among the modules in the system;
the video deframing analysis tracking cluster is to:
acquiring a real-time video stream, and analyzing the real-time video stream by adopting an opencv technology to obtain a picture to be processed;
adopting Cascade R-CNN to identify and analyze the picture to be processed to obtain a target to be tracked;
tracking the track of the target to be tracked by adopting depsort to obtain a coordinate set, the whole track and the frame number corresponding to the whole track of the target to be tracked;
the message node cluster is used for publishing the coordinate set and the frame number;
the data extraction module is used for acquiring the release data of the message node cluster and processing the release data to obtain illegal data;
and the illegal behavior judgment module is used for carrying out illegal judgment on the illegal data to obtain an illegal result.
2. The system of claim 1, wherein the data extraction module is configured to format and filter the release data; wherein, screening includes:
judging whether the initial position of the target to be tracked is in a lane or not;
judging whether the attribute of the target to be tracked accords with an analysis type;
selecting a preset number of pictures to analyze illegal behaviors to obtain illegal data;
performing four-picture-mosaic synthesis on the illegal data;
selecting pictures before, during and after the violation for synthesis;
and selecting pictures in a first preset time before and after the violation, and synthesizing the pictures into the violation video by using ffmepg.
3. The system of claim 2, wherein the system further comprises:
the picture storage medium is used for storing the picture to be processed obtained by the video de-framing analysis tracking cluster;
and the database is used for storing the illegal data, the illegal types, the point location information of the storage card ports, the scene configuration information, the system user information and the log data which are obtained by the data extraction module.
4. The system of claim 3, wherein the system further comprises a page management module, specifically comprising:
the checkpoint management unit is used for adding, deleting and modifying checkpoint positions;
the system comprises a marking management unit, a traffic light analysis unit and a traffic light analysis unit, wherein the marking management unit is used for marking the analysis violation types of the card interfaces, and the marked violation types comprise that a motor vehicle and a non-motor vehicle run through a traffic light, change lanes in a solid line, turn in a large curve and turn in a small curve, separate passengers and goods and occupy a bus lane;
the illegal data management unit is used for displaying four puzzles, illegal places and illegal events of the illegal data and playing illegal videos;
the checkpoint task management unit is used for displaying the checkpoint illegal type tasks and opening and closing the illegal type tasks;
and the user management unit is used for adding, modifying and deleting the user.
5. The system of any one of claims 1-4, wherein the interface module is further to provide a video stream task distribution management interface, the system further comprising a task maintenance module to:
regularly acquiring tasks of each server in a video unframing analysis tracking cluster;
distributing the tasks in a load balancing mode;
and starting, closing and pausing the tasks on each server through the video stream task distribution management interface.
6. An intelligent illegal behavior detection system based on target real-time tracking information is characterized by comprising:
the interface module is used for providing a real-time video stream acquisition interface;
the video analysis module is used for acquiring a real-time video stream through the real-time video stream acquisition interface and analyzing the real-time video stream by adopting an opencv technology to obtain a picture to be processed;
the detection module is used for identifying and analyzing the picture to be processed by using Cascade R-CNN to obtain a target to be tracked;
the tracking module is used for tracking the track of the target to be tracked by adopting depsort to obtain a coordinate set, a whole track and a corresponding frame number of the target to be tracked, and publishing the coordinate set and the frame number through the message node cluster;
the data extraction module is used for acquiring the release data of the message node cluster and processing the release data to obtain illegal data;
and the illegal behavior judgment module is used for carrying out illegal judgment on the illegal data to obtain an illegal result.
7. The system of claim 6, wherein the data extraction module is configured to format and filter the post data; wherein, screening includes:
judging whether the initial position of the target to be tracked is in a lane or not;
judging whether the attribute of the target to be tracked accords with an analysis type;
selecting a preset number of pictures to analyze illegal behaviors to obtain illegal data;
performing four-picture-mosaic synthesis on the illegal data;
selecting pictures before, during and after the violation for synthesis;
and selecting pictures in a first preset time before and after the violation, and synthesizing the pictures into the violation video by using ffmepg.
8. The system of claim 7, wherein the system further comprises:
the picture storage medium is used for storing the picture to be processed obtained by the video analysis module;
and the database is used for storing the illegal data and the illegal types, the checkpoint information, the scene configuration information, the system user information and the log data which are obtained by the data extraction module.
9. The system according to any one of claims 6 to 8, wherein the system further comprises a page management module, specifically comprising:
the checkpoint management unit is used for adding, deleting and modifying checkpoint positions;
the system comprises a marking management unit, a traffic light analysis unit and a traffic light analysis unit, wherein the marking management unit is used for marking the analysis violation types of the card interfaces, and the marked violation types comprise that a motor vehicle and a non-motor vehicle run through a traffic light, change lanes in a solid line, turn in a large curve and turn in a small curve, separate passengers and goods and occupy a bus lane;
the illegal data management unit is used for displaying four puzzles, illegal places and illegal events of the illegal data and playing illegal videos;
the checkpoint task management unit is used for displaying the checkpoint illegal type tasks and opening and closing the illegal type tasks;
and the user management unit is used for adding, modifying and deleting the user.
10. An intelligent illegal behavior detection method based on target real-time tracking information is characterized by comprising the following steps:
an acquisition interface acquires a real-time video stream, and the real-time video stream is analyzed by adopting an opencv technology to obtain a picture to be processed;
adopting Cascade R-CNN to identify and analyze the picture to be processed to obtain a target to be tracked;
tracking the track of the target to be tracked by adopting depsort to obtain a coordinate set, the whole track and a frame number corresponding to the track of the target to be tracked, and publishing the coordinate set and the frame number through a message node cluster;
acquiring release data of the message node cluster, and processing the release data to obtain illegal data;
and carrying out illegal judgment on the illegal data to obtain an illegal result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011272730.9A CN112380993A (en) | 2020-11-12 | 2020-11-12 | Intelligent illegal behavior detection system and method based on target real-time tracking information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011272730.9A CN112380993A (en) | 2020-11-12 | 2020-11-12 | Intelligent illegal behavior detection system and method based on target real-time tracking information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112380993A true CN112380993A (en) | 2021-02-19 |
Family
ID=74582411
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011272730.9A Pending CN112380993A (en) | 2020-11-12 | 2020-11-12 | Intelligent illegal behavior detection system and method based on target real-time tracking information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380993A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220888A (en) * | 2021-06-01 | 2021-08-06 | 上海交通大学 | Case clue element extraction method and system based on Ernie model |
| CN115662190A (en) * | 2022-12-23 | 2023-01-31 | 深圳曦华科技有限公司 | Prompt message processing method and device for vehicle based on road abnormal state recognition |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | Motor vehicle red light running rule violation evidence obtaining method based on high-definition videos |
| US20160034778A1 (en) * | 2013-12-17 | 2016-02-04 | Cloud Computing Center Chinese Academy Of Sciences | Method for detecting traffic violation |
| CN107784838A (en) * | 2016-08-30 | 2018-03-09 | 杭州海康威视系统技术有限公司 | A kind of traffic offence dynamic identifying method and system |
| CN108230669A (en) * | 2016-12-21 | 2018-06-29 | 杭州海康威视数字技术股份有限公司 | The illegal detection method of road vehicle and system based on big data and cloud analysis |
| CN110178167A (en) * | 2018-06-27 | 2019-08-27 | 潍坊学院 | Crossing video frequency identifying method violating the regulations based on video camera collaboration relay |
| CN110321814A (en) * | 2019-06-18 | 2019-10-11 | 浙江大华技术股份有限公司 | A kind of vehicle violation evidence collecting method, device, electronic equipment and storage medium |
| CN110459064A (en) * | 2019-09-19 | 2019-11-15 | 上海眼控科技股份有限公司 | Vehicle illegal behavioral value method, apparatus, computer equipment |
| CN110717433A (en) * | 2019-09-30 | 2020-01-21 | 华中科技大学 | Deep learning-based traffic violation analysis method and device |
| CN110826508A (en) * | 2019-11-12 | 2020-02-21 | 浙江工商大学 | Pedestrian and non-motor vehicle violation detection and tracking method based on video stream |
| CN111091041A (en) * | 2019-10-22 | 2020-05-01 | 上海眼控科技股份有限公司 | Vehicle law violation judging method and device, computer equipment and storage medium |
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN111798664A (en) * | 2020-09-08 | 2020-10-20 | 武汉中科通达高新技术股份有限公司 | Illegal data identification method and device and electronic equipment |
| CN111833609A (en) * | 2020-07-24 | 2020-10-27 | 王程 | Intelligent monitoring and automatic alarming highway real-time monitoring system |
-
2020
- 2020-11-12 CN CN202011272730.9A patent/CN112380993A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | Motor vehicle red light running rule violation evidence obtaining method based on high-definition videos |
| US20160034778A1 (en) * | 2013-12-17 | 2016-02-04 | Cloud Computing Center Chinese Academy Of Sciences | Method for detecting traffic violation |
| CN107784838A (en) * | 2016-08-30 | 2018-03-09 | 杭州海康威视系统技术有限公司 | A kind of traffic offence dynamic identifying method and system |
| CN108230669A (en) * | 2016-12-21 | 2018-06-29 | 杭州海康威视数字技术股份有限公司 | The illegal detection method of road vehicle and system based on big data and cloud analysis |
| WO2020000251A1 (en) * | 2018-06-27 | 2020-01-02 | 潍坊学院 | Method for identifying video involving violation at intersection based on coordinated relay of video cameras |
| CN110178167A (en) * | 2018-06-27 | 2019-08-27 | 潍坊学院 | Crossing video frequency identifying method violating the regulations based on video camera collaboration relay |
| CN110321814A (en) * | 2019-06-18 | 2019-10-11 | 浙江大华技术股份有限公司 | A kind of vehicle violation evidence collecting method, device, electronic equipment and storage medium |
| CN110459064A (en) * | 2019-09-19 | 2019-11-15 | 上海眼控科技股份有限公司 | Vehicle illegal behavioral value method, apparatus, computer equipment |
| CN110717433A (en) * | 2019-09-30 | 2020-01-21 | 华中科技大学 | Deep learning-based traffic violation analysis method and device |
| CN111091041A (en) * | 2019-10-22 | 2020-05-01 | 上海眼控科技股份有限公司 | Vehicle law violation judging method and device, computer equipment and storage medium |
| CN110826508A (en) * | 2019-11-12 | 2020-02-21 | 浙江工商大学 | Pedestrian and non-motor vehicle violation detection and tracking method based on video stream |
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN111833609A (en) * | 2020-07-24 | 2020-10-27 | 王程 | Intelligent monitoring and automatic alarming highway real-time monitoring system |
| CN111798664A (en) * | 2020-09-08 | 2020-10-20 | 武汉中科通达高新技术股份有限公司 | Illegal data identification method and device and electronic equipment |
Non-Patent Citations (4)
| Title |
|---|
| XIAO TAN 等: "Multi-camera vehicle tracking and re-identification based on visual and spatial-temporal features", 《CVPR》, pages 275 - 284 * |
| 官伟: "基于ArcGIS的交通卡口管理平台设计", 《中国优秀硕士学位论文全文数据库基础科学辑》, pages 008 - 85 * |
| 杨德山: "高速公路卡口系统中海量统计与备份恢复等子系统的实现——中心端软件部分", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》, pages 138 - 627 * |
| 贾桢: "长春市视频监控与智能卡口系统的设计与实施", 《中国优秀硕士学位论文全文数据库信息科技辑》, pages 140 - 493 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220888A (en) * | 2021-06-01 | 2021-08-06 | 上海交通大学 | Case clue element extraction method and system based on Ernie model |
| CN115662190A (en) * | 2022-12-23 | 2023-01-31 | 深圳曦华科技有限公司 | Prompt message processing method and device for vehicle based on road abnormal state recognition |
| CN115662190B (en) * | 2022-12-23 | 2023-03-21 | 深圳曦华科技有限公司 | Prompt message processing method and device for vehicle based on road abnormal state recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390262B (en) | Video analysis method, device, server and storage medium | |
| CN113157578B (en) | Automatic driving simulation test method and device based on scene | |
| CN111723727A (en) | Cloud monitoring method and device based on edge computing, electronic equipment and storage medium | |
| CN113111838B (en) | Behavior recognition method and device, equipment and storage medium | |
| CN110909699A (en) | Video vehicle non-guide driving detection method and device and readable storage medium | |
| CN104063712A (en) | Vehicle information extraction method and system thereof | |
| CN109377694B (en) | Monitoring method and system for community vehicles | |
| CN112200067B (en) | Intelligent video event detection method, system, electronic equipment and storage medium | |
| CN112380993A (en) | Intelligent illegal behavior detection system and method based on target real-time tracking information | |
| CN115830399B (en) | Classification model training method, device, equipment, storage medium and program product | |
| CN112233428B (en) | Traffic flow prediction method, device, storage medium and equipment | |
| CN109872541A (en) | A kind of information of vehicles analysis method and device | |
| CN111914648A (en) | Vehicle detection and identification method and device, electronic equipment and storage medium | |
| CN112434566A (en) | Passenger flow statistical method and device, electronic equipment and storage medium | |
| CN117746103A (en) | Method and device for identifying illegal behaviors | |
| CN114495128A (en) | Subtitle information detection method, device, equipment and storage medium | |
| CN110414375A (en) | Recognition methods, device, storage medium and the electronic equipment of low target | |
| Kejriwal et al. | Vehicle detection and counting using deep learning basedYOLO and deep SORT algorithm for urban traffic management system | |
| CN111985304A (en) | Patrol alarm method, system, terminal equipment and storage medium | |
| CN110766938B (en) | Road network topological structure construction method and device, computer equipment and storage medium | |
| CN110717475A (en) | Automatic driving scene classification method and system | |
| CN112529116B (en) | Scene element fusion processing method, device and equipment and computer storage medium | |
| CN114913470A (en) | Event detection method and device | |
| CN112312205B (en) | Video processing method and device, electronic equipment and computer storage medium | |
| CN114511825A (en) | Method, device and equipment for detecting area occupation and storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: 266000 3rd floor, building 3, optical valley software park, 396 Emeishan Road, Huangdao District, Qingdao City, Shandong Province Applicant after: QINGDAO YISA DATA TECHNOLOGY Co.,Ltd. Applicant after: Qingdao Issa Technology Co.,Ltd. Applicant after: Anhui Issa Data Technology Co.,Ltd. Address before: 266000 3rd floor, building 3, optical valley software park, 396 Emeishan Road, Huangdao District, Qingdao City, Shandong Province Applicant before: QINGDAO YISA DATA TECHNOLOGY Co.,Ltd. Applicant before: BEIJING YISA TECHNOLOGY Co.,Ltd. Applicant before: Anhui Issa Data Technology Co.,Ltd. Address after: 266000 3rd floor, building 3, optical valley software park, 396 Emeishan Road, Huangdao District, Qingdao City, Shandong Province Applicant after: QINGDAO YISA DATA TECHNOLOGY Co.,Ltd. Applicant after: Issa Technology Co.,Ltd. Applicant after: Anhui Issa Data Technology Co.,Ltd. Address before: 266000 3rd floor, building 3, optical valley software park, 396 Emeishan Road, Huangdao District, Qingdao City, Shandong Province Applicant before: QINGDAO YISA DATA TECHNOLOGY Co.,Ltd. Applicant before: Qingdao Issa Technology Co.,Ltd. Applicant before: Anhui Issa Data Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 266400 Room 302, building 3, Office No. 77, Lingyan Road, Huangdao District, Qingdao, Shandong Province Applicant after: QINGDAO YISA DATA TECHNOLOGY Co.,Ltd. Applicant after: Issa Technology Co.,Ltd. Applicant after: Anhui Issa Data Technology Co.,Ltd. Address before: 266000 3rd floor, building 3, optical valley software park, 396 Emeishan Road, Huangdao District, Qingdao City, Shandong Province Applicant before: QINGDAO YISA DATA TECHNOLOGY Co.,Ltd. Applicant before: Issa Technology Co.,Ltd. Applicant before: Anhui Issa Data Technology Co.,Ltd. |
|
| CB02 | Change of applicant information |