CN113269042B - Intelligent traffic management method and system based on driving vehicle violation identification - Google Patents
Intelligent traffic management method and system based on driving vehicle violation identification Download PDFInfo
- Publication number
- CN113269042B CN113269042B CN202110450498.1A CN202110450498A CN113269042B CN 113269042 B CN113269042 B CN 113269042B CN 202110450498 A CN202110450498 A CN 202110450498A CN 113269042 B CN113269042 B CN 113269042B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- violation
- abnormal
- illegal
- image
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 50
- 230000002159 abnormal effect Effects 0.000 claims abstract description 65
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000006399 behavior Effects 0.000 claims description 64
- 230000000875 corresponding effect Effects 0.000 claims description 31
- 238000004458 analytical method Methods 0.000 claims description 28
- 238000004891 communication Methods 0.000 claims description 12
- 230000009471 action Effects 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 8
- 238000010191 image analysis Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000003825 pressing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012423 maintenance 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
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- 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
Abstract
The invention discloses an intelligent traffic management method and system based on driving vehicle violation identification, wherein the method comprises the following steps: acquiring each vehicle in a monitoring video of a current monitoring point; determining a vehicle with abnormal running track, and marking the vehicle as a violation vehicle to be determined; obtaining a geographic position before the starting time of the abnormal driving track of the violation vehicle to be determined; judging whether the running track of the illegal vehicle after passing through the geographic position is illegal or not according to whether the running tracks of other vehicles after passing through the geographic position are abnormal. According to the method and the device for determining the illegal vehicle, whether the illegal vehicle to be determined breaks rules or not is determined by determining whether the running track of the illegal vehicle to be determined and the running track of other vehicles at the same geographic position of the illegal behavior of the vehicle are abnormal, so that the accuracy of the judgment of the illegal vehicle is improved.
Description
Technical Field
The invention relates to the technical field of traffic management, in particular to an intelligent traffic management method and system based on driving vehicle violation identification.
Background
In the prior art, for detecting and managing a vehicle violation event in traffic management, the detection of the violation and the determination of a driver are generally automatically performed through image analysis, however, in the traffic management process, the traffic environment and traffic facility equipment are abnormally diverse and may not be timely handled in operation and maintenance, so that some errors can occur in the violation judgment of the abnormal vehicle running track only through image acquisition and image analysis.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent traffic management method and system based on the identification of the driving vehicle violations, so as to improve the accuracy of the judgment of the vehicle violations in the traffic management process.
In a first aspect, the present application provides an intelligent traffic management method based on identification of a violation of a traveling vehicle, including:
acquiring each vehicle in a monitoring video of a current monitoring point;
determining a vehicle with abnormal running track, and marking the vehicle as a violation vehicle to be determined;
obtaining a geographic position before the starting time of the abnormal driving track of the violation vehicle to be determined;
judging whether the running track of the illegal vehicle after passing through the geographic position is illegal or not according to whether the running track of other vehicles after passing through the geographic position is abnormal or not;
when the vehicle judges that the violation occurs, obtaining a violation state image of the vehicle, a violation driver, confirming the image of the violation driver and storing violation punishment object information in a correlated mode.
Based on the first aspect, in some possible implementation manners, the determining the vehicle with abnormal running track includes:
inputting the monitoring video image into a preset multi-violation probability distribution analysis model to obtain the prediction probability of at least one violation of the vehicle;
taking the vehicle violation behavior image as a first violation image set, and acquiring target associated data based on the first violation image set;
and determining the violation behaviors of the vehicle according to the target association data and at least one violation behavior analysis model, wherein the target association judgment data is image feature data preset by each violation behavior analysis model and used for analyzing one type of violation behaviors.
Based on the first aspect, in some possible implementations, the taking the vehicle violation image as the first violation image set includes:
the prediction probability of at least one violation of the vehicle is output based on the multi-violation probability distribution analysis model;
sequencing the probability of each driving behavior from big to small;
if the probability that the running behavior of the vehicle is normal is maximum and is greater than a first preset threshold value, not extracting a video image corresponding to the running track of the vehicle;
otherwise, extracting a video image corresponding to the running track of the vehicle as a first violation image set.
Based on the first aspect, in some possible implementations, the determining the violation of the vehicle according to the target association data and the at least one violation analysis model includes:
based on the target association judgment data, judging whether the target association judgment data is abnormal or not through a preset judgment rule for different kinds of illegal behaviors, and determining that the illegal behaviors corresponding to the target association judgment data occur for the abnormal data.
Based on the first aspect, in some possible implementation manners, the target association determination data adopted by different violation analysis models are different, and the method for acquiring the target association determination data includes:
extracting general features based on the monitoring video image, including a positioning area of the vehicle in the image;
and acquiring the special characteristics corresponding to the abnormal driving behavior category based on the monitoring video image.
Based on the first aspect, in some possible implementation manners, the general feature is extracted based on the monitoring video image, the pixel processing is performed by adopting a convolutional neural network to obtain a pixel-level feature, the characteristic feature corresponding to the abnormal driving behavior category is obtained based on the monitoring video image, and the characteristic feature corresponding to the abnormal driving behavior category is obtained by analyzing a second preset number of image frames based on the pixel-level feature of each frame of image.
Based on the first aspect, in some possible implementation manners, the determining whether the driving track of the violation vehicle to be determined after the geographic location violates the rule according to whether the driving track of the other vehicle after passing through the geographic location is abnormal includes:
and in a period of continuous time before and after the vehicle passes through the geographic position, judging that the driving track of the geographic position of the vehicle is not in violation if the violation behaviors of all other vehicles passing through the geographic position are consistent with the vehicle.
In a second aspect, the present application provides an intelligent traffic management system based on identification of a violation of a traveling vehicle, comprising:
the video image unit is used for acquiring each vehicle in the monitoring video of the current monitoring point;
the to-be-determined illegal vehicle acquisition unit is used for determining a vehicle with abnormal running track and recording the vehicle as the to-be-determined illegal vehicle;
the abnormal track information acquisition unit is used for acquiring the geographic position before the starting time of the abnormal running track of the violation vehicle to be determined;
the illegal vehicle acquisition unit is used for judging whether the running track of the illegal vehicle after passing through the geographic position is illegal or not according to whether the running track of other vehicles after passing through the geographic position is abnormal;
and the violation information storage unit is used for obtaining the violation state image of the vehicle, the violation driver, confirming the image of the violation driver and the violation punishment object information for associated storage when the vehicle judges that the violation occurs.
In a third aspect, the present application provides an intelligent traffic management device, comprising: a processor and a communication interface;
the communication interface is coupled with the processor, and the processor acquires a monitoring video image of the current monitoring point through the communication interface;
the processor is configured to support the intelligent traffic management device to implement the functions of the first aspect or any possible implementation manner of the first aspect.
Based on the third aspect, in some possible implementations, the intelligent traffic management device further includes: the memory is used for storing computer execution instructions and data necessary for the intelligent traffic management equipment; and when the intelligent traffic management equipment runs, the processor executes the computer execution instructions stored in the memory so as to enable the intelligent traffic management equipment to execute the intelligent traffic management method.
The intelligent traffic management method and system based on the driving vehicle violation identification have the following beneficial effects:
1. the method has the advantages that the vehicle with abnormal running track is determined to be the illegal vehicle to be determined based on image analysis, and then whether the illegal vehicle to be determined is illegal is determined by judging whether the running track of other vehicles is abnormal at the same geographic position of the illegal behavior of the vehicle, so that the accuracy of the judgment of the illegal vehicle is improved, and misjudgment only based on image acquisition and image analysis is avoided.
2. The monitoring video image is input into a preset multi-violation probability distribution analysis model to obtain the prediction probability of at least one violation of the vehicle, and whether the vehicle violation actually occurs or not is determined according to the prediction probability and the corresponding violation analysis model, so that the accurate judgment of multiple possible violations is realized, and the accuracy of the image analysis on the violations is improved.
Drawings
FIG. 1 is a flow chart of an intelligent traffic management method based on identification of driving vehicle violations in an embodiment of the present invention;
FIG. 2 is a flow chart of a method of analyzing vehicle violations in an embodiment of the present invention;
fig. 3 is a block diagram of an intelligent traffic management system based on identification of driving vehicle violations in an embodiment of the present invention.
Detailed Description
Embodiments of the present application are described below with reference to the accompanying drawings in the embodiments of the present application. In the following description, reference is made to the accompanying drawings which form a part hereof and which show by way of illustration specific aspects in which embodiments of the application may be practiced. It is to be understood that the embodiments of the present application may be used in other respects and may include structural or logical changes not depicted in the drawings. The following detailed description is, therefore, not to be taken in a limiting sense. For example, it should be understood that the disclosure in connection with the described methods may be equally applicable to a corresponding apparatus or system for performing the methods, and vice versa. For example, if one or more specific method steps are described, the corresponding apparatus may comprise one or more units, such as functional units, to perform the one or more described method steps (e.g., one unit performing one or more steps, or multiple units each performing one or more of the multiple steps), even if such one or more units are not explicitly described or illustrated in the figures. On the other hand, if a specific apparatus is described based on one or more units such as a functional unit, for example, the corresponding method may include one step to perform the functionality of the one or more units (e.g., one step to perform the functionality of the one or more units, or multiple steps each to perform the functionality of one or more units, even if such one or more steps are not explicitly described or illustrated in the figures). Further, it is to be understood that features of the various exemplary embodiments and/or aspects described herein may be combined with each other, unless explicitly stated otherwise.
The intelligent traffic management method based on the driving vehicle violation identification, provided by the embodiment of the application, comprises the following steps:
(1) Acquiring each vehicle in a monitoring video of a current monitoring point;
(2) Determining a vehicle with abnormal running track, and marking the vehicle as a violation vehicle to be determined;
(3) Obtaining a geographic position before the starting time of the abnormal driving track of the violation vehicle to be determined;
(4) Judging whether the running track of the illegal vehicle after passing through the geographic position is illegal or not according to whether the running track of other vehicles after passing through the geographic position is abnormal or not;
specifically, in the step, whether the running track of the violation vehicle after passing through the geographic position to be determined is violating is judged according to whether the running track of other vehicles after passing through the geographic position is abnormal or not, including:
and in a period of continuous time before and after the vehicle passes through the geographic position, judging that the driving track of the geographic position of the vehicle is not in violation if the violation behaviors of all other vehicles passing through the geographic position are consistent with the vehicle.
(5) When the vehicle judges that the violation occurs, obtaining a violation state image of the vehicle, a violation driver, confirming the image of the violation driver and storing violation punishment object information in a correlated mode.
In the embodiment of the invention, the vehicle with abnormal running track is determined, the vehicle with abnormal running track can be the vehicle with illegal action determined based on video image analysis, the vehicle is determined as the vehicle with illegal action possibly, then whether the running track of other vehicles at the same geographic position is abnormal or not is determined according to the geographic position of the vehicle with illegal action, if the running tracks of other vehicles at the same geographic position are all abnormal, the vehicle can be specifically set as the vehicle with illegal action determined according to the video image analysis, and if the running tracks of other vehicles at the same geographic position are all abnormal, the cause of the running abnormality of the vehicle with illegal action to be determined can be determined as follows: the abnormal lane pavement of the current monitoring point causes abnormal lane vehicle running track, or the acquisition parameters (such as attribute information of an acquisition device acquisition image) of the current monitoring point for carrying out illegal behavior analysis, analysis algorithm parameters and the like are wrong, so that the running track is wrongly analyzed, particularly, the unclear or partial missing of the lane line in the acquisition image causes inaccurate identification of the lane line, and further, the judgment of the abnormal running track such as the vehicle line pressing and the like is wrong. If the running track of other vehicles in the same geographic position is normal, determining that the vehicle to be determined is a violation vehicle, and storing the violation associated data of the vehicle including the violation evidence, the driver of the vehicle violation and the violation punishment object information in a multidimensional manner so as to analyze big data of traffic violation information in the later stage and the like.
In the step (2), determining a vehicle having an abnormal running track, including:
(21) Inputting the monitoring video image into a preset multi-violation probability distribution analysis model to obtain the prediction probability of at least one violation of the vehicle;
in this step, the vehicle driving characteristics in the image are extracted based on the monitoring video, and the probability that the vehicle driving process belongs to a plurality of driving behaviors is judged based on the driving characteristics, wherein the vehicle driving behaviors comprise normal driving track and abnormal driving track, the abnormal driving track can comprise various vehicle illegal driving behaviors, such as overspeed, red light running, solid line lane changing, solid line pressing and the like, and the probability of each possible driving behavior can be analyzed through a probability neural network to obtain the occurrence probability of various driving behaviors including normal driving track and each illegal driving behavior.
(22) Taking the vehicle violation behavior image as a first violation image set, and acquiring target associated data based on the first violation image set;
(23) And determining the violation behaviors of the vehicle according to the target association data and at least one violation behavior analysis model, wherein the target association judgment data is image feature data preset by each violation behavior analysis model and used for analyzing one type of violation behaviors.
Each violation analysis model is used for specifically analyzing and judging whether a violation occurs, and analyzing whether the violation occurs according to input target association data, wherein the target association data is feature data which is extracted based on the first violation image set and is used for analyzing whether the violation occurs.
In the embodiment of the invention, probability distribution prediction is performed on various possible running behaviors of the vehicle, the current most possible running behavior of the vehicle is judged according to the probability, and further accurate analysis is performed on the basis of the most possible running behavior and the target associated data, so that the determined type of the illegal behavior of the vehicle is obtained.
The taking the vehicle violation image as the first violation image set includes:
the prediction probability of at least one violation of the vehicle is output based on the multi-violation probability distribution analysis model;
sequencing the probability of each driving behavior from big to small;
if the probability that the running behavior of the vehicle is normal is maximum and is greater than a first preset threshold value, not extracting a video image corresponding to the running track of the vehicle;
otherwise, extracting a video image corresponding to the running track of the vehicle as a first violation image set.
In this embodiment, when the probability that the vehicle running behavior belongs to the normal situation is the largest and is greater than the first preset threshold, it is determined that the vehicle does not have the offending running behavior, otherwise, specific abnormal running behavior analysis is performed based on the extracted first offending image set, specifically, the abnormal running behavior is sequentially determined from large to small according to the prediction probability of each abnormal running behavior category, it is assumed that the abnormal running behavior is sequentially the first abnormal behavior, the second abnormal behavior and the third abnormal behavior according to the occurrence probability from large to small, the corresponding occurrence probabilities are the first probability, the second probability and the third probability respectively, then the first abnormal behavior category corresponding to the first probability value is analyzed based on the first offending image set, if the first abnormal behavior is determined to occur based on the first offending image set, then the offending behavior of the vehicle is determined to be the first abnormal behavior, otherwise, the second abnormal behavior category corresponding to the second probability value is firstly analyzed based on the first offending image set, and the abnormal behavior category determining process is repeated, and the offending behavior category of the vehicle is obtained.
Determining the violation of the vehicle according to the target associated data and the at least one violation analysis model, which means determining whether a specific violation occurs, includes:
based on the target association judgment data, judging whether the target association judgment data is abnormal or not through a preset judgment rule for different kinds of illegal behaviors, and determining that the illegal behaviors corresponding to the target association judgment data occur for the abnormal data.
The target association judgment data is obtained based on the running track video extraction of the vehicle, and the target association judgment data of different abnormal running behaviors are different, for example, when the abnormal running behavior is overspeed running, the positioning, displacement, time characteristic data and the like in the running process of the vehicle are extracted based on the monitoring video image, and when the abnormal running behavior is line pressing, the edge line, lane line characteristics and the like of the target vehicle in the running process of the vehicle are extracted.
The rule for determining the different types of violations is described by taking rule for determining the violations of red light running as an example, and the rule for determining the violations can be:
acquiring stop lines of all lanes of a traffic intersection;
obtaining a red light time period in each driving direction;
acquiring lane stop line position monitoring video data in a red light time period in a driving direction;
extracting an image frame sequence based on the monitoring video;
acquiring a current image frame, and recording vehicles positioned in a stop line on the frame image as a first vehicle set;
acquiring vehicles in a stop line on the image frame for the next image frame, and marking the vehicles as a second vehicle set;
and comparing the first vehicle set with the second vehicle set, and acquiring vehicles in the first vehicle set and vehicles in the second vehicle set which are not present as red light running illegal vehicles, namely, the vehicles are subjected to red light running illegal behaviors.
Further, in order to accurately analyze whether different violations occur, target association determination data adopted by different violation analysis models are different, each violation analysis model adopts feature data matched with a corresponding violation as target association determination data, and the method for acquiring the target association determination data comprises the following steps:
extracting general features based on the monitoring video image, including a positioning area of the vehicle in the image;
and acquiring the special characteristics corresponding to the abnormal driving behavior category based on the monitoring video image. The method for extracting the general features based on the monitoring video image, adopting a convolutional neural network to perform pixel processing to obtain pixel-level features, and obtaining the special features corresponding to the abnormal driving behavior category based on the monitoring video image comprises the following steps: and analyzing a second preset number of image frames based on the pixel-level characteristics of each frame of image to acquire special characteristics corresponding to the abnormal driving behavior category.
In the embodiment of the invention, the first step can be to perform the training of detecting, identifying and tracking and positioning the vehicle target through a convolutional neural network, accurately find the vehicle target in the image through the analysis of the neural network at the pixel level, remove the pixel points of the non-vehicle target including the shadow and other background pixel points of the vehicle in the image through the pixel value distribution analysis of the single frame image, and position the target of the adjacent image frame of the continuous image of the target vehicle through the change of the corresponding pixel values of the continuous multi-frame image; and the second step is to further acquire macroscopic violation characteristic data of the vehicle based on the position area of the vehicle with continuous image frames, wherein the macroscopic violation characteristic data comprises characteristics for judging whether the vehicle runs red light, changes lanes with solid lines and other illegal driving behaviors, such as displacement change, accurate contour lines and the like of the vehicle, and the vehicle is analyzed based on corresponding judging rules through different special characteristics to realize judgment of different abnormal driving behavior types.
Based on the same inventive concept as the above method, the embodiment of the present invention provides an intelligent traffic management system based on recognition of a violation of a driving vehicle, where the intelligent traffic management system may implement the intelligent traffic management method in each embodiment, and the intelligent traffic management system may be a functional module for implementing the method described in each embodiment, where the functional module may be implemented by executing corresponding software by hardware, where the hardware or software includes one or more modules corresponding to the functions described above, for example, in one possible implementation manner, the intelligent traffic management system based on recognition of a violation of a driving vehicle according to the embodiment of the present invention includes:
the video image unit is used for acquiring each vehicle in the monitoring video of the current monitoring point;
the to-be-determined illegal vehicle acquisition unit is used for determining a vehicle with abnormal running track and recording the vehicle as the to-be-determined illegal vehicle;
the abnormal track information acquisition unit is used for acquiring the geographic position before the starting time of the abnormal running track of the violation vehicle to be determined;
the illegal vehicle acquisition unit is used for judging whether the running track of the illegal vehicle after passing through the geographic position is illegal or not according to whether the running track of other vehicles after passing through the geographic position is abnormal;
and the violation information storage unit is used for obtaining the violation state image of the vehicle, the violation driver, confirming the image of the violation driver and the violation punishment object information for associated storage when the vehicle judges that the violation occurs.
Based on the same inventive concept as the above method, an embodiment of the present invention provides an intelligent traffic management device, including: a processor and a communication interface;
the communication interface is coupled with the processor, and the processor acquires a monitoring video image of the current monitoring point through the communication interface;
the processor is used for supporting the intelligent traffic management equipment to realize the intelligent traffic management method.
In some possible embodiments, the intelligent traffic management device further comprises: the memory is used for storing computer execution instructions and data necessary for the intelligent traffic management equipment; and when the intelligent traffic management equipment runs, the processor executes the computer execution instructions stored in the memory so as to enable the intelligent traffic management equipment to execute the intelligent traffic management method.
Those of skill in the art will appreciate that the functions described in connection with the various illustrative logical blocks, modules, and algorithm steps described in connection with the disclosure herein may be implemented as hardware, software, firmware, or any combination thereof. If implemented in software, the functions described by the various illustrative logical blocks, modules, and steps may be stored on a computer readable medium or transmitted as one or more instructions or code and executed by a hardware-based processing unit. Computer-readable media may include computer-readable storage media corresponding to tangible media, such as data storage media, or communication media including any medium that facilitates transfer of a computer program from one place to another (e.g., according to a communication protocol). In this manner, a computer-readable medium may generally correspond to (1) a non-transitory tangible computer-readable storage medium, or (2) a communication medium, such as a signal or carrier wave. Data storage media may be any available media that can be accessed by one or more computers or one or more processors to retrieve instructions, code and/or data structures for implementing the techniques described herein. The computer program product may include a computer-readable medium.
By way of example, and not limitation, such computer-readable storage media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium.
The present invention is not limited to the above-described specific embodiments, and various modifications may be made by those skilled in the art without inventive effort from the above-described concepts, and are within the scope of the present invention.
Claims (9)
1. The intelligent traffic management method based on the driving vehicle violation identification is characterized by comprising the following steps:
acquiring each vehicle in a monitoring video of a current monitoring point;
determining a vehicle with abnormal running track, and marking the vehicle as a violation vehicle to be determined;
obtaining a geographic position before the starting time of the abnormal driving track of the violation vehicle to be determined;
judging whether the running track of the illegal vehicle after passing through the geographic position is illegal or not according to whether the running track of other vehicles after passing through the geographic position is abnormal or not, wherein the method specifically comprises the following steps: in a period of continuous time before and after the vehicle passes through the geographic position, judging that the driving track of the geographic position of the vehicle has no illegal action if the illegal actions of all other vehicles passing through the geographic position are consistent with the vehicle;
when the vehicle judges that the violation occurs, obtaining a violation state image of the vehicle, a violation driver, confirming the image of the violation driver and storing violation punishment object information in a correlated mode.
2. The intelligent traffic management method based on the identification of traveling vehicle violations according to claim 1, wherein the determining of the vehicle having the traveling track abnormality includes:
inputting the monitoring video image into a preset multi-violation probability distribution analysis model to obtain the prediction probability of at least one violation of the vehicle;
taking the vehicle violation behavior image as a first violation image set, and acquiring target associated data based on the first violation image set;
and determining the violation behaviors of the vehicle according to the target association data and at least one violation behavior analysis model, wherein the target association judgment data is image feature data preset by each violation behavior analysis model and used for analyzing one type of violation behaviors.
3. The intelligent traffic management method based on the identification of the driving vehicle violation according to claim 2, wherein the taking the vehicle violation image as the first violation image set includes:
the prediction probability of at least one violation of the vehicle is output based on the multi-violation probability distribution analysis model;
sequencing the probability of each driving behavior from big to small;
if the probability that the running behavior of the vehicle is normal is maximum and is greater than a first preset threshold value, not extracting a video image corresponding to the running track of the vehicle;
otherwise, extracting a video image corresponding to the running track of the vehicle as a first violation image set.
4. The intelligent traffic management method based on the identification of driving vehicle violations according to claim 2, wherein the determining of the vehicle's violations based on the target association data and at least one analysis model of the violations comprises:
based on the target association judgment data, judging whether the target association judgment data is abnormal or not through a preset judgment rule for different kinds of illegal behaviors, and determining that the illegal behaviors corresponding to the target association judgment data occur for the abnormal data.
5. The intelligent traffic management method based on the identification of the violations of the running vehicles according to claim 4, wherein the target association judgment data adopted by different analysis models of the violations are different, and the method for acquiring the target association judgment data comprises the following steps:
extracting general features based on the monitoring video image, including a positioning area of the vehicle in the image;
and acquiring the special characteristics corresponding to the abnormal driving behavior category based on the monitoring video image.
6. The intelligent traffic management method based on the driving vehicle violation identification according to claim 5, wherein the general feature is extracted based on a monitoring video image, a convolutional neural network is adopted for pixel processing to obtain a pixel-level feature, the characteristic feature corresponding to an abnormal driving behavior category is obtained based on the monitoring video image, and a second preset number of image frames are analyzed based on the pixel-level feature of each frame image to obtain the characteristic feature corresponding to the abnormal driving behavior category.
7. Intelligent traffic management system based on recognition of driving vehicle violations, characterized by comprising:
the video image unit is used for acquiring each vehicle in the monitoring video of the current monitoring point;
the to-be-determined illegal vehicle acquisition unit is used for determining a vehicle with abnormal running track and recording the vehicle as the to-be-determined illegal vehicle;
the abnormal track information acquisition unit is used for acquiring the geographic position before the starting time of the abnormal running track of the violation vehicle to be determined;
the illegal vehicle obtaining unit is used for judging whether the running track of the illegal vehicle to be determined after the geographic position is illegal according to whether the running track of other vehicles after passing through the geographic position is abnormal, and comprises the following steps: in a period of continuous time before and after the vehicle passes through the geographic position, judging that the driving track of the geographic position of the vehicle has no illegal action if the illegal actions of all other vehicles passing through the geographic position are consistent with the vehicle;
and the violation information storage unit is used for obtaining the violation state image of the vehicle, the violation driver, confirming the image of the violation driver and the violation punishment object information for associated storage when the vehicle judges that the violation occurs.
8. An intelligent traffic management device, comprising: a processor and a communication interface;
the communication interface is coupled with the processor, and the processor acquires a monitoring video image of the current monitoring point through the communication interface;
the processor is configured to support the intelligent traffic management device to implement the intelligent traffic management method according to any one of claims 1 to 6.
9. The apparatus of claim 8, wherein the intelligent traffic management apparatus further comprises: the memory is used for storing computer execution instructions and data necessary for the intelligent traffic management equipment; when the intelligent traffic management device is running, the processor executes the computer-executable instructions stored in the memory to cause the intelligent traffic management device to perform the intelligent traffic management method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110450498.1A CN113269042B (en) | 2021-04-25 | 2021-04-25 | Intelligent traffic management method and system based on driving vehicle violation identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110450498.1A CN113269042B (en) | 2021-04-25 | 2021-04-25 | Intelligent traffic management method and system based on driving vehicle violation identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113269042A CN113269042A (en) | 2021-08-17 |
| CN113269042B true CN113269042B (en) | 2024-03-29 |
Family
ID=77229298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110450498.1A Active CN113269042B (en) | 2021-04-25 | 2021-04-25 | Intelligent traffic management method and system based on driving vehicle violation identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113269042B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114255588A (en) * | 2021-11-29 | 2022-03-29 | 安徽百诚慧通科技有限公司 | Regional motor vehicle illegal parking prediction method, storage medium and device |
| CN115114312B (en) * | 2022-07-15 | 2023-06-27 | 北京百度网讯科技有限公司 | Map data updating method and device and electronic equipment |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012081963A1 (en) * | 2010-12-15 | 2012-06-21 | Mimos Bhd. | System and method for traffic violation detection |
| JP2013168016A (en) * | 2012-02-15 | 2013-08-29 | Toyota Motor Corp | Travel lane recognition device |
| CN105528894A (en) * | 2015-11-28 | 2016-04-27 | 浙江宇视科技有限公司 | Operation detection method and device for front-end monitoring devices based on track information |
| CN105761483A (en) * | 2014-12-16 | 2016-07-13 | 高德软件有限公司 | Vehicle data processing method and equipment thereof |
| KR20160092959A (en) * | 2016-05-19 | 2016-08-05 | 윤종식 | Method of preventing traffic accidents in crossroad for signal violation and overspeed, and system of the same |
| CN205680290U (en) * | 2016-06-01 | 2016-11-09 | 纪峥嵘 | A kind of vehicle travels monitoring device and system |
| CN106327863A (en) * | 2015-07-06 | 2017-01-11 | 北京文安智能技术股份有限公司 | Method, device and system for detection and early warning of vehicle congestion |
| CN106485927A (en) * | 2016-10-28 | 2017-03-08 | 江苏信息职业技术学院 | A kind of intelligent transportation violation information harvester and acquisition method |
| CN107038870A (en) * | 2017-05-11 | 2017-08-11 | 南宁市正祥科技有限公司 | A kind of vehicle peccancy detection method |
| CN108074400A (en) * | 2016-11-14 | 2018-05-25 | 北京航天长峰科技工业集团有限公司 | A kind of emphasis vehicle analysis model based on mass data analysis |
| CN109087506A (en) * | 2018-07-26 | 2018-12-25 | 东软集团股份有限公司 | A kind of vehicle monitoring method and device |
| CN110599353A (en) * | 2018-06-13 | 2019-12-20 | 百度在线网络技术（北京）有限公司 | Vehicle insurance and claims rate prediction method, device, equipment and medium |
| CN110738857A (en) * | 2018-07-18 | 2020-01-31 | 杭州海康威视数字技术股份有限公司 | vehicle violation evidence obtaining method, device and equipment |
| CN111259767A (en) * | 2020-01-13 | 2020-06-09 | 厦门大学 | Traffic illegal behavior identification method and system based on traffic data and street view data |
| CN111627217A (en) * | 2020-05-29 | 2020-09-04 | 济南博观智能科技有限公司 | Method, device and equipment for judging vehicle illegal turning around and storage medium |
| CN111680633A (en) * | 2020-06-10 | 2020-09-18 | 上海眼控科技股份有限公司 | Vehicle violation identification method and device, computer equipment and storage medium |
| CN112185115A (en) * | 2020-09-29 | 2021-01-05 | 南通智大信息技术有限公司 | Vehicle speed control method and device based on cloud platform |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017138694A (en) * | 2016-02-02 | 2017-08-10 | ソニー株式会社 | Picture processing device and picture processing method |
| JP7180565B2 (en) * | 2019-07-23 | 2022-11-30 | トヨタ自動車株式会社 | Signal interpretation system and vehicle control system |
-
2021
- 2021-04-25 CN CN202110450498.1A patent/CN113269042B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012081963A1 (en) * | 2010-12-15 | 2012-06-21 | Mimos Bhd. | System and method for traffic violation detection |
| JP2013168016A (en) * | 2012-02-15 | 2013-08-29 | Toyota Motor Corp | Travel lane recognition device |
| CN105761483A (en) * | 2014-12-16 | 2016-07-13 | 高德软件有限公司 | Vehicle data processing method and equipment thereof |
| CN106327863A (en) * | 2015-07-06 | 2017-01-11 | 北京文安智能技术股份有限公司 | Method, device and system for detection and early warning of vehicle congestion |
| CN105528894A (en) * | 2015-11-28 | 2016-04-27 | 浙江宇视科技有限公司 | Operation detection method and device for front-end monitoring devices based on track information |
| KR20160092959A (en) * | 2016-05-19 | 2016-08-05 | 윤종식 | Method of preventing traffic accidents in crossroad for signal violation and overspeed, and system of the same |
| CN205680290U (en) * | 2016-06-01 | 2016-11-09 | 纪峥嵘 | A kind of vehicle travels monitoring device and system |
| CN106485927A (en) * | 2016-10-28 | 2017-03-08 | 江苏信息职业技术学院 | A kind of intelligent transportation violation information harvester and acquisition method |
| CN108074400A (en) * | 2016-11-14 | 2018-05-25 | 北京航天长峰科技工业集团有限公司 | A kind of emphasis vehicle analysis model based on mass data analysis |
| CN107038870A (en) * | 2017-05-11 | 2017-08-11 | 南宁市正祥科技有限公司 | A kind of vehicle peccancy detection method |
| CN110599353A (en) * | 2018-06-13 | 2019-12-20 | 百度在线网络技术（北京）有限公司 | Vehicle insurance and claims rate prediction method, device, equipment and medium |
| CN110738857A (en) * | 2018-07-18 | 2020-01-31 | 杭州海康威视数字技术股份有限公司 | vehicle violation evidence obtaining method, device and equipment |
| CN109087506A (en) * | 2018-07-26 | 2018-12-25 | 东软集团股份有限公司 | A kind of vehicle monitoring method and device |
| CN111259767A (en) * | 2020-01-13 | 2020-06-09 | 厦门大学 | Traffic illegal behavior identification method and system based on traffic data and street view data |
| CN111627217A (en) * | 2020-05-29 | 2020-09-04 | 济南博观智能科技有限公司 | Method, device and equipment for judging vehicle illegal turning around and storage medium |
| CN111680633A (en) * | 2020-06-10 | 2020-09-18 | 上海眼控科技股份有限公司 | Vehicle violation identification method and device, computer equipment and storage medium |
| CN112185115A (en) * | 2020-09-29 | 2021-01-05 | 南通智大信息技术有限公司 | Vehicle speed control method and device based on cloud platform |
Non-Patent Citations (2)
| Title |
|---|
| iTV: Inferring Traffic Violation-Prone Locations With Vehicle Trajectories and Road Environment Data;Zhihan Jiang et al.;《arXiv.org》;第1-12页 * |
| 基于OGS-DTW算法的交通事件自动检测方法;张宁等;《公路交通科技》;第27卷(第8期);第103-108页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113269042A (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113269042B (en) | Intelligent traffic management method and system based on driving vehicle violation identification | |
| US10163038B2 (en) | Error detection in recognition data | |
| CN110288823B (en) | Traffic violation misjudgment identification method based on naive Bayesian network | |
| CN108932849B (en) | Method and device for recording low-speed running illegal behaviors of multiple motor vehicles | |
| CN112529109A (en) | Unsupervised multi-model-based anomaly detection method and system | |
| CN112541372B (en) | Difficult sample screening method and device | |
| CN114495498B (en) | Traffic data distribution effectiveness judging method and device | |
| CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
| CN111967451B (en) | Road congestion detection method and device | |
| CN107622667B (en) | Method and system for detecting altered license plate number | |
| CN112927498B (en) | Data analysis method and device based on intelligent traffic monitoring | |
| CN114495509A (en) | Method for monitoring tunnel running state based on deep neural network | |
| CN113902999A (en) | Tracking method, device, equipment and medium | |
| CN114407918B (en) | Takeover scene analysis method, takeover scene analysis device, takeover scene analysis equipment and storage medium | |
| CN116311080B (en) | Monitoring image detection method and device | |
| CN115841765B (en) | Vehicle position blind area monitoring method and device, electronic equipment and readable storage medium | |
| CN114155476B (en) | AEB (automatic Emergency bank) accident scene identification method, device, equipment and medium | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN115083038B (en) | Device and method for detecting abnormal running of vehicle | |
| US20230343148A1 (en) | Method of Digging Valuable Data and Server Using the Same | |
| CN112926823B (en) | Intelligent traffic service data detection method and device and electronic equipment | |
| CN112346985B (en) | ACC function failure determination method, system, device and storage medium | |
| CN117671308A (en) | Automatic driving test scene construction method and device, electronic equipment and medium | |
| CN115908359A (en) | Method, device, equipment and medium for detecting water spraying state of vehicle windscreen wiper | |
| CN116665190A (en) | Driver fatigue degree judging method and system based on face recognition |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |