CN116994428A - Intersection entrance road traffic accident identification method based on parameter change rate - Google Patents
Intersection entrance road traffic accident identification method based on parameter change rate Download PDFInfo
- Publication number
- CN116994428A CN116994428A CN202310818514.7A CN202310818514A CN116994428A CN 116994428 A CN116994428 A CN 116994428A CN 202310818514 A CN202310818514 A CN 202310818514A CN 116994428 A CN116994428 A CN 116994428A
- Authority
- CN
- China
- Prior art keywords
- traffic
- change rate
- traffic accident
- lane
- traffic flow
- 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.)
- Granted
Links
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 130
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000000295 complement effect Effects 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 230000000903 blocking effect Effects 0.000 abstract description 2
- 238000011217 control strategy Methods 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- 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
- G08G1/0133—Traffic data processing for classifying traffic situation
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
An intersection entrance road traffic accident identification method based on parameter change rate belongs to the technical field of traffic safety. Preprocessing data of electronic police and bayonet equipment; acquiring steering traffic flow data of an entrance way of an intersection; acquiring the time interval information of the vehicle passing through the parking line by utilizing the time interval of each vehicle; calculating a delay by using a delay calculation formula; analyzing the traffic flow change rate of the lane, the average delay change rate and the traffic flow standard deviation of the entrance lane after the traffic accident so as to determine the traffic accident alarming threshold; and constructing an intersection entrance road traffic accident identification method model based on the parameter change rate. The application can effectively improve the traffic accident identification efficiency of the entrance road of the intersection, obviously reduce the safety risk after the traffic accident occurs in the entrance road of the intersection, reduce the time for the traffic police to locate the traffic accident occurrence point and timely take the traffic accident emergency management and control strategy, thereby reducing the blocking time of the intersection.
Description
Technical Field
An intersection entrance road traffic accident identification method based on parameter change rate belongs to the technical field of traffic safety.
Background
Various traffic flows in the urban intersections cross and run, the conflict areas are large, and traffic accidents are easy to occur. With further increase of urban traffic pressure, traffic accidents at intersections are increasing. The traffic accident at the urban intersection brings great pressure to society, which seriously affects the operation efficiency of the intersection, causes road network blockage and is easy to cause traffic accident.
Disclosure of Invention
The application aims to solve the technical problems that: the method for identifying the traffic accidents at the intersection entrance road based on the parameter change rate overcomes the defects of the prior art, and can discover the traffic accidents at the intersection more timely and effectively improve the efficiency of identifying the traffic accidents at the intersection.
The technical scheme adopted for solving the technical problems is as follows: the intersection entrance road traffic accident identification method based on the parameter change rate is characterized by comprising the following steps of: the method comprises the following steps:
s1, preprocessing data of electronic police and bayonet equipment, and carrying out complement processing on abnormal information;
s2, acquiring steering traffic flow data of each intersection entrance road;
s3, acquiring the headway information by using the time interval of each vehicle passing through a parking line according to electronic police and bayonet video data;
s4, acquiring time from the vehicle passing through the bayonet shooting position to a stop line so as to calculate delay;
s5, counting traffic accidents of entrance roads of a plurality of intersections, and analyzing the traffic flow change rate, the average delay change rate and the traffic flow standard deviation of the entrance roads after the traffic accidents so as to determine traffic accident alarming thresholds;
s6, counting traffic accidents of entrance roads of a plurality of intersections, and analyzing the traffic flow change rate, the average delay change rate and the traffic flow standard deviation of the entrance roads after the traffic accidents so as to determine traffic accident alarming thresholds;
s7, constructing an intersection entrance road traffic accident identification method model based on the parameter change rate, and determining the duration of the traffic accident.
Preferably, the method for carrying out the complement processing on the abnormal information comprises the following steps:
s1.1, respectively extracting electronic police passing data and bayonet passing data;
s1.2, comparing and analyzing the electronic police passing data and the bayonet passing data, and searching and removing passing information corresponding to repeated license plates in the electronic police passing data and the bayonet passing data;
s1.3, sequencing the rest electronic police and the bayonet data according to equipment numbers;
s1.4, sequencing the electronic police driving data and the bayonet data of each number according to time respectively;
s1.5, comparing the electronic police passing data with the same number with the bayonet passing data according to time;
s1.6, complementing the license plate-free driving information.
Preferably, the method for calculating delay in step S4 is as follows: sequencing the electronic police and the bayonet data of the entrance way of the intersection according to time, taking 5min as a time window, sliding forwards, taking the license plate number as a characteristic variable, judging whether repeated vehicle passing records exist in the time window, extracting repeated vehicle passing data if the repeated vehicle passing records exist, and otherwise, continuing to traverse the vehicle passing information sequence until the data are processed.
Preferably, the delay calculating method is as follows:
wherein D represents a delay from the entrance road vehicle passing through the photographing position of the entrance to the stop line; x is x n Representing the number of the counted vehicles; t is t dx Indicating the moment when the xth vehicle is detected by the bayonet device; t is t cx Indicating the moment when the xth vehicle passes the stop line; t is t f The average time for the vehicle to pass the stop line from the bayonet shooting position in the unsaturated state is shown.
Preferably, the average delay change rate delta D, j of the j-period is the change rate delta Qlane of the traffic flow of each lane ij And j period lane traffic flow standard deviation sigma j The method comprises the following steps of:
wherein n is the number of lanes of the entrance road; i represents an i-th lane; j is the j-th period;D j average delay of the j period of the traffic accident; d'. j Average delay of the period j without traffic accidents; qlane ij The traffic flow of the traffic accident day j period of the ith lane is the traffic flow of the traffic accident day j period of the ith lane; qlane' ij The traffic flow of the ith lane in the day j period without traffic accidents is the traffic flow of the ith lane; qlane j The traffic flow average value of each lane in the time period j of the traffic accident day is obtained.
Preferably, the duration of the traffic accident is a time difference between the last vehicle before the traffic accident and the first vehicle after the traffic accident passing through the stop line.
Preferably, the traffic accident duration Ht i The calculation mode of (a) is as follows:
Ht i ＝t fi -t li ；
wherein t is li The time when the last vehicle passes through the stop line before the traffic accident occurs in the lane i; t is t fi The time when the first vehicle passes through the stop line after the traffic accident of the lane i is finished.
Preferably, the intersection entrance road traffic accident identification method model based on the parameter change rate comprises the following steps:
s7.1, sliding at intervals of 5 minutes to obtain average delay, traffic flow of a lane and a headway;
s7.2, inputting historical data of the synchronous average delay and the traffic flow of the lane;
s7.3, calculating an average delay change rate, a lane traffic flow change rate and a traffic flow standard deviation of each lane respectively;
s7.4, judging whether the average delay change rate and the traffic flow standard deviation of each lane reach respective thresholds, if so, judging that traffic accidents occur in the entrance lane, if not, entering the next 5min, and returning to the step S7.1;
s7.5, judging whether the traffic flow change rate of each lane meets the condition that the traffic flow change rate of the i traffic flow of the part of lanes is reduced and reaches a threshold value, if so, judging that the traffic accident occurs in the i lane, and if not, entering the next 5min, and returning to the step S7.1;
s7.6, judging whether the headway of the lane i is 0, if so, determining the duration of the traffic accident; if the threshold is not reached, the next 5min is entered, and the process returns to the step S7.1.
Compared with the prior art, the application has the following beneficial effects:
the intersection entrance road traffic accident identification method based on the parameter change rate designs a set of parameter extraction flow based on electronic police and bayonet equipment aiming at an intersection entrance road, and calculates the change rate of traffic flow of a blocked road, the average delay change rate, the standard deviation of traffic flow of an entrance lane and the headway by extracting traffic flow data, headway time and average delay data of the intersection. And determining a traffic accident alarming threshold value by analyzing historical traffic accident data, so as to realize the identification of traffic accidents of the entrance road.
The application can effectively improve the traffic accident identification efficiency of the entrance road of the intersection, obviously reduce the safety risk after the traffic accident occurs in the entrance road of the intersection, simultaneously improve the traffic accident identification speed of the intersection, reduce the time for a traffic police to locate the traffic accident occurrence point, timely take the traffic accident emergency management and control strategy, further reduce the blocking time of the intersection and quickly recover the normal operation of the intersection.
Drawings
FIG. 1 is a flow chart of a method for identifying traffic accidents at an intersection entrance based on a parameter change rate;
FIG. 2 is a flow chart of the completion processing of exception information;
FIG. 3 is a schematic diagram of the electronic police and bayonet device acquisition scope;
fig. 4 is a flow chart of a traffic accident identification method model based on the parameter change rate.
Detailed Description
The present application will be further described with reference to specific embodiments, however, it will be appreciated by those skilled in the art that the detailed description herein with reference to the accompanying drawings is for better illustration, and that the application is not necessarily limited to such embodiments, but rather is intended to cover various equivalent alternatives or modifications, as may be readily apparent to those skilled in the art.
FIGS. 1-4 illustrate preferred embodiments of the present application, and the present application will be further described with reference to FIGS. 1-4.
The application aims at improving the traffic accident identification efficiency of the intersection, fully considers the change rule of traffic flow characteristic parameters of each entrance road of the intersection, such as traffic flow, headway, delay and the like, and provides a traffic accident identification method of the entrance road of the intersection based on the parameter change rate according to the change rule of the traffic flow characteristic parameters, realizes traffic accident identification by using the change rate of each parameter after the traffic accident occurs in the entrance road of the intersection, judges the position of the traffic accident of the intersection, and rapidly and effectively identifies the traffic accident of the entrance road of the intersection.
Referring to fig. 1, first, the information of passing vehicles at an intersection is acquired based on electronic police and a bayonet device, and abnormal data is preprocessed. And then extracting traffic flow characteristic parameter information such as traffic flow, headway, delay and the like. And secondly, calculating the traffic flow change rate, the average delay change rate of the blocked traffic, and the traffic flow standard deviation of the imported lane. Finally, a model of a traffic accident identification method based on the parameter change rate is set to identify the traffic accident at the intersection.
Specifically, the intersection entrance road traffic accident identification method based on the parameter change rate comprises the following steps:
s1, preprocessing data of electronic police and bayonet equipment, and carrying out complement processing on abnormal information;
in the process of detecting road traffic information by electronic police and bayonet equipment, abnormal information such as incomplete license plate identification such as no license plate and license plate numbers such as license plate number identification caused by pollution shielding, insufficient illumination, bad weather and the like of the license plate numbers of vehicles appears in detection results. The application designs a license plate-free vehicle passing information complement method according to the data acquisition principle of electronic police and bayonet equipment.
Referring to fig. 2, the method for supplementing the license plate-free driving information, namely, the method for supplementing the abnormal information, comprises the following steps:
s1.1, respectively extracting electronic police passing data and bayonet passing data;
s1.2, comparing and analyzing the electronic police passing data and the bayonet passing data, and searching and removing passing information corresponding to repeated license plates in the electronic police passing data and the bayonet passing data;
s1.3, sequencing the rest electronic police and the data of the passing of the bus at the bus stop according to equipment numbers;
s1.4, sequencing the electronic police passing data and the bayonet passing data of each number according to time respectively;
s1.5, comparing the electronic police passing data with the same number with the bayonet passing data according to time;
s1.6, complementing the license plate-free driving information.
S2, acquiring steering traffic flow data of each intersection entrance road.
The electronic police and the bayonet equipment can identify license plates and record vehicle information, so that the application adopts electronic police data to extract traffic flow parameters. In the practical application process, the electronic police equipment can identify the lane to which the vehicle belongs according to the lane range demarcation standard. The traffic flow information is counted by dividing directions and dividing lanes, and a foundation is laid for identifying traffic accidents.
In traffic flow statistics, it is necessary to divide the appropriate time intervals, but the dividing time intervals have no fixed standard. If the time interval is too short, the traffic flow characteristics in the whole period cannot be contained; if the time interval is too long, the traffic accident occurrence moment is difficult to identify in time. Considering the two factors comprehensively, the application adopts 5min as a period of time when analyzing the traffic flow of the intersection.
S3, acquiring the headway information by using the time interval of each vehicle passing through the parking line according to the electronic police and the video data of the bayonet.
In actual road traffic, the time it takes for the first vehicle to start and accelerate away from the entrance road is relatively large due to the influence of the driver's reaction time, resulting in a relatively large first headway and a second headway. And the like, the subsequent headway is sequentially reduced until the vehicles are completely accelerated when passing through the stop line at a certain moment, and the subsequent motorcade keeps stable headway to run at a constant speed. The headway observed at this time is called the saturated headway, and therefore the present application selects the average headway of the computing fleet starting from the third headway.
The collection time in the electronic police data is the time of the vehicles passing through the stop line, so that the headway of the front vehicle and the rear vehicle can be calculated by the time difference of the adjacent vehicles passing through the stop line, and the specific extraction steps are as follows:
s3.1, screening electronic police data, dividing the electronic police data based on the driving direction and the lanes, and sorting according to the time when vehicles pass through stop lines;
s3.2, extracting the headway. According to the time difference of the front and rear vehicles passing through the stop line of the same lane, the headway is calculated by the following calculation method:
HtS x ＝t x -t x-1 ；
wherein HtSx is the headway of the xth vehicle; t is t x Time for the xth vehicle to pass the stop line; t is t x-1 Time to stop line for the x-1 vehicle;
s3.3 is divided according to period time. The traffic is periodically stopped under the influence of the signal control, so that the time interval between the last vehicle passing through a certain lane in the current phase and the first vehicle passing through the next phase is the period duration during the green light. In summary, the application divides the headway extracted in the step S3.2 according to the signal period to obtain a single period headway set [ HtS ] 1 ，HtS 2 ，...，HtS x ]。
S4, acquiring time from the vehicle passing through the bayonet shooting position to the stop line to calculate delay.
Referring to fig. 3, at the intersection, an electronic police and a bayonet high-definition camera are arranged at the same time, and an entrance stop line and an approach are respectively aligned, so that technical support is provided for vehicle delay analysis.
In the calculation process, different driving information of the same vehicle needs to be extracted, and a specific processing flow is shown in fig. 1. Firstly, sequencing electronic police and bayonet data of an entrance way of an intersection according to time, taking 5min as a time window, sliding forwards, taking a license plate number as a characteristic variable, judging whether repeated vehicle passing records exist in the time window, extracting repeated vehicle passing data if the repeated vehicle passing records exist, and otherwise, continuing to traverse a vehicle passing information sequence until the data are processed.
The specific formula of the delay is as follows:
wherein D represents a delay from the entrance road vehicle passing through the photographing position of the entrance to the stop line; x is x n Representing the number of the counted vehicles; t is t dx Indicating the moment when the xth vehicle is detected by the bayonet device; t is t cx Indicating the moment when the xth vehicle passes the stop line; t is t f The average time for the vehicle to pass the stop line from the bayonet shooting position in the unsaturated state is shown.
S5, counting traffic accidents of entrance roads of a plurality of intersections, and analyzing the traffic flow change rate, the average delay change rate and the traffic flow standard deviation of the entrance roads after the traffic accidents so as to determine the traffic accident alarming threshold.
The lane traffic flow rate refers to: and determining the traffic flow of each lane in a certain period, and counting the traffic flow of the lane in the same period without traffic accidents. The lane traffic flow rate is the relative rate of change of the two.
The standard deviation of traffic flow of the entrance lane means: traffic flow data of each lane was recorded every 5min, and the average value thereof was taken. And calculating the standard deviation of the traffic flow of the entrance road of the intersection as the standard deviation of the traffic flow of the entrance lane.
Average delay change rate means: and determining average delay data of the entrance way of the intersection every 5min, and counting the average delay data of the same period without traffic accidents, wherein the average delay change rate is the relative change rate of the two.
S6, counting traffic accidents of entrance roads of a plurality of intersections, and analyzing the traffic flow change rate, the average delay change rate and the traffic flow standard deviation of the entrance roads after the traffic accidents so as to determine the traffic accident alarming threshold.
Assuming that the intersection entrance way is total to n lanes, taking every 5min as a period, statistically analyzing historical data to determine a traffic accident alarming threshold. The calculation formulas of the average delay change rate, the lane traffic flow change rate and the standard deviation of the traffic flow of the entrance lane are as follows:
wherein n is the number of lanes of the entrance road; i represents an i-th lane; j is the j-th period; d (D) j Average delay of the j period of the traffic accident; d'. j Average delay of the period j without traffic accidents; qlane ij The traffic flow of the traffic accident day j period of the ith lane is the traffic flow of the traffic accident day j period of the ith lane; qlane' ij The traffic flow of the ith lane in the day j period without traffic accidents is the traffic flow of the ith lane; qlane j The traffic flow average value of each lane in the time period j of the traffic accident day; ΔD is the average delay change rate, ΔQlane ij The traffic flow rate change rate of each lane; sigma (sigma) j And j time interval traffic flow standard deviation.
In this embodiment, 200 intersection entrance road traffic accidents are analyzed. Counting the change rate of each parameter relative to the history synchronization in the duration of the traffic accident by taking 5min as a counting interval, and determining a traffic accident alarming threshold value, wherein the traffic accident alarming threshold value of each parameter is as follows: average delay change rate Δd=1.99, traffic flow change rate Δqlane ij -0.75, standard deviation σ of traffic flow in entrance lane j ＝19.4pcu/5min。
S7, constructing an intersection entrance road traffic accident identification method model based on the parameter change rate, and determining the duration of the traffic accident.
After a traffic accident occurs in the entrance road of the intersection, in order to determine the duration of the traffic accident, the time difference between the last vehicle before the traffic accident and the first vehicle after the traffic accident passing through the stop line is defined as the duration of the traffic accident in the entrance road of the intersection. As shown below, the traffic accident duration Ht is calculated i ：
Ht i ＝t fi -t li ；
Wherein t is li The time when the last vehicle passes through the stop line before the traffic accident occurs in the lane i; t is t fi The time when the first vehicle passes through the stop line after the traffic accident of the lane i is finished.
Referring to fig. 4, the intersection entrance road traffic accident identification method model based on the parameter change rate comprises the following steps:
s7.1 sliding at intervals of 5min to obtain average delay D j Traffic flow rate of lane Qlane ij And the headway HtSx i ；
S7.2 input-contemporaneous average delay D' j And lane traffic flow Qlane' ij History data of (2);
s7.3 respectively calculating the average delay change rate delta D and the traffic flow change rate delta Qlane ij And standard deviation sigma of traffic flow of each lane j ；
S7.4, judging whether the average delay change rate and the traffic flow standard deviation of each lane reach respective thresholds, if so, judging that traffic accidents occur in the entrance lane, if not, entering the next 5min, and returning to the step S7.1;
s7.5, judging whether the traffic flow change rate of each lane meets the condition that the traffic flow change rate of the i traffic flow of the part of lanes is increased and reaches a threshold value, if so, judging that the traffic accident occurs in the i lane, and if not, entering the next 5min, and returning to the step S7.1;
s7.6 judging the headway HtSx of the lane i i If HtSx i =0, then the traffic accident persists at i Second, wherein the second is; if the threshold is not reached, the next 5min is entered, and the process returns to the step S7.1.
HtSx i Is the headway of the i lanes.
The above description is only a preferred embodiment of the present application, and is not intended to limit the application in any way, and any person skilled in the art may make modifications or alterations to the disclosed technical content to the equivalent embodiments. However, any simple modification, equivalent variation and variation of the above embodiments according to the technical substance of the present application still fall within the protection scope of the technical solution of the present application.
Claims (8)
1. A method for identifying traffic accidents at an intersection entrance based on a parameter change rate is characterized by comprising the following steps: the method comprises the following steps:
s1, preprocessing data of electronic police and bayonet equipment, and carrying out complement processing on abnormal information;
s2, acquiring steering traffic flow data of each intersection entrance road;
s3, acquiring the headway information by using the time interval of each vehicle passing through a parking line according to electronic police and bayonet video data;
s4, acquiring time from the vehicle passing through the bayonet shooting position to a stop line so as to calculate delay;
s5, counting traffic accidents of entrance roads of a plurality of intersections, and analyzing the traffic flow change rate, the average delay change rate and the traffic flow standard deviation of the entrance roads after the traffic accidents so as to determine traffic accident alarming thresholds;
s6, counting traffic accidents of entrance roads of a plurality of intersections, and analyzing the traffic flow change rate, the average delay change rate and the traffic flow standard deviation of the entrance roads after the traffic accidents so as to determine traffic accident alarming thresholds;
s7, constructing an intersection entrance road traffic accident identification method model based on the parameter change rate, and determining the duration of the traffic accident.
2. The intersection entrance road traffic accident identification method based on the parameter change rate according to claim 1, wherein the method comprises the following steps: the method for carrying out the complement processing on the abnormal information comprises the following steps:
s1.1, respectively extracting electronic police passing data and bayonet passing data;
s1.2, comparing and analyzing the electronic police passing data and the bayonet passing data, and searching and removing passing information corresponding to repeated license plates in the electronic police passing data and the bayonet passing data;
s1.3, sequencing the rest electronic police and the bayonet data according to equipment numbers;
s1.4, sequencing the electronic police driving data and the bayonet data of each number according to time respectively;
s1.5, comparing the electronic police passing data with the same number with the bayonet passing data according to time;
s1.6, complementing the license plate-free driving information.
3. The intersection entrance road traffic accident identification method based on the parameter change rate according to claim 1, wherein the method comprises the following steps: the method for calculating delay in the step S4 is as follows: sequencing the electronic police and the bayonet data of the entrance way of the intersection according to time, taking 5min as a time window, sliding forwards, taking the license plate number as a characteristic variable, judging whether repeated vehicle passing records exist in the time window, extracting repeated vehicle passing data if the repeated vehicle passing records exist, and otherwise, continuing to traverse the vehicle passing information sequence until the data are processed.
4. The intersection entrance road traffic accident identification method based on the parameter change rate according to claim 1 or 3, wherein: the delay calculating method comprises the following steps:
wherein D represents a delay from the entrance road vehicle passing through the photographing position of the entrance to the stop line; x is x n Statistical representation vehicleA number of vehicles; t is t dx Indicating the moment when the xth vehicle is detected by the bayonet device; t is t cx Indicating the moment when the xth vehicle passes the stop line; t is t f The average time for the vehicle to pass the stop line from the bayonet shooting position in the unsaturated state is shown.
5. The intersection entrance road traffic accident identification method based on the parameter change rate according to claim 1, wherein the method comprises the following steps: average delay change rate delta D, j of j period and traffic flow change rate delta Qlane of each lane ij And j period lane traffic flow standard deviation sigma j The method comprises the following steps of:
wherein n is the number of lanes of the entrance road; i represents an i-th lane; j is the j-th period; d (D) j Average delay of the j period of the traffic accident; d'. j Average delay of the period j without traffic accidents; qlane ij The traffic flow of the traffic accident day j period of the ith lane is the traffic flow of the traffic accident day j period of the ith lane; qlane' ij The traffic flow of the ith lane in the day j period without traffic accidents is the traffic flow of the ith lane; qlane j The traffic flow average value of each lane in the time period j of the traffic accident day is obtained.
6. The intersection entrance road traffic accident identification method based on the parameter change rate according to claim 1, wherein the method comprises the following steps: the duration of the traffic accident is the time difference between the last vehicle before the traffic accident and the first vehicle after the traffic accident passing through the stop line.
7. The intersection entrance road traffic accident identification method based on the parameter change rate according to claim 1, wherein the method comprises the following steps: the duration Ht of the traffic accident i The calculation mode of (a) is as follows:
Ht i ＝t fi -t li ；
wherein t is li The time when the last vehicle passes through the stop line before the traffic accident occurs in the lane i; t is t fi The time when the first vehicle passes through the stop line after the traffic accident of the lane i is finished.
8. The intersection entrance road traffic accident identification method based on the parameter change rate according to claim 1, wherein the method comprises the following steps: the intersection entrance road traffic accident identification method model based on the parameter change rate comprises the following steps:
s7.1, sliding at intervals of 5 minutes to obtain average delay, traffic flow of a lane and a headway;
s7.2, inputting historical data of the synchronous average delay and the traffic flow of the lane;
s7.3, calculating an average delay change rate, a lane traffic flow change rate and a traffic flow standard deviation of each lane respectively;
s7.4, judging whether the average delay change rate and the traffic flow standard deviation of each lane reach respective thresholds, if so, judging that traffic accidents occur in the entrance lane, if not, entering the next 5min, and returning to the step S7.1;
s7.5, judging whether the traffic flow change rate of each lane meets the condition that the traffic flow change rate of the i traffic flow of the part of lanes is reduced and reaches a threshold value, if so, judging that the traffic accident occurs in the i lane, and if not, entering the next 5min, and returning to the step S7.1;
s7.6 judging whether the headway of the lane i is 0, if so, determining that the duration of the traffic accident is Ht i Second, wherein the second is; if the threshold is not reached, the next 5min is entered, and the process returns to the step S7.1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818514.7A CN116994428B (en) | 2023-07-05 | Intersection entrance road traffic accident identification method based on parameter change rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818514.7A CN116994428B (en) | 2023-07-05 | Intersection entrance road traffic accident identification method based on parameter change rate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116994428A true CN116994428A (en) | 2023-11-03 |
| CN116994428B CN116994428B (en) | 2024-04-26 |
Family
ID=
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117275260A (en) * | 2023-11-21 | 2023-12-22 | 山东理工大学 | Emergency control method for urban road intersection entrance road traffic accident |
| CN117292562A (en) * | 2023-11-23 | 2023-12-26 | 山东理工大学 | Signal control time period division method based on intersection accurate flow direction identification |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050105773A1 (en) * | 2003-09-24 | 2005-05-19 | Mitsuru Saito | Automated estimation of average stopped delay at signalized intersections |
| US20080167821A1 (en) * | 1997-10-22 | 2008-07-10 | Intelligent Technologies International, Inc. | Vehicular Intersection Management Techniques |
| CN102592451A (en) * | 2012-02-23 | 2012-07-18 | 浙江大学 | Method for detecting road traffic incident based on double-section annular coil detector |
| CN106355883A (en) * | 2016-10-20 | 2017-01-25 | 同济大学 | Risk evaluation model-based traffic accident happening probability acquiring method and system |
| CN108765985A (en) * | 2018-06-13 | 2018-11-06 | 重庆交通大学 | The signalized intersections entrance driveway delay estimation method reached based on first car |
| CN109191872A (en) * | 2018-10-09 | 2019-01-11 | 东南大学 | A kind of access connection traffic flow characteristic parameter extraction method based on number plate data |
| CN110796859A (en) * | 2019-10-28 | 2020-02-14 | 长安大学 | Real-time traffic state identification and accident risk early warning method based on traffic flow |
| CN111640295A (en) * | 2020-05-09 | 2020-09-08 | 天津市市政工程设计研究院 | Intersection accident black point distinguishing method based on potential conflict risk assessment |
| CN112489383A (en) * | 2020-11-16 | 2021-03-12 | 山东理工大学 | Early warning system and method for preventing red light running accident based on machine vision |
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080167821A1 (en) * | 1997-10-22 | 2008-07-10 | Intelligent Technologies International, Inc. | Vehicular Intersection Management Techniques |
| US20050105773A1 (en) * | 2003-09-24 | 2005-05-19 | Mitsuru Saito | Automated estimation of average stopped delay at signalized intersections |
| CN102592451A (en) * | 2012-02-23 | 2012-07-18 | 浙江大学 | Method for detecting road traffic incident based on double-section annular coil detector |
| CN106355883A (en) * | 2016-10-20 | 2017-01-25 | 同济大学 | Risk evaluation model-based traffic accident happening probability acquiring method and system |
| CN108765985A (en) * | 2018-06-13 | 2018-11-06 | 重庆交通大学 | The signalized intersections entrance driveway delay estimation method reached based on first car |
| CN109191872A (en) * | 2018-10-09 | 2019-01-11 | 东南大学 | A kind of access connection traffic flow characteristic parameter extraction method based on number plate data |
| CN110796859A (en) * | 2019-10-28 | 2020-02-14 | 长安大学 | Real-time traffic state identification and accident risk early warning method based on traffic flow |
| CN111640295A (en) * | 2020-05-09 | 2020-09-08 | 天津市市政工程设计研究院 | Intersection accident black point distinguishing method based on potential conflict risk assessment |
| CN112489383A (en) * | 2020-11-16 | 2021-03-12 | 山东理工大学 | Early warning system and method for preventing red light running accident based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 陈河明;李硕;高岩;李渭饶;: "信号交叉口期望交通延误模型及计算方法研究", 交通运输系统工程与信息, no. 03, 30 June 2013 (2013-06-30) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117275260A (en) * | 2023-11-21 | 2023-12-22 | 山东理工大学 | Emergency control method for urban road intersection entrance road traffic accident |
| CN117275260B (en) * | 2023-11-21 | 2024-02-02 | 山东理工大学 | Emergency control method for urban road intersection entrance road traffic accident |
| CN117292562A (en) * | 2023-11-23 | 2023-12-26 | 山东理工大学 | Signal control time period division method based on intersection accurate flow direction identification |
| CN117292562B (en) * | 2023-11-23 | 2024-02-20 | 山东理工大学 | Signal control time period division method based on intersection accurate flow direction identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
| CN109961639B (en) | Method for estimating queuing length of lane in oversaturated state | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN109191830B (en) | Road congestion detection method based on video image processing | |
| CN107170247B (en) | Method and device for determining queuing length of intersection | |
| CN106373426A (en) | Computer vision-based parking space and illegal lane occupying parking monitoring method | |
| CN108806272B (en) | Method and device for reminding multiple motor vehicle owners of illegal parking behaviors | |
| CN111815959B (en) | Vehicle violation detection method and device and computer readable storage medium | |
| CN106600977A (en) | Parking violation detection method and system based on multi-feature identification | |
| CN110164132B (en) | Method and system for detecting road traffic abnormity | |
| CN108932849B (en) | Method and device for recording low-speed running illegal behaviors of multiple motor vehicles | |
| CN114037924A (en) | Vehicle brake-passing judgment method based on image recognition technology and related device | |
| CN109191861B (en) | System and method for detecting abnormal behavior of fee evasion vehicle on expressway based on video detector | |
| CN107329977B (en) | A kind of false-trademark vehicle postsearch screening method based on probability distribution | |
| CN112509325B (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| CN103559792A (en) | Method for identifying fatigue driving of driver who drives vehicle on expressway | |
| CN113012436B (en) | Road monitoring method and device and electronic equipment | |
| CN110930723A (en) | Illegal parking detection implementation method | |
| CN112395976A (en) | Motorcycle manned identification method, device, equipment and storage medium | |
| CN112380892A (en) | Image identification method, device, equipment and medium | |
| CN109003457B (en) | Method and device for recording behaviors of multiple motor vehicles illegally occupying emergency lane | |
| CN116994428B (en) | Intersection entrance road traffic accident identification method based on parameter change rate | |
| CN116994428A (en) | Intersection entrance road traffic accident identification method based on parameter change rate | |
| CN108932853B (en) | Method and device for recording illegal parking behaviors of multiple motor vehicles | |
| CN114170798B (en) | Message reminding system and method |
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 |