CN116704780A - Abnormal driving behavior identification method based on GPS track data - Google Patents
Abnormal driving behavior identification method based on GPS track data Download PDFInfo
- Publication number
- CN116704780A CN116704780A CN202310818487.3A CN202310818487A CN116704780A CN 116704780 A CN116704780 A CN 116704780A CN 202310818487 A CN202310818487 A CN 202310818487A CN 116704780 A CN116704780 A CN 116704780A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- rapid
- driving behavior
- behaviors
- speed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000006399 behavior Effects 0.000 claims abstract description 201
- 230000001133 acceleration Effects 0.000 claims abstract description 73
- 230000028838 turning behavior Effects 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims description 54
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Navigation (AREA)
Abstract
An abnormal driving behavior identification method based on GPS track data belongs to the technical field of traffic safety. S1, dividing abnormal driving behaviors into overspeed behaviors, rapid acceleration behaviors, rapid deceleration behaviors, rapid lane changing behaviors and rapid turning behaviors, and extracting characteristic indexes of GPS track data of five abnormal driving behaviors; s2, determining recognition thresholds of five abnormal driving behaviors; s3, identifying abnormal driving behaviors. According to the method, through analysis and excavation of GPS track data, characteristic indexes of five different abnormal driving behavior data such as overspeed driving behavior, rapid acceleration driving behavior, rapid deceleration driving behavior, rapid lane changing driving behavior and rapid turning driving behavior are extracted, recognition thresholds of the five different abnormal driving behaviors are determined based on the extracted characteristic indexes, and further five abnormal driving behavior recognition models based on threshold overspeed, rapid acceleration, rapid deceleration, rapid lane changing and rapid turning are established, so that accurate recognition of the five abnormal driving behaviors is achieved.
Description
Technical Field
An abnormal driving behavior identification method based on GPS track data belongs to the technical field of traffic safety.
Background
The urban road traffic environment is complex and changeable, traffic problems are more serious, wherein the traffic problems with the largest loss of life and property and the most extensive social influence are regarded as traffic accidents. Research shows that abnormal driving behavior factors of drivers are main reasons for traffic accidents. Along with the continuous increase of the number of drivers and the daily and monthly variation of urban development planning and road infrastructure construction, more kinds of driving habits of different drivers are excited, but driving behaviors are difficult to analyze and describe and cannot be applied to the field of traffic safety.
Disclosure of Invention
The application aims to solve the technical problems that: the method for identifying the abnormal driving behavior based on the GPS track data overcomes the defects of the prior art, and provides a more effective, accurate and scientific method for identifying the abnormal driving behavior for traffic management departments and researchers.
The technical scheme adopted for solving the technical problems is as follows: an abnormal driving behavior identification method based on GPS track data is characterized by comprising the following steps: the method comprises the following steps:
s1, dividing abnormal driving behaviors into overspeed behaviors, rapid acceleration behaviors, rapid deceleration behaviors, rapid lane changing behaviors and rapid turning behaviors, and extracting characteristic indexes of GPS track data of five abnormal driving behaviors;
s2, determining recognition thresholds of five abnormal driving behaviors;
s3, identifying abnormal driving behaviors by traversing the GPS track data of the vehicle.
Preferably, the method further comprises, when the speed of the vehicle is greater than a vehicle speed threshold, recognizing that overspeed behavior occurs; when the acceleration speed is greater than the rapid acceleration threshold value in the acceleration state process; then the occurrence of a rapid acceleration behavior is determined; when the deceleration is smaller than the sudden deceleration threshold value in the deceleration state process, the sudden deceleration behavior is determined to occur; when the lane change angular speed of the driving behavior is greater than the rapid lane change angular speed threshold, the vehicle is considered to have rapid lane change behavior among the track points; when the cornering angular velocity of an adjacent track point is greater than the cornering angular velocity threshold, then the vehicle is considered to have a sharp cornering behaviour between the set of track points.
Preferably, the method further comprises the step of determining the speed v of the vehicle n on the road section n，i The method comprises the following steps:
wherein the longitude and latitude coordinates of the vehicle n on the road section at time t are long t 、lat t At time T-T c Longitude and latitude coordinates at the time areThe time interval of the GPS data record is T c The speed of the vehicle n on the road section is v n，i 。
Preferably, the method further comprises the section acceleration a of all the adjacent track points of the vehicle of each road section n，i + The method comprises the following steps:
wherein T is s1 Time interval recorded for GPS data, v t For the instantaneous speed of the vehicle n at time t,for at time T-T s1 The instantaneous speed of the vehicle n.
Preferably, the section deceleration a of the vehicle n on the road section n，i - The method comprises the following steps:
wherein T is s2 Time interval recorded for GPS data, v t For the instantaneous speed of the vehicle n at time t, v t -T s2 For at time T-T s2 The instantaneous speed of the vehicle n.
Preferably, the method further comprises, the lane change behavior angular velocity ω lc n, i is:
wherein d t For the direction angle of the vehicle n at time t,for at time T-T b The steering angle T of the vehicle n b Is the number of GPSThe recorded time interval.
Preferably, the method further comprises, turning behavior angular velocity ω tc n, i is:
wherein d t For the direction angle of the vehicle n at time T, T z For the time interval of the GPS data record,for at time T-T z The direction angle of the vehicle n.
Preferably, the method further comprises the step of identifying the overdrive behavior, comprising the steps of:
s3.1.1 obtaining the position change and corresponding time interval of all vehicles through the GPS track data of the vehicles, calculating the interval speed of adjacent track points of all vehicles, and sequencing from small to large;
s3.1.2 extracting the average value of the 85 th quantile of the interval speed as the speed limit threshold value of the road section;
s3.1.3 traversing all time period vehicle speed data of each road section, comparing the speed data with a speed limit threshold, and recording overspeed driving behavior in the time period of the road section when the vehicle speed is greater than the speed limit threshold;
s3.1.4 completes the overspeed behavior recognition.
Preferably, the method further comprises the following steps of:
s3.2.1 extracting relevant characteristic indexes of acceleration through GPS track data of vehicles to obtain instantaneous speeds and time intervals of all vehicles, calculating section acceleration of adjacent track points of all vehicles of each road section, and sequencing the section acceleration from small to large;
s3.2.2 selecting the 90 th quantile mean value of the interval acceleration as a sudden acceleration threshold value;
s3.2.3 traversing all vehicle acceleration sequences, and recording the occurrence of rapid acceleration driving behaviors when the vehicle acceleration is larger than a rapid acceleration threshold value;
s3.2.4 the recognition of the rapid acceleration driving behavior is completed.
Preferably, the method further comprises the step of identifying the rapid deceleration driving behavior, comprising the steps of:
s3.3.1 extracting relevant characteristic indexes of deceleration through GPS track data of the vehicles to obtain speeds and time intervals of all vehicles, calculating section deceleration of all adjacent track points of the vehicles on each road section, and sequencing the section deceleration from large to small;
s3.3.2 selecting the 90 th quantile average value of the interval deceleration as the sudden deceleration threshold value;
s3.3.3 traversing all vehicle deceleration sequences and recording that rapid deceleration driving behavior occurs when the vehicle deceleration is less than a rapid deceleration threshold;
s3.3.4 the recognition of the rapid deceleration driving behavior is completed.
Preferably, the method further comprises the step of identifying the driving behavior of the jerky road, comprising the steps of:
s3.4.1 traversing GPS track data of the same vehicle on a road section, and when two continuous data are changed by more than 6 degrees and the direction angle of the third data is corrected, determining that one lane change occurs;
s3.4.2 defining primary lane change behavior data as a group, calculating the angular velocity between the second data and the first data in each group of lane change behavior data, sorting the lane change angular velocities of the groups from small to large, and selecting the 90 th quantile average value of the lane change angular velocity as an angular velocity threshold;
s3.4.3 traversing the angular velocities of all lane change behaviors, comparing the angular velocities with a lane change angular velocity threshold value, and recording the occurrence of the rapid lane change driving behavior if the angular velocity is greater than the threshold value;
s3.4.4 the identification of the driving behavior of the rapid lane change is completed.
Preferably, the method further comprises the step of identifying the sharp-cornering behaviour comprises the steps of:
s3.5.1 traversing the track data of the same vehicle on the road section, and when the change of the direction angle of the track point which starts to end within a certain time window exceeds 90 degrees, determining that a turning action occurs;
s3.5.2 defining one-time turning behavior data as a group, calculating the angular speed of each group of turning track points, sequencing the turning angular speeds from small to large, and selecting the 90 th quantile average value of the turning angular speeds as an angular speed threshold value;
s3.5.3 traversing the angular velocities of all turning behaviors, comparing the angular velocities with a turning angular velocity threshold value, and recording that a sharp turning driving behavior occurs if the turning angular velocity is greater than the threshold value;
s3.5.4 the recognition of the sharp turning driving behavior is completed.
Compared with the prior art, the application has the following beneficial effects:
according to the method, through analysis and excavation of GPS track data, characteristic indexes of five different abnormal driving behavior data such as overspeed driving behavior, rapid acceleration driving behavior, rapid deceleration driving behavior, rapid lane changing driving behavior and rapid turning driving behavior are extracted, recognition thresholds of the five different abnormal driving behaviors are determined based on the extracted characteristic indexes, and further five abnormal driving behavior recognition models based on threshold overspeed, rapid acceleration, rapid deceleration, rapid lane changing and rapid turning are established, so that accurate recognition of the five abnormal driving behaviors is achieved.
The application provides an abnormal driving behavior identification method based on GPS track data by taking the GPS track data of a vehicle as a data source, provides an effective, accurate and real-time road network safety risk monitoring method for traffic safety management departments and researchers, facilitates the omnibearing mastering and analysis of road safety risk data, helps traffic managers effectively supervise the driving behavior of drivers, and improves road traffic safety.
Drawings
FIG. 1 is a flow chart of a method for identifying abnormal driving behavior based on GPS trajectory data;
FIG. 2 is a schematic diagram of overspeed driving behavior occurring at adjacent waypoints;
FIG. 3 is a schematic diagram of the behavior of the adjacent track points in rapid acceleration driving;
FIG. 4 is a schematic diagram of the behavior of adjacent track points in rapid deceleration driving
FIG. 5 is a schematic diagram of driving behavior of an adjacent track point in a jerky lane;
FIG. 6 is a schematic diagram of the driving behavior of a city intersection with a sharp turn;
FIG. 7 is a graph of an overdrive behavior recognition model;
FIG. 8 is a graph of a rapid acceleration driving behavior recognition model;
FIG. 9 is a graph of a rapid deceleration driving behavior recognition model;
FIG. 10 is a graph of a jerky driving behavior recognition model;
fig. 11 is a sharp-cornering behavior recognition model diagram.
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. 1-11 illustrate preferred embodiments of the present application, and the present application will be further described with reference to FIGS. 1-11.
According to the method, based on GPS track data and behavior characteristics of driving behaviors, characteristic indexes such as longitude and latitude coordinates, recording time intervals and direction angles of five different abnormal driving behaviors are respectively extracted, indexes such as speed, acceleration, deceleration, lane change angular speed and turning angular speed of the five abnormal driving behaviors and recognition thresholds are determined, and further five abnormal driving behavior recognition models based on threshold overspeed, rapid acceleration, rapid deceleration, rapid lane change and rapid turning are established, so that accurate recognition of five different abnormal driving behaviors of urban drivers is completed.
Referring to fig. 1, the application defines five different abnormal driving behaviors, extracts corresponding characteristic indexes, determines recognition thresholds of the five different abnormal driving behaviors, and establishes an abnormal driving behavior recognition model based on the thresholds. Traversing all GPS track data, and performing five abnormal driving according to the recognition threshold values of five abnormal driving behaviors such as overspeed behavior, rapid acceleration behavior, rapid deceleration behavior, rapid lane changing behavior and rapid turning behaviorBehavior is identified when v n，i ＞V m When overspeed driving behavior occurs, recording; when a is n，i + ＞A m + When the vehicle is in a driving state, the driving behavior is accelerated rapidly; when a is n，i - <A m - When the driving behavior is recorded, the driving behavior of sudden deceleration is recorded; when omega lc n，i Recording the driving behavior of the emergency lane change when the speed is more than omega bm; when omega tc n，i ＞ω zm When the driver is driving, the driver is driving in a sharp turn.
An abnormal driving behavior identification method based on GPS track data comprises the following steps:
s1, the abnormal driving behaviors are divided into overspeed behaviors, rapid acceleration behaviors, rapid deceleration behaviors, rapid lane changing behaviors and rapid turning behaviors, and feature indexes of GPS track data of the five abnormal driving behaviors are extracted.
Five different abnormal driving behaviors of overspeed, rapid acceleration, rapid deceleration, rapid lane change and rapid turning driving are respectively defined, and characteristic indexes and recognition thresholds of the five abnormal driving behaviors are determined. The specific flow is as follows:
abnormal driving behaviors are divided into five types of overspeed behaviors, rapid acceleration behaviors, rapid deceleration behaviors, rapid lane changing behaviors and rapid turning behaviors, and the five types are defined respectively. The specific definition is as follows:
overspeed behavior: comparing the speed v of the vehicle with reference to the basic principle of overspeed behavior recognition n，i And a vehicle speed threshold V m When the speed v of the vehicle n，i Greater than the threshold V of the vehicle speed m In this process, the overspeed driving behavior of the vehicle is considered to occur, and the vehicle speed value is recorded as v n，t As shown in fig. 2;
acute acceleration behavior: instantaneous velocity using adjacent trace point data during acceleration statev t And an interval time T s1 Calculating acceleration a in acceleration state process n，i + When acceleration a n，i + Greater than the rapid acceleration threshold A m + In this case, the vehicle is considered to have a rapid acceleration behavior during the process, and the acceleration value is recorded as a n，t + As shown in fig. 3;
sudden deceleration behavior: instantaneous speed using front and rear trace point data during deceleration statev t And an interval time T s2 Calculating deceleration a during deceleration state n，i - When the deceleration a n，i - Less than the threshold A of rapid deceleration m - In this case, the vehicle is considered to undergo rapid deceleration during this process, and the deceleration value at this time is recorded as a n，t - As shown in fig. 4;
jerky lane behavior: recording the change of the direction angle of the adjacent track points, when the change of the direction angle of the track points is larger than 6 degrees, and the third data direction angle is corrected (3 degrees error), judging that the lane change behavior occurs, calculating the angular speed of the driving behavior on the basis, and when the calculated angular speed omega is equal to the calculated angular speed omega lc When n, i is greater than the rapid lane angular velocity threshold ωbm, the vehicle is considered to have rapid lane behavior between the set of track points, and the lane angular velocity value is recorded as ω lc n, t, as shown in FIG. 5;
sharp cornering behaviour: recording the direction angle change of the track point, judging that turning behavior occurs when the direction angle change of the track point is more than or equal to 90 degrees, taking data meeting the condition as a group, and calculating the angular velocity omega of the adjacent track points tc n, i, when calculated turning angular velocity omega tc When n, i is greater than the turning angular velocity threshold ωzm, the vehicle is considered to have a sharp turning behavior between the set of track points, and the turning angular velocity value is recorded as ω tc n, t, as shown in fig. 6.
S2, determining recognition thresholds of five abnormal driving behaviors.
And extracting characteristic indexes of five different abnormal driving behaviors through GPS track data, and determining recognition thresholds of the five different abnormal driving behaviors. The specific flow is as follows:
determining characteristic indexes and speed limit thresholds of overspeed driving behavior:
through longitude and latitude coordinates and time interval T of front and back adjacent track points c Calculating the interval speed v of all adjacent track points of the vehicle n，i Sequencing from small to large, and extracting the average value of the vehicle speed of the 85 th quantile as the speed limit threshold V in the time period m 。
The parameters include: longitude and latitude coordinates long of vehicle n on road section at time t t 、lat t At time T-T c Longitude and latitude coordinates of timeTime interval T of GPS data recording c Speed v of vehicle n on road section n，i Speed limit threshold V n The speed value when exceeding the speed limit threshold is v n，t 。
Determining characteristic indexes and a sudden acceleration threshold value of sudden acceleration driving behaviors:
by speed and time interval T of front and rear adjacent track points s1 Calculating the section acceleration a of all the adjacent track points of the vehicles of each road section n，i + Sorting from small to large, and selecting the 90 th quantile mean value as a sudden acceleration threshold A m + 。
The parameters include: section acceleration a of vehicle n on road section n，i + Time interval T of GPS data recording s1 Instantaneous speed v of vehicle n at time t t At the time ofInstantaneous speed of vehicle n>Phase emergency acceleration threshold A m + Acceleration value a when the sudden acceleration threshold value is exceeded n，t + 。
Determining characteristic indexes and sudden deceleration threshold values of sudden deceleration driving behaviors:
by speed and time interval T of front and rear adjacent track points s2 Calculating the section deceleration a of all the adjacent track points of the vehicles of each road section n，t - Sorting from big to small, and selecting the 90 th quantile mean value as the rapid deceleration threshold A m - 。
The parameters include: section deceleration a of vehicle n on road section n，t - Time interval T of GPS data recording s2 Instantaneous speed v of vehicle n at time t t At time v t -T s2 Instantaneous speed of vehicle nEmergency deceleration threshold a m - The deceleration value when exceeding the sudden deceleration threshold value is a n，t - 。
Determining characteristic indexes and angular speed thresholds of driving behaviors of the emergency road:
by change of direction angle and time interval T of adjacent track points b Calculating the angular velocity omega of all lane change behaviors lc n, i, selecting the 90 th quantile mean value as the angular speed threshold omega bm of the rapid change track.
The parameters include: the direction angle d of the vehicle n at time t t At time T-T b Steering angle of vehicle nTime interval T of GPS data recording b Lane change behavior angular velocity omega lc n, i, angular velocity threshold ω of the jerky track bm The angular velocity value when exceeding the abrupt change road angular velocity threshold value is omega l cn，t。
Determining characteristic indexes and angular speed thresholds of the driving behavior of the sharp turning:
by change of direction angle and time interval T of adjacent track points z Calculating the angular velocity omega of all turning behaviors tc n, i, selecting the 90 th quantile mean value as the angular velocity threshold omega zm of the sharp turn.
The parameters include: the direction angle d of the vehicle n at time t t Time interval T of GPS data recording z At time T-T z Direction angle d of vehicle n t-T z, cornering behaviour angular velocity ω tc n, i, angular velocity threshold ωzm of abrupt turning, and the angular velocity value when exceeding the abrupt road angular velocity threshold is ω tc n，t
S3, identifying abnormal driving behaviors by traversing the GPS track data of the vehicle.
And establishing an abnormal driving behavior identification model based on the threshold value. The vehicle GPS track data is traversed, and five abnormal driving behaviors are identified according to the identification threshold values of the five abnormal driving behaviors such as overspeed behavior, rapid acceleration behavior, rapid deceleration behavior, rapid lane changing behavior and rapid turning behavior. The specific identification process comprises the following steps:
overspeed driving behavior identification based on GPS trajectory data:
s3.1.1 obtaining the position changes of all vehicles and corresponding time intervals T by GPS track data of the vehicles c Calculating the interval speed v of all adjacent track points of the vehicle n，i Sequencing from small to large;
s3.1.1 extraction section vehicle speed v n，i Mean value of 85 th quantile of vehicle speedSpeed limit threshold V for this road section m ；
S3.1.1 traversing all time period vehicle speed data of each road section, and limiting speed threshold V m Comparing when the vehicle speed v n，i Greater than the speed limit threshold V m Recording overspeed driving behavior in the period of the road section;
s3.1.1 completes the overspeed behavior recognition, see fig. 7.
And (3) identifying the rapid acceleration driving behavior based on GPS track data:
s3.2.1 extracting the related characteristic indexes of acceleration by vehicle GPS track data to obtain the instantaneous speeds and time intervals T of all vehicles s1 Calculating the section acceleration a of all the adjacent track points of the vehicles of each road section n，i + Sequencing the section acceleration from small to large;
s3.2.2 selecting 90 th quantile mean value of interval acceleration as a sudden acceleration threshold value A m + ；
S3.2.3 traversing all vehicle acceleration sequences when vehicle acceleration a n，i + Greater than the rapid acceleration threshold A m + When the driving behavior is recorded, the rapid acceleration driving behavior is recorded;
s3.2.4, see fig. 8, completes the recognition of the rapid acceleration driving behavior.
Rapid deceleration driving behavior identification based on GPS trajectory data:
s3.3.1 extracting relevant characteristic indexes of deceleration by vehicle GPS track data to obtain speeds and time intervals Ts2 of all vehicles, and calculating section deceleration a of all adjacent track points of all vehicles of each road section n，i - Sequencing the interval deceleration from big to small;
s3.3.2 selecting 90 th quantile average value of interval deceleration as sudden deceleration threshold A m - ；
S3.3.3 traversing all vehicle deceleration sequences when vehicle deceleration a n，t - Less than the threshold A of rapid deceleration m - When the driving behavior is recorded, the driving behavior of sudden deceleration is recorded;
s3.3.4 the recognition of the rapid deceleration driving behavior is completed, see fig. 9.
Identification of rapid lane change driving behavior based on GPS track data
S3.4.1 traversing GPS track data of the same vehicle on a road section, and when two continuous data are changed by more than 6 degrees and the direction angle of the third data is corrected (3 degrees error), determining that one lane change behavior occurs;
s3.4.2 defining primary lane change data as groups, and calculating angular velocity omega between second data and first data in each group of lane change data lc n, i, sorting the variable-track angular velocities of each group from small to large, and selecting the 90 th quantile average value of the variable-track angular velocities as an angular velocity threshold omega bm;
s3.4.3 angular velocity ω of all lane change behavior lc n, i, compared with the lane change angular velocity threshold ωbm, if the angular velocity ω lc n, i is greater than a threshold omega bm, and recording the driving behavior of the emergency lane change;
s3.4.4 completes the identification of the rapid lane change driving behavior, see fig. 10.
Identification of sharp turning driving behavior based on GPS trajectory data:
s3.5.1 traversing the track data of the same vehicle on the road section, and when the change of the direction angle of the track point which starts to end within a certain time window exceeds 90 degrees, determining that a turning action occurs;
s3.5.2 defining one-turn behavior data as groups, calculating angular velocity ω of each group of turn locus points tc n, i, sorting the turning angular velocity from small to large, and selecting the 90 th quantile average value of the turning angular velocity as an angular velocity threshold omega zm;
s3.5.3 angular velocity ω of all cornering behaviour is traversed tc n, i, compared with the turning angular velocity threshold ωzm, if the turning angular velocity ω tc n, i is greater than a threshold ωzm, and recording the driving behavior of a sharp turn;
s3.5.4 completes the recognition of the sharp turning driving behavior, see fig. 11.
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 (10)
1. An abnormal driving behavior identification method based on GPS track data is characterized by comprising the following steps: the method comprises the following steps:
s1, dividing abnormal driving behaviors into overspeed behaviors, rapid acceleration behaviors, rapid deceleration behaviors, rapid lane changing behaviors and rapid turning behaviors, and extracting characteristic indexes of GPS track data of five abnormal driving behaviors;
s2, determining recognition thresholds of five abnormal driving behaviors;
s3, identifying abnormal driving behaviors by traversing the GPS track data of the vehicle;
when the speed of the vehicle is greater than the speed threshold, overspeed behavior is considered to occur; when the acceleration speed is greater than the rapid acceleration threshold value in the acceleration state process; then the occurrence of a rapid acceleration behavior is determined; when the deceleration is smaller than the sudden deceleration threshold value in the deceleration state process, the sudden deceleration behavior is determined to occur; when the lane change angular speed of the driving behavior is greater than the rapid lane change angular speed threshold, the vehicle is considered to have rapid lane change behavior among the track points; when the cornering angular velocity of an adjacent track point is greater than the cornering angular velocity threshold, then the vehicle is considered to have a sharp cornering behaviour between the set of track points.
2. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method further comprises the step of determining the speed v of the vehicle n on the road section n，i The method comprises the following steps:
wherein the longitude and latitude coordinates of the vehicle n on the road section at time t are long t 、lat t At time T-T c Longitude and latitude coordinates at the time are long t-Tc 、lat t -T c The time interval of the GPS data record is T c The speed of the vehicle n on the road section is v n，i 。
3. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method also comprises the section acceleration a of all the adjacent track points of the vehicles of each road section n，i + The method comprises the following steps:
wherein T is s1 Time interval recorded for GPS data, v t For the instantaneous speed of the vehicle n at time t,for at time T-T s1 The instantaneous speed of the vehicle n.
4. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: section deceleration a of vehicle n on road section n，i - The method comprises the following steps:
wherein T is s2 Time interval recorded for GPS data, v t For the instantaneous speed of the vehicle n at time t,for at time T-T s2 The instantaneous speed of the vehicle n.
5. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method also comprises the following steps of changing the angular velocity of the track behaviorDegree omega lc n，i The method comprises the following steps:
wherein d t For the direction angle of the vehicle n at time t,for at time T-T b The steering angle T of the vehicle n b Time intervals recorded for GPS data.
6. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method further comprises the turning behavior angular velocity omega tc n，i The method comprises the following steps:
wherein d t For the direction angle of the vehicle n at time T, T z For the time interval of the GPS data record,for at time T-T z The direction angle of the vehicle n.
7. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method further comprises the following steps of:
s3.1.1 obtaining the position change and corresponding time interval of all vehicles through the GPS track data of the vehicles, calculating the interval speed of adjacent track points of all vehicles, and sequencing from small to large;
s3.1.2 extracting the average value of the 85 th quantile of the interval speed as the speed limit threshold value of the road section;
s3.1.3 traversing all time period vehicle speed data of each road section, comparing the speed data with a speed limit threshold, and recording overspeed driving behavior in the time period of the road section when the vehicle speed is greater than the speed limit threshold;
s3.1.4 completes the overspeed behavior recognition.
8. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method also comprises the following steps of:
s3.2.1 extracting relevant characteristic indexes of acceleration through GPS track data of vehicles to obtain instantaneous speeds and time intervals of all vehicles, calculating section acceleration of adjacent track points of all vehicles of each road section, and sequencing the section acceleration from small to large;
s3.2.2 selecting the 90 th quantile mean value of the interval acceleration as a sudden acceleration threshold value;
s3.2.3 traversing all vehicle acceleration sequences, and recording the occurrence of rapid acceleration driving behaviors when the vehicle acceleration is larger than a rapid acceleration threshold value;
s3.2.4 the recognition of the rapid acceleration driving behavior is completed.
9. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method further comprises the steps of identifying the driving behavior of the rapid change road, including the following steps:
s3.4.1 traversing GPS track data of the same vehicle on a road section, and when two continuous data are changed by more than 6 degrees and the direction angle of the next data is corrected, determining that a lane change behavior occurs;
s3.4.2 defining primary lane change behavior data as a group, calculating the angular velocity between the second data and the first data in each group of lane change behavior data, sorting the lane change angular velocities of the groups from small to large, and selecting the 90 th quantile average value of the lane change angular velocity as an angular velocity threshold;
s3.4.3 traversing the angular velocities of all lane change behaviors, comparing the angular velocities with a lane change angular velocity threshold value, and recording the occurrence of the rapid lane change driving behavior if the angular velocity is greater than the threshold value;
s3.4.4 the identification of the driving behavior of the rapid lane change is completed.
10. The abnormal driving behavior recognition method based on GPS trajectory data according to claim 1, wherein: the method further comprises the step of identifying the sharp turning driving behavior, comprising the following steps:
s3.5.1 traversing the track data of the same vehicle on the road section, and when the change of the direction angle of the track point which starts to end within a certain time window exceeds 90 degrees, determining that a turning action occurs;
s3.5.2 defining one-time turning behavior data as a group, calculating the angular speed of each group of turning track points, sequencing the turning angular speeds from small to large, and selecting the 90 th quantile average value of the turning angular speeds as an angular speed threshold value;
s3.5.3 traversing the angular velocities of all turning behaviors, comparing the angular velocities with a turning angular velocity threshold value, and recording that a sharp turning driving behavior occurs if the turning angular velocity is greater than the threshold value;
s3.5.4 the recognition of the sharp turning driving behavior is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818487.3A CN116704780A (en) | 2023-07-05 | 2023-07-05 | Abnormal driving behavior identification method based on GPS track data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818487.3A CN116704780A (en) | 2023-07-05 | 2023-07-05 | Abnormal driving behavior identification method based on GPS track data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116704780A true CN116704780A (en) | 2023-09-05 |
Family
ID=87839155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310818487.3A Pending CN116704780A (en) | 2023-07-05 | 2023-07-05 | Abnormal driving behavior identification method based on GPS track data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116704780A (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008302849A (en) * | 2007-06-08 | 2008-12-18 | Sumitomo Electric Ind Ltd | Vehicle driving support system, driving support device, vehicle, and vehicle driving support method |
| CN102023305A (en) * | 2010-08-05 | 2011-04-20 | 深圳市赛格导航科技股份有限公司 | Positioning method and device as well as vehicle-mounted terminal |
| CN103856978A (en) * | 2012-12-06 | 2014-06-11 | 中国联合网络通信集团有限公司 | Mobile network quality assessing method and device |
| CN106127883A (en) * | 2016-06-23 | 2016-11-16 | 北京航空航天大学 | driving event detection method |
| CN107284451A (en) * | 2017-06-22 | 2017-10-24 | 北京雄信息科技有限公司 | The monitoring method and system of bad steering behavior based on GPS |
| CN107433921A (en) * | 2017-04-21 | 2017-12-05 | 深圳市博实结科技有限公司 | A kind of travel condition of vehicle monitoring method, device and system |
| CN108694756A (en) * | 2018-05-09 | 2018-10-23 | 北京九五智驾信息技术股份有限公司 | The method that driving behavior is analyzed |
| CN109017798A (en) * | 2018-05-09 | 2018-12-18 | 北京九五智驾信息技术股份有限公司 | Driving behavior analysis method |
| CN109345870A (en) * | 2018-09-07 | 2019-02-15 | 北京邮电大学 | The method for early warning and device for preventing vehicle collision |
| CN110047167A (en) * | 2019-04-15 | 2019-07-23 | 上海经达信息科技股份有限公司 | Vehicle zig zag number equivalent statistics method |
| CN110615001A (en) * | 2019-09-27 | 2019-12-27 | 汉纳森（厦门）数据股份有限公司 | Driving safety reminding method, device and medium based on CAN data |
| CN111131617A (en) * | 2019-12-28 | 2020-05-08 | 长安大学 | Driving behavior analysis and feedback method based on smart phone |
| CN111942397A (en) * | 2020-08-06 | 2020-11-17 | 华南理工大学 | Dangerous driving behavior monitoring method and device and storage medium |
| CN113442935A (en) * | 2021-07-15 | 2021-09-28 | 华中科技大学 | Method and system for judging poor driving behavior of commercial vehicle |
| CN114701505A (en) * | 2022-05-06 | 2022-07-05 | 上海金脉电子科技有限公司 | Method and device for determining vehicle running state and storage medium |
| CN114882695A (en) * | 2022-03-24 | 2022-08-09 | 成都亿盟恒信科技有限公司 | High risk judgment method and system based on sharp acceleration and sharp reduction and sharp turning data |
| CN115257771A (en) * | 2022-09-28 | 2022-11-01 | 天津所托瑞安汽车科技有限公司 | Intersection identification method, electronic device and storage medium |
| CN115909752A (en) * | 2022-11-01 | 2023-04-04 | 东南大学 | Sharp turn recognition and statistics method based on historical data of vehicle user |
| CN116368544A (en) * | 2020-10-16 | 2023-06-30 | 格步计程车控股私人有限公司 | Method, electronic device and system for detecting overspeed |
-
2023
- 2023-07-05 CN CN202310818487.3A patent/CN116704780A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008302849A (en) * | 2007-06-08 | 2008-12-18 | Sumitomo Electric Ind Ltd | Vehicle driving support system, driving support device, vehicle, and vehicle driving support method |
| CN102023305A (en) * | 2010-08-05 | 2011-04-20 | 深圳市赛格导航科技股份有限公司 | Positioning method and device as well as vehicle-mounted terminal |
| CN103856978A (en) * | 2012-12-06 | 2014-06-11 | 中国联合网络通信集团有限公司 | Mobile network quality assessing method and device |
| CN106127883A (en) * | 2016-06-23 | 2016-11-16 | 北京航空航天大学 | driving event detection method |
| CN107433921A (en) * | 2017-04-21 | 2017-12-05 | 深圳市博实结科技有限公司 | A kind of travel condition of vehicle monitoring method, device and system |
| CN107284451A (en) * | 2017-06-22 | 2017-10-24 | 北京雄信息科技有限公司 | The monitoring method and system of bad steering behavior based on GPS |
| CN108694756A (en) * | 2018-05-09 | 2018-10-23 | 北京九五智驾信息技术股份有限公司 | The method that driving behavior is analyzed |
| CN109017798A (en) * | 2018-05-09 | 2018-12-18 | 北京九五智驾信息技术股份有限公司 | Driving behavior analysis method |
| CN109345870A (en) * | 2018-09-07 | 2019-02-15 | 北京邮电大学 | The method for early warning and device for preventing vehicle collision |
| CN110047167A (en) * | 2019-04-15 | 2019-07-23 | 上海经达信息科技股份有限公司 | Vehicle zig zag number equivalent statistics method |
| CN110615001A (en) * | 2019-09-27 | 2019-12-27 | 汉纳森（厦门）数据股份有限公司 | Driving safety reminding method, device and medium based on CAN data |
| CN111131617A (en) * | 2019-12-28 | 2020-05-08 | 长安大学 | Driving behavior analysis and feedback method based on smart phone |
| CN111942397A (en) * | 2020-08-06 | 2020-11-17 | 华南理工大学 | Dangerous driving behavior monitoring method and device and storage medium |
| CN116368544A (en) * | 2020-10-16 | 2023-06-30 | 格步计程车控股私人有限公司 | Method, electronic device and system for detecting overspeed |
| CN113442935A (en) * | 2021-07-15 | 2021-09-28 | 华中科技大学 | Method and system for judging poor driving behavior of commercial vehicle |
| CN114882695A (en) * | 2022-03-24 | 2022-08-09 | 成都亿盟恒信科技有限公司 | High risk judgment method and system based on sharp acceleration and sharp reduction and sharp turning data |
| CN114701505A (en) * | 2022-05-06 | 2022-07-05 | 上海金脉电子科技有限公司 | Method and device for determining vehicle running state and storage medium |
| CN115257771A (en) * | 2022-09-28 | 2022-11-01 | 天津所托瑞安汽车科技有限公司 | Intersection identification method, electronic device and storage medium |
| CN115909752A (en) * | 2022-11-01 | 2023-04-04 | 东南大学 | Sharp turn recognition and statistics method based on historical data of vehicle user |
Non-Patent Citations (2)
| Title |
|---|
| 惠飞;彭娜;景首才;周琪;贾硕;: "基于凝聚层次的驾驶行为聚类与异常检测方法", 计算机工程, no. 12, 1 November 2018 (2018-11-01) * |
| 杨洪: "电子计算机常用算法选编》", 31 March 1985, 山东科学技术出版社, pages: 41 - 44 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110728842B (en) | Abnormal driving early warning method based on reasonable driving range of vehicles at intersection | |
| CN102568200B (en) | Method for judging vehicle driving states in real time | |
| CA2811879C (en) | Driver profiling system and method | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| CN106652445A (en) | Road traffic accident judging method and device | |
| CN108871357B (en) | Method for displaying accident lane of congested road section on electronic map | |
| US20220383738A1 (en) | Method for short-term traffic risk prediction of road sections using roadside observation data | |
| CN100466010C (en) | Different species traffic information real time integrating method | |
| CN109523787A (en) | A kind of fatigue driving analysis method based on vehicle pass-through track | |
| CN114999181A (en) | ETC system data-based highway vehicle speed abnormity identification method | |
| CN108482385B (en) | A kind of mobile unit operational risk discrimination method considering traffic environment complexity | |
| CN106875677A (en) | Method, analysis platform and system for analyzing driving behavior | |
| CN114169444B (en) | Driving style classification method considering risk potential field distribution under vehicle following working condition | |
| CN108492563B (en) | Overspeed event detection method based on average speed | |
| Wang et al. | Causation analysis of crashes and near crashes using naturalistic driving data | |
| Mahapatra et al. | Dynamic parameters of vehicles under heterogeneous traffic stream with non-lane discipline: an experimental study | |
| CN110619340A (en) | Method for generating lane change rule of automatic driving automobile | |
| CN102945602B (en) | Vehicle trajectory classifying method for detecting traffic incidents | |
| CN109147320B (en) | Road section traffic state discrimination method based on checkpoint data | |
| CN116704780A (en) | Abnormal driving behavior identification method based on GPS track data | |
| CN108665723A (en) | A kind of information acquisition method and device | |
| CN106897948B (en) | Riding and pushing traffic accident identification method | |
| CN112927497B (en) | Floating car identification method, related method and device | |
| CN112373482B (en) | Driving habit modeling method based on driving simulator | |
| CN109448377B (en) | Method for evaluating vehicle driving safety by using satellite positioning data |
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 |