CN112233421A - Intelligent city intelligent traffic monitoring system based on machine vision - Google Patents
Intelligent city intelligent traffic monitoring system based on machine vision Download PDFInfo
- Publication number
- CN112233421A CN112233421A CN202011105333.2A CN202011105333A CN112233421A CN 112233421 A CN112233421 A CN 112233421A CN 202011105333 A CN202011105333 A CN 202011105333A CN 112233421 A CN112233421 A CN 112233421A
- Authority
- CN
- China
- Prior art keywords
- accident
- violation
- picture
- vehicle
- pictures
- 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.)
- Withdrawn
Links
Images
Classifications
-
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- 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
-
- 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
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent system for monitoring urban intelligent traffic based on machine vision, which comprises an accident information input module, an accident video extraction and decomposition module, a vehicle violation behavior identification and analysis module, a violation behavior information base, an accident two-party responsibility division module and a display terminal, wherein the accident information input module is used for inputting basic information of an occurred traffic accident, extracting a traffic accident video through the input basic information of the traffic accident, simultaneously decomposing the traffic accident video into a plurality of accident pictures, combining each accident picture to identify a violation party and analyze the violation behavior of the violation party, further carrying out accident two-party responsibility division, being capable of carrying out intelligent processing on the traffic accident of urban traffic, making up the problems of delay of the existing traffic police in processing the traffic accident and poor accuracy of judging the violation party of the accident, having the characteristics of high intelligent degree and improving the traffic accident processing efficiency, the demand of modern traffic management is satisfied.
Description
Technical Field
The invention belongs to the technical field of urban traffic monitoring and management, and particularly relates to an intelligent urban intelligent traffic monitoring system based on machine vision.
Background
In recent years, with the development of cities, the number of motor vehicles is increasing, various traffic violations and traffic accidents between vehicles are also increasing, and meanwhile, due to the limited police force of a traffic management mechanism, all-weather and all-around management on all road sections and intersections cannot be performed by manpower. Therefore, when a traffic accident occurs, both accident parties need to give an alarm and wait for the traffic police to come before handling, so that a time process is needed before a traffic police comes, the time of both accident parties may be wasted in the time process, and the handling efficiency is reduced; the second time traffic police handles traffic accidents, and when traffic is analyzed for accident violation, subjective assumption may exist, which affects the accuracy of accident violation judgment and is difficult to meet the requirements of modern traffic management.
Disclosure of Invention
In order to make up for the defects of the prior art and aim at traffic accidents between vehicles, the invention provides an intelligent urban intelligent traffic monitoring system based on machine vision, which can intelligently analyze and identify the violation behaviors of accident violation parties by adopting a machine vision technology aiming at accident videos when a traffic accident occurs, accurately judge the responsibilities of both accident parties and meet the requirements of modern traffic management.
The technical scheme adopted by the invention for solving the technical problems is as follows: the invention relates to an urban intelligent traffic monitoring system based on machine vision, which comprises an accident information input module, an accident video extraction and decomposition module, a vehicle violation behavior identification and analysis module, a violation behavior information base, an accident two-party responsibility division module and a display terminal, wherein the accident information input module is respectively connected with the accident video extraction and decomposition module and the vehicle violation behavior identification and analysis module;
the accident information recording module is used for recording accident basic information into the system by both accident parties when a traffic accident occurs;
the accident video extracting and decomposing module is used for extracting an accident video from a monitoring video shot by a monitoring camera of a corresponding accident occurrence point according to accident basic information of the input system, decomposing the accident video into a plurality of accident pictures according to the number of extracted accident video frames, numbering the decomposed accident pictures according to a time sequence, and sequentially marking the number as 1,2, i.e. n;
the vehicle violation behavior recognition and analysis module is used for screening and processing each marked accident picture and recognizing the vehicle violation behavior according to the analysis of the target accident picture, wherein the vehicle violation behavior recognition and analysis module comprises an accident picture screening unit, an accident picture processing unit and a picture recognition and analysis unit;
the accident picture screening unit is used for analyzing and screening irrelevant accident pictures of the marked accident pictures, removing the accident pictures irrelevant to the accident, reserving accident pictures relevant to the accident, marking as target accident pictures, marking as 1,2.. j.. m respectively, and simultaneously sending the target accident pictures to the accident picture processing unit;
the accident picture processing unit carries out high-definition filtering processing on the received target accident pictures to obtain high-definition processed target accident pictures, and sends the high-definition processed target accident pictures to the picture identification and analysis unit;
the image identification and analysis unit is used for analyzing the violation behaviors of the vehicle according to the target accident images after high-definition processing, and the specific analysis method comprises the following steps:
step S1: acquiring accident vehicles in sequence from each target accident picture according to the marking sequence of the pictures, acquiring the license plate number of the accident vehicle if only one accident vehicle exists in a certain target accident picture, wherein the target accident picture is the violation analysis reference picture of the accident vehicle, acquiring the license plate numbers of the accident vehicles of both sides in the target accident picture if the accident vehicles of both sides are included in the certain target accident picture, and the target accident picture is the violation analysis reference picture of the accident vehicles of both sides, so that all the target accident pictures are divided into violation analysis reference picture sets of the vehicles of all the accident sides according to different accident vehicles included in the target accident picture, and the violation analysis reference picture sets are marked as A (a1, a2, a, ak, a), B (B1, B2, a, B g, B, g, a, B, bh) where ak is denoted as the kth violation analysis reference picture of the accident a-side vehicle, and bg is denoted as the g-th violation analysis reference picture of the accident B-side vehicle;
step S2: comparing each violation analysis reference picture in the violation analysis reference picture set of each vehicle of the accident with each violation picture corresponding to each violation behavior of the vehicle stored in the violation behavior information base, analyzing whether each violation analysis reference picture of each vehicle of the accident has a picture matched with each violation picture corresponding to each violation behavior of the vehicle, if any one or more target accident pictures in each violation analysis reference picture of the vehicle of a certain accident are successfully matched with each violation picture corresponding to each violation behavior of the vehicle, indicating that the accident party violates the rule, counting the number of violation accident parties at the moment, if only one violation accident party exists, executing step S3, and if the violation accident party is both parties, executing step S4;
step S3: sending the license plate number of the vehicle of the violation accident party to a duty dividing module of the accident party, counting the number of violation analysis reference pictures which are successfully matched with various violation pictures corresponding to various vehicle violations in various violation analysis reference pictures of the vehicle of the violation accident party, obtaining the violation behavior type corresponding to the violation analysis reference pictures which are successfully matched according to various violation pictures corresponding to various violation behaviors in a violation behavior information base, if the violation behavior types corresponding to all the violation analysis reference pictures which are successfully matched are the same type, the violation behavior type of the violation accident party is the type, recording the violation behavior type name, and sending the violation behavior type name to the duty dividing module of the accident party, if the violation behavior types corresponding to all the vehicle violation analysis reference pictures which are successfully matched are different types, the violation of the violation accident party is a violation type violation behavior, recording the names of various violation behavior types, and sending the names to a responsibility division module of both accident parties;
step S4: sending the license plate numbers of the vehicles of the illegal accident parties to a liability division module of the accident parties, acquiring the violation types corresponding to the illegal accident parties according to the method of step S3, if the violation types corresponding to the illegal accident parties are only one, extracting violation coefficients corresponding to the illegal behaviors in a violation information base, comparing the violation types corresponding to the accident parties with the violation coefficients corresponding to the illegal behaviors, screening the violation coefficients corresponding to the violation types of the illegal accident parties, sending the violation coefficients to the liability division module of the accident parties, if the violation types corresponding to the illegal accident parties are not only one, comparing the violation types corresponding to the accident parties with the violation coefficients corresponding to the illegal behaviors, screening the violation coefficients corresponding to the violation types of the illegal accident parties, and sending the data to a responsibility division module of both parties of the accident;
the accident party responsibility division module carries out classification processing on the received illegal accident party information, the illegal behavior type and the illegal coefficient, and the processing process comprises the following steps:
step W1: if only one accident party breaks rules, the license plate number of the violation accident party is sent to a display terminal;
step W2: if both accident sides violate rules and both violation behavior types corresponding to the accident sides are one, comparing violation coefficients corresponding to the violation behavior types of the accident sides, wherein the larger violation coefficient is marked as a main violation accident side, the smaller violation coefficient is marked as a secondary violation accident side, and sending the license plate numbers of the vehicle sides, the violation main and secondary and the violation coefficients of the accident sides to a display terminal;
step W3: if both accident parties violate rules and the violation types corresponding to the accident parties are multiple, overlapping violation coefficients corresponding to the violation types of the accident parties to obtain comprehensive violation coefficients corresponding to the accident parties, marking the party with the larger comprehensive violation coefficient as a main violation accident party, and marking the party with the smaller comprehensive violation coefficient as a secondary violation accident party, and sending the vehicle license plate numbers, the violation main and secondary numbers and the comprehensive violation coefficients of the accident parties to a display terminal;
and the display terminal receives and displays the license plate number, the violation behavior type, the violation primary and the violation coefficient of the violation accident party, which are sent by the accident party responsibility division module.
As an embodiment of the present invention, the violation information base is configured to store various violation pictures corresponding to various vehicle violations, and store violation coefficients corresponding to various vehicle violations.
As an embodiment of the present invention, the accident basic information includes accident occurrence position information, accident occurrence time information, and accident both-side information, and the accident both-side information includes owner name, contact information, and license plate number of the accident both-side.
As an embodiment of the present invention, a specific process of the accident video extracting and decomposing module extracting the accident video is as follows:
step H1: screening accident occurrence positions from accident basic information recorded into a system, selecting a monitoring camera corresponding to the accident occurrence position from a plurality of monitoring cameras according to the accident occurrence positions, and acquiring a monitoring video corresponding to the monitoring camera;
step H2: screening accident occurrence time from accident basic information input into a system, recording the accident occurrence time as a video extraction starting time point, and acquiring a video extraction finishing time point through a preset video extraction time period;
step H3: and according to the obtained video extraction starting time point and the obtained video extraction ending time point, searching the monitoring video positions corresponding to the video extraction starting time point and the video extraction ending time point from the obtained monitoring video corresponding to the monitoring camera, and extracting the section of monitoring video to be recorded as an accident video.
As an embodiment of the present invention, the video extraction end time point obtaining method is adding a video extraction start time point to a video extraction time period.
As an embodiment of the present invention, the screening of the accident-independent picture by the accident picture screening unit specifically includes the following steps:
step K1: checking whether a vehicle exists in each marked accident picture, if the vehicle does not exist in a certain accident picture, indicating that the accident picture is a picture irrelevant to the accident, recording the number of the accident picture, and if the vehicle exists in the certain accident picture, executing a step K2;
step K2: counting the number of accident pictures of existing vehicles, extracting the license plate numbers of the vehicles from the accident pictures of the existing vehicles, simultaneously extracting the license plate numbers of the vehicles at two sides of the accident from the recorded basic information of the accident, matching the extracted license plate numbers from the accident pictures of the existing vehicles with the license plate numbers of the vehicles at two sides of the accident one by one, if any one or both of the extracted license plate numbers from the accident pictures of a certain existing vehicle and the license plate numbers of the vehicles at two sides of the accident are matched, the matching is successful, the vehicles in the accident pictures of the existing vehicles are the accident vehicles, the accident pictures of the existing vehicles are related to the accident, the accident pictures are kept, if any one of the extracted license plate numbers from the accident pictures of a certain existing vehicle and the license plate numbers of the vehicles at two sides of the accident is not matched, the matching is failed, the accident picture of the existing vehicle is shown to be irrelevant to the accident, and the serial number of the accident picture is recorded;
step K3: counting the accident picture numbers recorded in the step K1 and the step K2, and screening the accident pictures which are not related to the accident from the decomposed accident pictures.
The invention has the following beneficial effects:
1. the invention inputs the basic information of the traffic accident through the accident information input module, extracting a traffic accident video through the input accident basic information, simultaneously decomposing the video into a plurality of accident pictures, identifying violation parties by combining the accident pictures and analyzing violation behaviors of the violation parties, further, the responsibility division of accident parties is carried out, the vehicle traffic accident of urban traffic can be intelligently processed, the problems of delay of traffic accident processing and poor judgment accuracy of accident violation parties of the existing traffic police are solved, the intelligent traffic accident processing system has the characteristic of high intelligent degree, the traffic accident processing efficiency is improved, and then the traffic road is recovered to be normal as soon as possible, road congestion caused by traffic accidents is avoided, secondary traffic accidents caused by the fact that the traffic accidents are not processed in time are effectively reduced, and the requirements of modern traffic management are met.
2. According to the invention, the independent accident picture screening is carried out on each decomposed accident picture in the vehicle violation behavior recognition and analysis module, so that the accident pictures related to the accident are reserved, the accident violation side and violation behaviors can be analyzed conveniently according to the accident pictures related to the accident at the later stage, the analysis progress and the analysis result of the accident pictures related to the accident are prevented from being disturbed, and the analysis efficiency and the analysis accuracy are improved.
Drawings
The invention is further described with the aid of the accompanying drawings, in which the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a block diagram of the present invention;
FIG. 2 is a block diagram of a vehicle violation identification and analysis module according to the present invention;
fig. 3 is a block diagram of the structure of the accident both-side responsibility division module of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
As shown in fig. 1 to 3, the intelligent city intelligent traffic monitoring system based on machine vision comprises an accident information recording module, an accident video extracting and decomposing module, a vehicle violation behavior identifying and analyzing module, a violation behavior information base, an accident both-side responsibility dividing module and a display terminal, wherein the accident information recording module is respectively connected with the accident video extracting and decomposing module and the vehicle violation behavior identifying and analyzing module, the accident video extracting and decomposing module is connected with the vehicle violation behavior identifying and analyzing module, the vehicle violation behavior identifying and analyzing module is connected with the accident both-side responsibility dividing module, and the accident both-side responsibility dividing module is connected with the display terminal.
The accident information recording module is used for recording accident basic information into the system by accident parties when a traffic accident occurs, wherein the accident basic information comprises accident occurrence position information, accident occurrence time information and accident party information, and the accident party information comprises vehicle owner names, contact ways and vehicle license plate numbers of the accident parties.
The accident video extracting and decomposing module is used for extracting accident videos from the monitoring videos shot by the monitoring cameras of the corresponding accident occurrence points according to the accident basic information recorded into the system, wherein the accident videos are extracted in the following process:
step H1: screening accident occurrence positions from accident basic information recorded into a system, selecting a monitoring camera corresponding to the accident occurrence position from a plurality of monitoring cameras according to the accident occurrence positions, and acquiring a monitoring video corresponding to the monitoring camera;
step H2: screening accident occurrence time from accident basic information input into a system, recording the accident occurrence time as a video extraction starting time point, and acquiring a video extraction ending time point through a preset video extraction time period, wherein the video extraction ending time point acquisition method is that the video extraction starting time point is added with the video extraction time period;
step H3: according to the obtained video extraction starting time point and the obtained video extraction ending time point, the monitoring video positions corresponding to the video extraction starting time point and the video extraction ending time point are searched from the obtained monitoring video corresponding to the monitoring camera, the section of monitoring video is extracted and recorded as an accident video, the accident video is decomposed into a plurality of accident pictures according to the number of the extracted accident video frames, meanwhile, the decomposed accident pictures are numbered according to the time sequence and are sequentially marked as 1,2.
The preset video extraction time period mentioned in this embodiment may be adjustable, and when the accident video extracted in the preset video extraction time period is incomplete, the video extraction time period may be adjusted until the extracted accident video is a complete accident video.
The vehicle violation behavior recognition and analysis module is used for screening the marked accident pictures, reserving target accident pictures and analyzing and recognizing vehicle violation behaviors according to the target accident pictures, wherein the vehicle violation behavior recognition and analysis module comprises an accident picture screening unit, an accident picture processing unit and a picture recognition and analysis unit;
the accident picture screening unit is used for analyzing and screening irrelevant accident pictures of the marked accident pictures, removing the accident pictures irrelevant to the accident, reserving the accident pictures relevant to the accident, recording the accident pictures as target accident pictures, respectively marking the target accident pictures as 1,2.
Step K1: checking whether a vehicle exists in each marked accident picture, if the vehicle does not exist in a certain accident picture, indicating that the accident picture is a picture irrelevant to the accident, recording the number of the accident picture, and if the vehicle exists in the certain accident picture, executing a step K2;
step K2: counting the number of accident pictures of existing vehicles, extracting the license plate numbers of the vehicles from the accident pictures of the existing vehicles, simultaneously extracting the license plate numbers of the vehicles at two sides of the accident from the recorded basic information of the accident, matching the extracted license plate numbers from the accident pictures of the existing vehicles with the license plate numbers of the vehicles at two sides of the accident one by one, if any one or both of the extracted license plate numbers from the accident pictures of a certain existing vehicle and the license plate numbers of the vehicles at two sides of the accident are matched, the matching is successful, the vehicles in the accident pictures of the existing vehicles are the accident vehicles, the accident pictures of the existing vehicles are related to the accident, the accident pictures are kept, if any one of the extracted license plate numbers from the accident pictures of a certain existing vehicle and the license plate numbers of the vehicles at two sides of the accident is not matched, the matching is failed, the accident picture of the existing vehicle is shown to be irrelevant to the accident, and the serial number of the accident picture is recorded;
step K3: counting the accident picture numbers recorded in the step K1 and the step K2, and screening the accident pictures which are not related to the accident from the decomposed accident pictures.
In the embodiment, independent accident pictures are screened from all the decomposed accident pictures at the vehicle violation behavior recognition and analysis module, so that accident violation parties and violation behaviors are conveniently analyzed according to the accident pictures related to the accident in the later period, the analysis progress and the analysis result of the accident pictures related to the accident are prevented from being disturbed, and the analysis efficiency and the analysis accuracy are improved.
The accident picture processing unit carries out high-definition filtering processing on the received target accident pictures to obtain high-definition processed target accident pictures, and sends the high-definition processed target accident pictures to the picture identification and analysis unit;
the image identification and analysis unit is used for analyzing the violation behaviors of the vehicle according to the target accident images after high-definition processing, and the specific analysis method comprises the following steps:
step S1: acquiring accident vehicles in sequence from each target accident picture according to the marking sequence of the pictures, acquiring the license plate number of the accident vehicle if only one accident vehicle exists in a certain target accident picture, wherein the target accident picture is the violation analysis reference picture of the accident vehicle, acquiring the license plate numbers of the accident vehicles of both sides in the target accident picture if the accident vehicles of both sides are included in the certain target accident picture, and the target accident picture is the violation analysis reference picture of the accident vehicles of both sides, so that all the target accident pictures are divided into violation analysis reference picture sets of the vehicles of all the accident sides according to different accident vehicles included in the target accident picture, and the violation analysis reference picture sets are marked as A (a1, a2, a, ak, a), B (B1, B2, a, B g, B, g, a, B, bh) where ak is denoted as the kth violation analysis reference picture of the accident a-side vehicle, and bg is denoted as the g-th violation analysis reference picture of the accident B-side vehicle;
step S2: comparing each violation analysis reference picture in the violation analysis reference picture set of each vehicle of the accident with each violation picture corresponding to each violation behavior of the vehicle stored in the violation behavior information base, analyzing whether each violation analysis reference picture of each vehicle of the accident has a picture matched with each violation picture corresponding to each violation behavior of the vehicle, if any one or more target accident pictures in each violation analysis reference picture of the vehicle of a certain accident are successfully matched with each violation picture corresponding to each violation behavior of the vehicle, indicating that the accident party violates the rule, counting the number of violation accident parties at the moment, if only one violation accident party exists, executing step S3, and if the violation accident party is both parties, executing step S4;
step S3: sending the license plate number of the vehicle of the violation accident party to a duty dividing module of the accident party, counting the number of violation analysis reference pictures which are successfully matched with various violation pictures corresponding to various vehicle violations in various violation analysis reference pictures of the vehicle of the violation accident party, obtaining the violation behavior type corresponding to the violation analysis reference pictures which are successfully matched according to various violation pictures corresponding to various violation behaviors in a violation behavior information base, if the violation behavior types corresponding to all the violation analysis reference pictures which are successfully matched are the same type, the violation behavior type of the violation accident party is the type, recording the violation behavior type name, and sending the violation behavior type name to the duty dividing module of the accident party, if the violation behavior types corresponding to all the vehicle violation analysis reference pictures which are successfully matched are different types, the violation of the violation accident party is a violation type violation behavior, recording the names of various violation behavior types, and sending the names to a responsibility division module of both accident parties;
step S4: sending the license plate numbers of the vehicles of the illegal accident parties to a liability division module of the accident parties, acquiring the violation types corresponding to the illegal accident parties according to the method of step S3, if the violation types corresponding to the illegal accident parties are only one, extracting violation coefficients corresponding to the illegal behaviors in a violation information base, comparing the violation types corresponding to the accident parties with the violation coefficients corresponding to the illegal behaviors, screening the violation coefficients corresponding to the violation types of the illegal accident parties, sending the violation coefficients to the liability division module of the accident parties, if the violation types corresponding to the illegal accident parties are not only one, comparing the violation types corresponding to the accident parties with the violation coefficients corresponding to the illegal behaviors, screening the violation coefficients corresponding to the violation types of the illegal accident parties, and sends the data to the accident both-side responsibility division module.
In the embodiment, by adopting the image recognition in the machine vision, each violation analysis reference picture of the vehicles of both sides of the accident is compared with various violation pictures corresponding to various violation behaviors to recognize the violation party of the accident and the corresponding violation behaviors, so that the recognition speed is high, the recognition accuracy is high, and the problems of low efficiency and low accuracy caused by manual visual recognition of a traffic police are solved.
The violation behavior information base is used for storing various violation pictures corresponding to various vehicle violation behaviors and storing violation coefficients corresponding to the various vehicle violation behaviors, wherein the various vehicle violation behaviors comprise line pressing, line reversing, violation traffic signal indication, improper interval keeping, violation parking and the like.
The accident party responsibility division module carries out classification processing on the received illegal accident party license plate number, the illegal behavior type and the illegal coefficient, and the processing process comprises the following steps:
step W1: if only one accident party breaks rules, the license plate number of the violation accident party and the type of the violation behavior are sent to a display terminal;
step W2: if both accident sides violate rules and both violation types corresponding to the accident sides are one, comparing violation coefficients corresponding to the violation types of the accident sides, wherein the larger violation coefficient is marked as a main violation accident side, the smaller violation coefficient is marked as a secondary violation accident side, and sending the license plate numbers of the accident sides, the violation types corresponding to the accident sides, the violation primary and the violation coefficients to a display terminal;
step W3: if both accident parties violate rules and the violation types corresponding to the accident parties are multiple, wherein the violation types corresponding to the accident parties are multiple, and the violation types of one violation accident party are one, and the violation types of the other violation accident party are multiple, the violation coefficients corresponding to the violation types of the accident parties are superposed to obtain a comprehensive violation coefficient corresponding to the accident parties, the larger one of the comprehensive violation coefficients is marked as a main violation accident party, the smaller one of the comprehensive violation coefficients is a secondary violation accident party, and the license plate numbers of the accident parties, the various violation types corresponding to the accident parties, the primary violation factor and the comprehensive violation coefficient are sent to a display terminal.
The display terminal receives and displays the license plate number, the violation type, the violation primary and the violation coefficient of the violation accident party sent by the responsibility division module of the accident party and the accident party, so that the accident party and the violation party can visually know the violation party and the violation of the traffic accident at this time, and a reliable reference is provided for accident compensation processing in the later period.
According to the method and the device, the violation party is identified by combining the accident pictures and the violation behaviors of the violation party are analyzed, so that the responsibility of the accident parties is divided, the traffic accident handling efficiency is improved, the traffic road is recovered to be normal as soon as possible, the road congestion caused by the traffic accident is avoided, the occurrence of secondary traffic accidents caused by the fact that the traffic accident is not handled in time is effectively reduced, and the requirements of modern traffic management are met.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (6)
1. The utility model provides an urban intelligent traffic monitoring system based on machine vision which characterized in that: the accident video extracting and analyzing module is connected with the vehicle violation behavior identifying and analyzing module, the vehicle violation behavior identifying and analyzing module is connected with the accident party responsibility dividing module, and the accident party responsibility dividing module is connected with the display terminal;
the accident information recording module is used for recording accident basic information into the system by both accident parties when a traffic accident occurs;
the accident video extracting and decomposing module is used for extracting an accident video from a monitoring video shot by a monitoring camera of a corresponding accident occurrence point according to accident basic information of an input system, decomposing the accident video into a plurality of accident pictures according to the number of extracted accident video frames according to the number of the video frames, and numbering the decomposed accident pictures according to a time sequence, wherein the number of the accident pictures is sequentially marked as 1,2.
The vehicle violation behavior recognition and analysis module is used for screening and processing each marked accident picture and recognizing the vehicle violation behavior according to the analysis of the target accident picture, wherein the vehicle violation behavior recognition and analysis module comprises an accident picture screening unit, an accident picture processing unit and a picture recognition and analysis unit;
the accident picture screening unit is used for analyzing and screening irrelevant accident pictures of the marked accident pictures, removing the accident pictures irrelevant to the accident, reserving accident pictures relevant to the accident, marking as target accident pictures, respectively marking as 1,2.. j.. m, and simultaneously sending the target accident pictures to the accident picture processing unit;
the accident picture processing unit carries out high-definition filtering processing on the received target accident pictures to obtain high-definition processed target accident pictures, and sends the high-definition processed target accident pictures to the picture identification and analysis unit;
the image identification and analysis unit is used for analyzing the vehicle violation behaviors according to the target accident images after high-definition processing, and the specific analysis method comprises the following steps:
step S1: acquiring accident vehicles in sequence from each target accident picture according to the marking sequence of the pictures, acquiring the license plate number of the accident vehicle if only one accident vehicle exists in a certain target accident picture, wherein the target accident picture is the violation analysis reference picture of the accident vehicle, acquiring the license plate numbers of the accident vehicles of both parties in the target accident picture if the accident vehicles of both parties are included in the certain target accident picture, and the target accident picture is the violation analysis reference picture of the accident vehicles of both parties, so that all the target accident pictures are divided into violation analysis reference picture sets of the vehicles of all the accident parties according to different accident vehicles included, and are marked as A (a1, a2, a, ak, a., al) and B (B1, B2, a., bg., a., B,), wherein the k-th violation analysis reference picture of the vehicle of the accident A party is expressed, bg is expressed as the g-th violation analysis reference picture of the accident B-side vehicle;
step S2: comparing each violation analysis reference picture in the violation analysis reference picture set of each vehicle of the accident with each violation picture corresponding to each vehicle violation, which is stored in a violation information base, analyzing whether each violation analysis reference picture of each vehicle of the accident has a picture matched with each violation picture corresponding to each vehicle violation, if any one or more target accident pictures in each violation analysis reference picture of the vehicle of the accident have a successful matching with each violation picture corresponding to each vehicle violation, indicating that the accident party violates the rule, counting the number of violation accident parties at the moment, if only one violation accident party exists, executing step S3, and if the violation accident party is both parties, executing step S4;
step S3: sending the license plate number of the vehicle of the violation accident party to a duty division module of both accident parties, counting the number of violation analysis reference pictures which are successfully matched with various violation pictures corresponding to various vehicle violations in the violation analysis reference pictures of the vehicle of the violation accident party, obtaining the violation behavior type corresponding to the violation analysis reference pictures which are successfully matched according to the various violation pictures corresponding to various violation behaviors in a violation behavior information base, if the violation behavior types corresponding to all the violation analysis reference pictures which are successfully matched are the same type, the violation behavior type of the violation accident party is the type, recording the violation behavior type name, and sending the violation behavior name to the duty division module of both accident parties, if the violation types corresponding to all the vehicle violation analysis reference pictures which are successfully matched are different types, the violation of the violation accident party is a multi-type violation behavior, recording the names of various violation behavior types, and sending the names to a responsibility division module of both accident parties;
step S4: the license plate numbers of the vehicles of the illegal accident parties are sent to the liability division module of the accident parties, at this time, the illegal action types corresponding to the illegal accident parties are obtained according to the method of the step S3, if the illegal action types corresponding to the illegal accident parties are only one, extracting violation coefficients corresponding to various violations in the violation information base, comparing the violation types corresponding to both accident parties with the violation coefficients corresponding to various violations, screening the violation coefficients corresponding to the violation types of the violation accident parties, and the rule violation data is sent to a responsibility division module of accident parties, if the rule violation types corresponding to the rule violation accident parties are more than one, comparing the violation types corresponding to the accident parties with violation coefficients corresponding to the violation types, screening the violation coefficients corresponding to the violation types of the violation accident parties, and sending the violation coefficients to the accident party responsibility division module;
the accident party responsibility division module carries out classification processing on the received violation accident party information, violation behavior types and violation coefficients, and the processing process comprises the following steps:
step W1: if only one accident party breaks rules, the license plate number of the violation accident party is sent to a display terminal;
step W2: if both accident sides violate rules and both violation behavior types corresponding to both accident sides are one, comparing violation coefficients corresponding to the violation behavior types of both accident sides, marking the side with the larger violation coefficient as a main violation accident side, and marking the side with the smaller violation coefficient as a secondary violation accident side, and sending the vehicle license plate numbers, the violation main and secondary and the violation coefficients of both accident sides to a display terminal;
step W3: if both accident parties violate rules and the violation types corresponding to the accident parties are multiple, overlapping violation coefficients corresponding to the violation types of the accident parties to obtain comprehensive violation coefficients corresponding to the accident parties, marking the side with the larger comprehensive violation coefficient as a main violation accident side, marking the side with the smaller comprehensive violation coefficient as a secondary violation accident side, and sending the license plate numbers, the violation main side and the comprehensive violation coefficients of the accident parties to a display terminal;
and the display terminal receives the license plate number of the violation accident party, the violation behavior type, the violation primary and the violation coefficient sent by the liability division module of the accident parties.
2. The intelligent system for intelligent traffic monitoring in city based on machine vision as claimed in claim 1, wherein: the violation information base is used for storing various violation pictures corresponding to various vehicle violation behaviors and storing violation coefficients corresponding to various vehicle violation behaviors.
3. The intelligent system for intelligent traffic monitoring in city based on machine vision as claimed in claim 1, wherein: the accident basic information comprises accident occurrence position information, accident occurrence time information and accident party information, and the accident party information comprises names, contact ways and license plate numbers of car owners of the accident parties.
4. The intelligent system for intelligent traffic monitoring in city based on machine vision as claimed in claim 1, wherein: the accident video extracting and decomposing module extracts the accident video in the following specific process:
step H1: screening accident occurrence positions from accident basic information recorded into a system, selecting a monitoring camera corresponding to the accident occurrence position from a plurality of monitoring cameras according to the accident occurrence positions, and acquiring a monitoring video corresponding to the monitoring camera;
step H2: screening accident occurrence time from accident basic information input into a system, recording the accident occurrence time as a video extraction starting time point, and acquiring a video extraction finishing time point through a preset video extraction time period;
step H3: and searching the positions of the monitoring videos corresponding to the video extraction starting time point and the video extraction ending time point from the obtained monitoring videos corresponding to the monitoring camera according to the obtained video extraction starting time point and video extraction ending time point, and extracting the section of monitoring video to be recorded as an accident video.
5. The intelligent system for intelligent traffic monitoring in city based on machine vision as claimed in claim 4, wherein: the video extraction ending time point acquisition method is that the video extraction starting time point is added with the video extraction time period.
6. The intelligent system for intelligent traffic monitoring in city based on machine vision as claimed in claim 1, wherein: the screening of the accident picture screening unit for the accident-independent pictures specifically comprises the following steps:
step K1: checking whether a vehicle exists in each marked accident picture, if the vehicle does not exist in a certain accident picture, indicating that the accident picture is a picture irrelevant to the accident, recording the number of the accident picture, and if the vehicle exists in the certain accident picture, executing a step K2;
step K2: counting accident picture numbers of existing vehicles, extracting license plate numbers of the vehicles from each accident picture of the existing vehicles, simultaneously extracting license plate numbers of the vehicles of both accident sides from the recorded accident basic information, matching the vehicle license plate numbers extracted from each accident picture of the existing vehicles with the license plate numbers of the vehicles of both accident sides one by one, if any one or both of the vehicle license plate numbers extracted from the accident picture of a certain existing vehicle and the license plate numbers of the vehicles of both accident sides are matched, the matching is successful, the vehicles in the accident picture of the existing vehicle are the accident vehicles, the accident picture of the existing vehicle is related to the accident, the accident picture is kept, if any one of the vehicle license plate numbers extracted from the accident picture of a certain existing vehicle and the license plate numbers of the vehicles of both accident sides is not matched, the matching is failed, the accident picture indicating the existing vehicle is irrelevant to the accident, and the serial number of the accident picture is recorded;
step K3: counting the accident picture numbers recorded in the step K1 and the step K2, and screening the accident pictures which are not related to the accident from the decomposed accident pictures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011105333.2A CN112233421A (en) | 2020-10-15 | 2020-10-15 | Intelligent city intelligent traffic monitoring system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011105333.2A CN112233421A (en) | 2020-10-15 | 2020-10-15 | Intelligent city intelligent traffic monitoring system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112233421A true CN112233421A (en) | 2021-01-15 |
Family
ID=74118405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011105333.2A Withdrawn CN112233421A (en) | 2020-10-15 | 2020-10-15 | Intelligent city intelligent traffic monitoring system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112233421A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114596711A (en) * | 2022-03-31 | 2022-06-07 | 北京世纪高通科技有限公司 | Accident responsibility determination method, device, equipment and storage medium |
| CN114973664A (en) * | 2022-05-17 | 2022-08-30 | 保银信科信息技术(湖北)有限公司 | Machine vision-based urban traffic online intelligent monitoring and early warning management system |
| CN115394085A (en) * | 2022-10-26 | 2022-11-25 | 广州国交润万交通信息有限公司 | System for automatically simulating and restoring highway events through high-precision map |
| CN117894182A (en) * | 2024-03-15 | 2024-04-16 | 长春师范大学 | Vehicle accident data rapid acquisition method and system based on Internet of vehicles |
Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002232873A (en) * | 2001-01-29 | 2002-08-16 | Kunihiko Sakiyama | Automobile accident verifying system |
| CN103295396A (en) * | 2013-04-19 | 2013-09-11 | 福建工程学院 | Method and system for speedy ex-situ evidence collection of traffic accident |
| CN104537844A (en) * | 2015-01-26 | 2015-04-22 | 成都美联微智科技有限公司 | Vehicle license plate recognition system for traffic violation detection |
| US20160039377A1 (en) * | 2014-08-08 | 2016-02-11 | Yi-Ou Hsu | Event Data Recorder Capable of Detecting and Notifying a Vehicle Accident |
| CN105632182A (en) * | 2016-01-27 | 2016-06-01 | 福建工程学院 | Vehicle violation behavior proof method and system thereof |
| CN106097479A (en) * | 2016-05-30 | 2016-11-09 | 北京奇虎科技有限公司 | The recording method and device of running information |
| KR20160146051A (en) * | 2015-06-11 | 2016-12-21 | 김정애 | An apparatus of monitoring a traffic accident |
| CN106297287A (en) * | 2016-08-19 | 2017-01-04 | 深圳市永兴元科技有限公司 | Vehicle accident evidence acquisition methods and system |
| CN106781436A (en) * | 2016-12-19 | 2017-05-31 | 东软集团股份有限公司 | Traffic accident treatment method and device |
| CN106875696A (en) * | 2017-04-13 | 2017-06-20 | 深圳市赛亿科技开发有限公司 | The system and method and drive recorder of automatic identification traffic violations illegal activities |
| CN107909113A (en) * | 2017-11-29 | 2018-04-13 | 北京小米移动软件有限公司 | Traffic-accident image processing method, device and storage medium |
| CN107945512A (en) * | 2017-11-27 | 2018-04-20 | 海尔优家智能科技（北京）有限公司 | A kind of traffic accident treatment method and system |
| CN108268874A (en) * | 2016-12-30 | 2018-07-10 | 环达电脑(上海)有限公司 | Driving system for prompting and its method |
| CN108389392A (en) * | 2018-04-04 | 2018-08-10 | 广东容祺智能科技有限公司 | A kind of traffic accident responsibility identification system based on machine learning |
| CN108986474A (en) * | 2018-08-01 | 2018-12-11 | 平安科技（深圳）有限公司 | Fix duty method, apparatus, computer equipment and the computer storage medium of traffic accident |
| CN109242739A (en) * | 2018-06-28 | 2019-01-18 | 平安科技（深圳）有限公司 | Traffic accident treatment method, system and server |
| CN109523389A (en) * | 2018-09-19 | 2019-03-26 | 平安科技（深圳）有限公司 | Vehicle damage processing method, device, equipment and medium based on image recognition |
| CN109543588A (en) * | 2018-11-16 | 2019-03-29 | 广州慧睿思通信息科技有限公司 | Method, apparatus, system, service platform and the medium that traffic accident responsibility determines |
| CN109785210A (en) * | 2018-12-13 | 2019-05-21 | 丁宏伟 | Remote visualization quickly handles road traffic accident system |
| CN109979196A (en) * | 2019-03-23 | 2019-07-05 | 闽南理工学院 | A kind of intelligent transportation big data processing system |
| CN110062208A (en) * | 2019-04-23 | 2019-07-26 | 上海赫煊自动化系统工程有限公司 | A kind of security protection intelligence real-time analyzer and method |
| CN110070642A (en) * | 2019-03-22 | 2019-07-30 | 天津大学 | A kind of traffic accident responsibility appraisal procedure and device based on deep learning |
| CN110392235A (en) * | 2019-07-17 | 2019-10-29 | 河南大学 | A kind of video monitoring processing system based on artificial intelligence |
| CN110427432A (en) * | 2019-08-08 | 2019-11-08 | 英华达（上海）科技有限公司 | Violation event processing method, system, equipment and storage medium based on block chain |
| KR20190126024A (en) * | 2019-08-23 | 2019-11-08 | 엘지전자 주식회사 | Traffic Accident Handling Device and Traffic Accident Handling Method |
| CN110738842A (en) * | 2018-07-18 | 2020-01-31 | 阿里巴巴集团控股有限公司 | Accident responsibility division and behavior analysis method, device, equipment and storage medium |
| CN110991558A (en) * | 2019-12-18 | 2020-04-10 | 中国平安财产保险股份有限公司 | Accident processing method and device based on image recognition and computer equipment |
| CN111368617A (en) * | 2019-07-31 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Vehicle access data processing method and device |
| CN111582268A (en) * | 2020-04-13 | 2020-08-25 | 浙江大华技术股份有限公司 | License plate image processing method and device and computer storage medium |
-
2020
- 2020-10-15 CN CN202011105333.2A patent/CN112233421A/en not_active Withdrawn
Patent Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002232873A (en) * | 2001-01-29 | 2002-08-16 | Kunihiko Sakiyama | Automobile accident verifying system |
| CN103295396A (en) * | 2013-04-19 | 2013-09-11 | 福建工程学院 | Method and system for speedy ex-situ evidence collection of traffic accident |
| US20160039377A1 (en) * | 2014-08-08 | 2016-02-11 | Yi-Ou Hsu | Event Data Recorder Capable of Detecting and Notifying a Vehicle Accident |
| CN104537844A (en) * | 2015-01-26 | 2015-04-22 | 成都美联微智科技有限公司 | Vehicle license plate recognition system for traffic violation detection |
| KR20160146051A (en) * | 2015-06-11 | 2016-12-21 | 김정애 | An apparatus of monitoring a traffic accident |
| CN105632182A (en) * | 2016-01-27 | 2016-06-01 | 福建工程学院 | Vehicle violation behavior proof method and system thereof |
| CN106097479A (en) * | 2016-05-30 | 2016-11-09 | 北京奇虎科技有限公司 | The recording method and device of running information |
| CN106297287A (en) * | 2016-08-19 | 2017-01-04 | 深圳市永兴元科技有限公司 | Vehicle accident evidence acquisition methods and system |
| CN106781436A (en) * | 2016-12-19 | 2017-05-31 | 东软集团股份有限公司 | Traffic accident treatment method and device |
| CN108268874A (en) * | 2016-12-30 | 2018-07-10 | 环达电脑(上海)有限公司 | Driving system for prompting and its method |
| CN106875696A (en) * | 2017-04-13 | 2017-06-20 | 深圳市赛亿科技开发有限公司 | The system and method and drive recorder of automatic identification traffic violations illegal activities |
| CN107945512A (en) * | 2017-11-27 | 2018-04-20 | 海尔优家智能科技（北京）有限公司 | A kind of traffic accident treatment method and system |
| CN107909113A (en) * | 2017-11-29 | 2018-04-13 | 北京小米移动软件有限公司 | Traffic-accident image processing method, device and storage medium |
| CN108389392A (en) * | 2018-04-04 | 2018-08-10 | 广东容祺智能科技有限公司 | A kind of traffic accident responsibility identification system based on machine learning |
| CN109242739A (en) * | 2018-06-28 | 2019-01-18 | 平安科技（深圳）有限公司 | Traffic accident treatment method, system and server |
| CN110738842A (en) * | 2018-07-18 | 2020-01-31 | 阿里巴巴集团控股有限公司 | Accident responsibility division and behavior analysis method, device, equipment and storage medium |
| CN108986474A (en) * | 2018-08-01 | 2018-12-11 | 平安科技（深圳）有限公司 | Fix duty method, apparatus, computer equipment and the computer storage medium of traffic accident |
| CN109523389A (en) * | 2018-09-19 | 2019-03-26 | 平安科技（深圳）有限公司 | Vehicle damage processing method, device, equipment and medium based on image recognition |
| CN109543588A (en) * | 2018-11-16 | 2019-03-29 | 广州慧睿思通信息科技有限公司 | Method, apparatus, system, service platform and the medium that traffic accident responsibility determines |
| CN109785210A (en) * | 2018-12-13 | 2019-05-21 | 丁宏伟 | Remote visualization quickly handles road traffic accident system |
| CN110070642A (en) * | 2019-03-22 | 2019-07-30 | 天津大学 | A kind of traffic accident responsibility appraisal procedure and device based on deep learning |
| CN109979196A (en) * | 2019-03-23 | 2019-07-05 | 闽南理工学院 | A kind of intelligent transportation big data processing system |
| CN110062208A (en) * | 2019-04-23 | 2019-07-26 | 上海赫煊自动化系统工程有限公司 | A kind of security protection intelligence real-time analyzer and method |
| CN110392235A (en) * | 2019-07-17 | 2019-10-29 | 河南大学 | A kind of video monitoring processing system based on artificial intelligence |
| CN111368617A (en) * | 2019-07-31 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Vehicle access data processing method and device |
| CN110427432A (en) * | 2019-08-08 | 2019-11-08 | 英华达（上海）科技有限公司 | Violation event processing method, system, equipment and storage medium based on block chain |
| KR20190126024A (en) * | 2019-08-23 | 2019-11-08 | 엘지전자 주식회사 | Traffic Accident Handling Device and Traffic Accident Handling Method |
| CN110991558A (en) * | 2019-12-18 | 2020-04-10 | 中国平安财产保险股份有限公司 | Accident processing method and device based on image recognition and computer equipment |
| CN111582268A (en) * | 2020-04-13 | 2020-08-25 | 浙江大华技术股份有限公司 | License plate image processing method and device and computer storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 薛大维等: ""基于违法行为过错系数的交通事故责任认定体系"", 《黑龙江工程学院学报（自然科学版）》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114596711A (en) * | 2022-03-31 | 2022-06-07 | 北京世纪高通科技有限公司 | Accident responsibility determination method, device, equipment and storage medium |
| CN114973664A (en) * | 2022-05-17 | 2022-08-30 | 保银信科信息技术(湖北)有限公司 | Machine vision-based urban traffic online intelligent monitoring and early warning management system |
| CN115394085A (en) * | 2022-10-26 | 2022-11-25 | 广州国交润万交通信息有限公司 | System for automatically simulating and restoring highway events through high-precision map |
| CN117894182A (en) * | 2024-03-15 | 2024-04-16 | 长春师范大学 | Vehicle accident data rapid acquisition method and system based on Internet of vehicles |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112233421A (en) | Intelligent city intelligent traffic monitoring system based on machine vision | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN109740420B (en) | Vehicle law violation identification method and related product | |
| CN104766479A (en) | Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching | |
| CN108389396B (en) | Vehicle type matching method and device based on video and charging system | |
| CN112509325B (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| CN105279971B (en) | A kind of information of vehicles matching process, system and supervising device | |
| CN102682608B (en) | Method for image forensics of motor vehicle plate covering and staining behaviors | |
| CN107305736B (en) | License plate recognition intelligent error checking method and system based on license plate rule and space-time reachability | |
| CN107464446B (en) | Inspection method and device for vertical parking space parking information | |
| CN111612104B (en) | Vehicle loss assessment image acquisition method, device, medium and electronic equipment | |
| CN106097722A (en) | Video is utilized to carry out the system and method for trackside parking stall automatization supervision | |
| CN111369801B (en) | Vehicle identification method, device, equipment and storage medium | |
| CN106571040B (en) | Suspicious vehicle confirmation method and equipment | |
| CN114049612A (en) | Highway vehicle charge auditing system based on graph searching technology and dual-obtaining and checking method for driving path | |
| CN112668642A (en) | System and method for combining electronic identification and video of motor vehicle | |
| CN110969860B (en) | Background auditing system and method for traffic law violation behaviors | |
| CN110164136B (en) | Fake-licensed vehicle identification method | |
| CN111768630A (en) | Violation waste image detection method and device and electronic equipment | |
| CN111179452A (en) | ETC channel-based bus fee deduction system and method | |
| CN110930724A (en) | Traffic off-site illegal record screening and auditing method and system based on deep learning | |
| CN113723258B (en) | Dangerous goods vehicle image recognition method and related equipment thereof | |
| CN114596439A (en) | Image-based intelligent damage assessment and check method and device for car insurance and electronic equipment | |
| CN113283303A (en) | License plate recognition method and device | |
| CN113743316A (en) | Vehicle jamming behavior identification method, system and device based on target detection |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210115 |
|
| WW01 | Invention patent application withdrawn after publication |