CN111968365B - Non-signalized intersection vehicle behavior analysis method and system and storage medium - Google Patents
Non-signalized intersection vehicle behavior analysis method and system and storage medium Download PDFInfo
- Publication number
- CN111968365B CN111968365B CN202010723673.5A CN202010723673A CN111968365B CN 111968365 B CN111968365 B CN 111968365B CN 202010723673 A CN202010723673 A CN 202010723673A CN 111968365 B CN111968365 B CN 111968365B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- distance
- speed
- tracks
- track
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
- G06F16/906—Clustering; Classification
-
- 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
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)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a system for analyzing vehicle behaviors at a non-signalized intersection and a computer-readable storage medium, belongs to the technical field of vehicle behavior analysis, and solves the technical problem that the vehicle behavior mode of the non-signalized intersection cannot be objectively, simply and conveniently obtained in the prior art. A non-signalized intersection vehicle behavior analysis method comprises the following steps: in the vehicle track acquisition area, acquiring the distance between a vehicle and a stop line and the corresponding instantaneous speed of the vehicle to obtain a series of vehicle distance-speed tracks; acquiring the distance between any two vehicle distance-speed tracks according to a series of vehicle distance-speed tracks; and clustering all the vehicle distance-speed tracks according to the distance between any two vehicle distance-speed tracks to obtain the distance between the vehicle and the stop line and the corresponding clustering result of the vehicle instantaneous speed. The method of the invention can objectively and simply obtain the behavior mode of the vehicle at the non-signal control intersection.
Description
Technical Field
The invention relates to the technical field of vehicle behavior analysis, in particular to a method and a system for analyzing vehicle behaviors at a non-signalized intersection and a computer-readable storage medium.
Background
The traffic accidents at the highway level intersections in China account for 30-40% of the total accidents, wherein the accident rate and the accident severity of the non-signal control level intersections are higher than those of the signal control level intersections, so that the traffic safety problems of the non-signal intersections are very severe, the vehicle behavior modes of the non-signal control intersections are deeply analyzed, and the safety management efficiency of the vehicles passing through the non-signal control intersections is improved to meet the personal benefits of people.
However, in the traditional behavior pattern analysis of the vehicle crossing the non-signal control intersection, the motor vehicle behavior research is mainly based on behavior characteristic observation statistics or questionnaire survey and the like, and the method is single and subjective; in order to avoid the problems, some scholars adopt vehicle sensor data or recruit drivers who voluntarily receive experiments and install experimental equipment on the vehicles to acquire experimental data to study the driving behaviors of the vehicles, however, the behavior difference of the vehicles at a non-signal control intersection is delicate, so that the difficulty of data acquisition is increased, the error of the acquired data is large, and the operation of the method is complex. At present, an objective and highly operable vehicle behavior pattern analysis method is not available at a non-signal control intersection.
Disclosure of Invention
In view of the above, the invention provides a method and a system for analyzing vehicle behavior at a non-signalized intersection and a computer-readable storage medium, so as to solve the technical problem that the vehicle behavior mode at the non-signalized intersection cannot be objectively and simply obtained in the prior art.
In one aspect, the invention provides a method for analyzing vehicle behaviors at a non-signalized intersection, which comprises the following steps:
in the vehicle track acquisition area, acquiring the distance between a vehicle and a stop line and the corresponding instantaneous speed of the vehicle, and acquiring a series of vehicle distance-speed tracks according to the distance between the vehicle and the stop line and the corresponding instantaneous speed of the vehicle;
acquiring the distance between any two vehicle distance-speed tracks according to a series of vehicle distance-speed tracks;
and clustering all the vehicle distance-speed tracks according to the distance between any two vehicle distance-speed tracks to obtain the distance between the vehicle and the stop line and the corresponding clustering result of the vehicle instantaneous speed.
Further, the method for analyzing the vehicle behaviors at the non-signalized intersection further comprises the step of taking an area between a first set distance from the stop line and a second set distance exceeding the stop line as a vehicle track acquisition area.
Further, the obtaining of the distance from the vehicle to the stop line specifically includes obtaining a length of a trajectory through a distance calculation formula, and obtaining the distance from the vehicle to the stop line according to the length of the trajectory, where the distance calculation formula is L ═ L1+l2+...+li+...+ln，
Wherein liIs the distance, x, between two coordinate points of the total adjacent trackiIs the abscissa, y, of the ith track point in the trackiIs the ordinate of the ith track point in one track, and L is the length of the track.
Further, acquiring the corresponding vehicle instantaneous speed specifically comprises acquiring the distance vector of each frame motion of the vehicle and the frame rate of the observation video, and utilizing a formula
Acquiring a corresponding vehicle instantaneous speed, wherein V is the corresponding vehicle instantaneous speed,
a distance vector for each frame of motion of the vehicle, and f is a frame rate of the observation video.
Further, acquiring the distance between any two vehicle distance-speed tracks according to a series of vehicle distance-speed tracks specifically comprises acquiring the distance between any two vehicle distance-speed tracks according to a track distance calculation formula, wherein the track distance calculation formula is that
Wherein the content of the first and second substances,
d⊥represents the distance of the two tracks; TrajS represents the shorter of the two traces compared two by two; TrajL represents the longer of the two traces compared two by two; l⊥iThe vertical distance from the ith point representing the shorter track to the longer track; s0A first point representing a shorter vehicle trajectory; si(xnumji，ynumji) An ith point representing a shorter vehicle trajectory; sn(xnumji+1i，ynumji+1i) N-th point, L, representing a shorter vehicle trajectory0(xl0，yl0) A first point representing a longer vehicle trajectory; l isi(xli，yli) An ith point representing a longer vehicle trajectory; l isn(xln，yln) The nth point representing a longer vehicle trajectory,
is a line segment L0S0The direction vector of (a) is,
is a line segment L0LnDirection vector of e1And e2Are respectively as
And
the unit vector of (2).
Further, according to the distance between any two vehicle distance-speed tracks, clustering all the vehicle distance-speed tracks, specifically comprising determining a clustering radius and a neighborhood object number, according to the size relationship between the distance between any two vehicle distance-speed tracks and the clustering radius, determining whether the corresponding vehicle distance-speed tracks are placed in the same cluster, and according to the size relationship between the cluster number and the neighborhood object number, determining whether the tracks in the cluster are clustering results.
And further, determining whether the corresponding vehicle distance-speed tracks are put into the same cluster according to the size relation between the distance between any two vehicle distance-speed tracks and the clustering radius, wherein the step of specifically comprises the step of putting the two vehicle distance-speed tracks into the same cluster if the distance between the two vehicle distance-speed tracks is smaller than the clustering radius, and otherwise, not putting the two vehicle distance-speed tracks into the same cluster.
Further, determining whether the track in the cluster is a clustering result according to the size relationship between the track number in the cluster and the number of the neighborhood objects, specifically, determining the track in the cluster as the clustering result if the track number in the cluster is greater than the number of the neighborhood objects, otherwise, discarding the track of the cluster.
On the other hand, the invention also provides a non-signalized intersection vehicle behavior analysis system, which comprises a processor and a memory, wherein the memory is stored with a computer program, and when the computer program is executed by the processor, the non-signalized intersection vehicle behavior analysis method is realized according to any one of the technical schemes.
In another aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the non-signalized intersection vehicle behavior analysis method according to any one of the above technical solutions.
Compared with the prior art, the invention has the beneficial effects that: obtaining the distance between a vehicle and a stop line and the corresponding instantaneous speed of the vehicle in a vehicle track acquisition area, and obtaining a series of vehicle distance-speed tracks according to the distance between the vehicle and the stop line and the corresponding instantaneous speed of the vehicle; acquiring the distance between any two vehicle distance-speed tracks according to a series of vehicle distance-speed tracks; and clustering all the vehicle distance-speed tracks according to the distance between any two vehicle distance-speed tracks to obtain the distance between the vehicle and the stop line and a corresponding clustering result of the vehicle instantaneous speed, and objectively, simply and conveniently acquiring the behavior mode of the vehicle at the non-signal control intersection according to the clustering result.
Drawings
Fig. 1 is a schematic flow chart of a method for analyzing vehicle behavior at a non-signalized intersection according to embodiment 1 of the present invention;
fig. 2 is a schematic view of a vehicle track acquisition area according to embodiment 1 of the present invention;
fig. 3 is a schematic diagram of a distance-speed trajectory of a vehicle according to embodiment 1 of the present invention;
FIG. 4 is a schematic diagram of calculating a distance between two tracks according to embodiment 1 of the present invention;
fig. 5 is a schematic diagram of a track clustering idea according to embodiment 1 of the present invention;
fig. 6 is a schematic flow chart of track clustering according to embodiment 1 of the present invention;
fig. 7 shows a track clustering result according to embodiment 1 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
The embodiment of the invention provides a method for analyzing vehicle behaviors at a non-signalized intersection, which is a flow schematic diagram and comprises the following steps of:
s1, in the vehicle track acquisition area, acquiring the distance between the vehicle and the stop line and the corresponding vehicle instantaneous speed, and acquiring a series of vehicle distance-speed tracks according to the distance between the vehicle and the stop line and the corresponding vehicle instantaneous speed;
s2, acquiring the distance between any two vehicle distance-speed tracks according to the series of vehicle distance-speed tracks;
and S3, clustering the distance-speed tracks of all vehicles according to the distance between any two distance-speed tracks of the vehicles to obtain the distance between the vehicle and the stop line and the corresponding clustering result of the instantaneous speed of the vehicle.
Preferably, the method for analyzing the vehicle behavior at the non-signalized intersection further comprises taking an area between a first set distance from the stop line and a second set distance beyond the stop line as a vehicle track acquisition area.
In one specific embodiment, since the length of a vehicle body of a general vehicle is 4.5-5 meters, the vehicle reaction behavior of the vehicle at a non-signalized intersection to a sign is involved in the embodiment of the invention, and some vehicles can more or less cross a stop line when reacting to the sign at the non-signalized intersection, the embodiment of the invention takes an area 5-5.5 meters (specifically, 5 meters) behind the stop line of an entrance lane of the non-signalized intersection and 1-1.5 meters (specifically, 1.5 meters) beyond the stop line as a vehicle track collection area (research area), and the vehicle track collection area is schematically illustrated as fig. 2;
preferably, the obtaining of the distance from the vehicle to the stop line specifically includes obtaining a length of a trajectory through a distance calculation formula, and obtaining the distance from the vehicle to the stop line according to the length of the trajectory, where the distance calculation formula is L ═ L1+l2+...+li+...+ln，
Wherein liIs the distance, x, between two coordinate points of the total adjacent trackiIs the abscissa, y, of the ith track point in the trackiThe ordinate of the ith track point in one track is shown, and L is the length of the track;
preferably, the obtaining of the corresponding vehicle instantaneous speed specifically includes obtaining a distance vector of each frame motion of the vehicle and a frame rate of the observation video, and using a formula
Acquiring a corresponding vehicle instantaneous speed, wherein V is the corresponding vehicle instantaneous speed,
a distance vector of each frame motion of the vehicle, and f is a frame rate of the observation video;
in one specific embodiment, by recording a video of a vehicle driving into a non-signal control intersection, image recognition software (Traffic Intelligence, TvaLib open source trajectory analysis platform) of a computer vision technology is used for extracting vehicle speed and distance vector data and storing the data into a database SQLite; the distance between the vehicle and the stop line and the corresponding vehicle instantaneous speed are obtained, that is, the distance between the vehicle and the stop line and the corresponding vehicle instantaneous speed are obtained in one frame of image, and the vehicle instantaneous speed and the distance data between the vehicle and the stop line can be extracted by writing a script file through Python to obtain a series of vehicle distance-speed tracks, wherein a schematic diagram of the vehicle distance-speed tracks is shown in fig. 3, an abscissa represents the distance between the vehicle and the stop line, that is, the distance between the vehicle and the zero point, and an ordinate represents the vehicle speed;
preferably, the step of obtaining the distance between any two vehicle distance-speed tracks according to a series of vehicle distance-speed tracks specifically comprises obtaining the distance between any two vehicle distance-speed tracks according to a track distance calculation formula, wherein the track distance calculation formula is
Wherein the content of the first and second substances,
d⊥represents the distance of the two tracks; TrajS denotes two rails compared two by twoThe shorter of the traces; TrajL represents the longer of the two traces compared two by two; l⊥iThe vertical distance from the ith point representing the shorter track to the longer track; s0A first point representing a shorter vehicle trajectory; si(xnumji，ynumji) An ith point representing a shorter vehicle trajectory; sn(xnumji+1i，ynumji+1i) N-th point, L, representing a shorter vehicle trajectory0(xl0，yl0) A first point representing a longer vehicle trajectory; l isi(xli，yli) An ith point representing a longer vehicle trajectory; l isn(xln，yln) The nth point representing a longer vehicle trajectory,
is a line segment L0S0The direction vector of (a) is,
is a line segment L0LnDirection vector of e1And e2Are respectively as
And
a unit vector of (a);
preferably, the method for clustering the distance-speed tracks of all vehicles according to the distance between any two distance-speed tracks of the vehicles specifically comprises the steps of determining a clustering radius and the number of neighborhood objects, determining whether the distance-speed tracks of the corresponding vehicles are placed in the same cluster according to the size relationship between the distance between any two distance-speed tracks of the vehicles and the clustering radius, and determining whether the tracks in the cluster are clustering results according to the size relationship between the number of the clusters and the number of the neighborhood objects;
in one embodiment, a schematic diagram of calculating the distance between two tracks is shown in fig. 4, and based on the calculated distance between two tracks, if the distance between two tracks is smaller than the clustering halfIf the track number of the paths which are clustered into one class is larger than the minimum cluster number, the cluster is used as a class track mode; there are five parameters in total, namely the distance d between two tracks⊥(TrajS, TrajL), cluster radius D, minimum cluster number MinL, number of vehicle tracks n of cluster 1, number of vehicle tracks m of cluster 2, wherein the parameter determination of D and MinL is determined according to specific research purpose and acquired data characteristics, and is adjusted appropriately according to the clustering result, n and m after D and MinL are determined are only larger than or equal to the number of MinL and D⊥(TrajS, TrajL) is less than D, the cluster is determined as the final classification result; a track clustering idea diagram, as shown in fig. 5;
the track clustering step is (1) determining the clustering radius and the number of neighborhood objects according to the research purpose and the distribution condition of track data; (2) randomly selecting a track trj1, respectively comparing the length of the selected track with the length of the rest tracks, and respectively calculating the distance L between the two tracks; (3) judging whether the distance L is smaller than the clustering radius, if so, putting the track and trj1 into the same cluster T, otherwise, discarding the track, and repeating the steps until all the tracks are judged; (4) whether the track number in the cluster T is larger than the number of the neighborhood objects or not is judged, if so, the cluster is determined as one type of the clustering result, otherwise, the track of the cluster is discarded; (5) repeating the steps (3) and (4) until all the tracks are compared; (6) and finishing track clustering and acquiring various track data of the track clustering.
In another specific embodiment, a track clustering is performed by using an improved DBSCAN algorithm, and a track clustering flow diagram is shown in fig. 6, where the track clustering is specifically as follows, S11, an input radius D, and a neighborhood object number MinL; s12, randomly selecting a track L1 from the vehicle space-time track data set D, and setting the clustering type T as 1 and the number i as 1; s13, judging whether the track L1 is marked as F (whether the track does not belong to the clustering type T), judging whether the track L1 is noise, if so, reselecting the track, and if so, executing S14; s14, randomly selecting another track L2 from the vehicle spatiotemporal track data set D, S15, judging whether the track L2 is marked as T, judging whether the track L2 is noise, if so, re-selecting the track, and if not, executing S16; s16, comparing the lengths of the tracks L1 and L2, calculating the spacing distance between the two, and marking L2 as T; s17, comparing whether the spacing distance is smaller than the radius D, if so, executing S18; s18 sets the aggregation type to T ═ 1 and the number i ═ i + +, performs step S20; otherwise, executing S19; s19, marking the track L2 as noise, and executing the step S14; s20, judging whether the number i is larger than the MinL of the neighborhood objects, if not, executing a step S21, and if so, executing S22; step S21, marking the track L1 as noise, and executing S12 again; s22, marking the track L2 as F, finishing clustering when the clustering type T is 1, and re-assigning T to be T + +; s23, judging whether all the track classification is finished, if not, executing the step S12 again, and if so, executing the step S24; step S24, finishing all track clustering;
preferably, according to the size relationship between the distance between any two vehicle distance-speed tracks and the clustering radius, determining whether the corresponding vehicle distance-speed tracks are placed in the same cluster, specifically, if the distance between the two vehicle distance-speed tracks is smaller than the clustering radius, placing the two vehicle distance-speed tracks in the same cluster, otherwise, not placing the two vehicle distance-speed tracks in the same cluster;
preferably, determining whether the track in the cluster is a clustering result according to the size relationship between the track number in the cluster and the number of the neighborhood objects, specifically, determining the track in the cluster as the clustering result if the track number in the cluster is greater than the number of the neighborhood objects, otherwise, discarding the track of the cluster;
in a specific embodiment, the video data obtained by field investigation is subjected to cluster analysis by using speed-distance data obtained by a vehicle track as cluster basic data and using an improved DBSCAN algorithm, and a parking control intersection in a non-signalized intersection is taken as an example, track clustering results are shown in fig. 7, where an abscissa represents a distance from a vehicle to a stop line, i.e., a zero point, and an ordinate represents a vehicle speed.
Example 2
The embodiment of the invention provides a non-signalized intersection vehicle behavior analysis system which comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the non-signalized intersection vehicle behavior analysis method is realized according to the embodiment 1.
Example 3
An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the non-signalized intersection vehicle behavior analysis method according to embodiment 1.
The invention discloses a non-signalized intersection vehicle behavior analysis method, a system and a computer readable storage medium.A series of vehicle distance-speed tracks are obtained according to the distance between a vehicle and a stop line and the corresponding vehicle instantaneous speed by obtaining the distance between the vehicle and the stop line and the corresponding vehicle instantaneous speed in a vehicle track acquisition area; acquiring the distance between any two vehicle distance-speed tracks according to a series of vehicle distance-speed tracks; according to the distance between any two vehicle distance-speed tracks, clustering all the vehicle distance-speed tracks to obtain the distance between the vehicle and a stop line and a corresponding clustering result of the vehicle instantaneous speed, and objectively, simply and conveniently obtaining the behavior mode of the vehicle at the non-signal control intersection through the clustering result;
according to the technical scheme, the detailed position and speed information of the driver can be provided by considering the vehicle track data, whether the vehicle decelerates or stops according to the traffic rule of the non-signalized intersection or not is determined by acquiring the vehicle track mode of the non-signalized intersection, and a basis is provided for the management of the vehicle violation behaviors of the non-signalized intersection, so that the management efficiency of the non-signalized intersection is effectively improved.
The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention. Any other corresponding changes and modifications made according to the technical idea of the present invention should be included in the protection scope of the claims of the present invention.
Claims (8)
1. A non-signalized intersection vehicle behavior analysis method is characterized by comprising the following steps:
in the vehicle track acquisition area, acquiring the distance from a vehicle to a stop line and the corresponding instantaneous speed of the vehicle, and acquiring a series of vehicle distance-speed tracks according to the distance from the vehicle to the stop line and the corresponding instantaneous speed of the vehicle, wherein the area between a first set distance from the stop line and a second set distance exceeding the stop line is used as the vehicle track acquisition area;
acquiring the distance between any two vehicle distance-speed tracks according to a series of vehicle distance-speed tracks;
clustering all the vehicle distance-speed tracks according to the distance between any two vehicle distance-speed tracks to obtain the distance between the vehicle and a stop line and a corresponding clustering result of the vehicle instantaneous speed;
the obtaining of the distance between any two vehicle distance-speed trajectories according to the series of vehicle distance-speed trajectories specifically includes: acquiring the distance between any two vehicle distances and the speed track according to a track distance calculation formula; the track distance calculation formula is
Wherein the content of the first and second substances,
2. The non-signalized intersection vehicle behavior analysis method according to claim 1, wherein the obtaining of the distance from the vehicle to the stop line specifically comprises obtaining a length of a trajectory through a trajectory length calculation formula, and obtaining the distance from the vehicle to the stop line according to the length of the trajectory, wherein the trajectory length calculation formula is L ═ L1+l2+...+li+...+ln，
Wherein liIs the distance, x, between the ith track point and the (i + 1) th track point of the trackiIs the abscissa, y, of the ith track point in the trackiIs the ordinate of the ith track point in one track, and L is the length of the track.
3. The non-signalized intersection vehicle behavior analysis method according to claim 1, wherein obtaining the corresponding vehicle instantaneous speed specifically comprises obtaining a distance vector of each frame of motion of the vehicle and a frame rate of an observation video, and using a formula
Acquiring a corresponding vehicle instantaneous speed, wherein V is the corresponding vehicle instantaneous speed,
a distance vector for each frame of motion of the vehicle, and f is a frame rate of the observation video.
4. The non-signalized intersection vehicle behavior analysis method according to claim 1, wherein all vehicle distance-speed tracks are clustered according to the distance between any two vehicle distance-speed tracks, and specifically the method comprises the steps of determining a clustering radius and the number of neighborhood objects, determining whether the corresponding vehicle distance-speed tracks are placed in the same cluster according to the size relationship between the distance between any two vehicle distance-speed tracks and the clustering radius, and determining whether the tracks in the cluster are clustering results according to the size relationship between the number of clusters and the number of neighborhood objects.
5. The non-signalized intersection vehicle behavior analysis method according to claim 4, wherein whether the corresponding vehicle distance-speed tracks are placed in the same cluster is determined according to the magnitude relation between the distance between any two vehicle distance-speed tracks and the clustering radius, and specifically, the method comprises the step of placing the two vehicle distance-speed tracks in the same cluster if the distance between the two vehicle distance-speed tracks is smaller than the clustering radius, and otherwise, not placing the two vehicle distance-speed tracks in the same cluster.
6. The non-signalized intersection vehicle behavior analysis method according to claim 5, wherein whether the tracks in the cluster are clustering results is determined according to the size relationship between the number of the tracks in the cluster and the number of the neighborhood objects, and specifically includes determining the tracks in the cluster to be clustering results if the number of the tracks in the cluster is greater than the number of the neighborhood objects, and discarding the tracks of the cluster otherwise.
7. A non-signalized intersection vehicle behavior analysis system comprising a processor and a memory, the memory having stored thereon a computer program that, when executed by the processor, implements a non-signalized intersection vehicle behavior analysis method according to any one of claims 1 to 6.
8. A computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements a non-signalized intersection vehicle behavior analysis method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010723673.5A CN111968365B (en) | 2020-07-24 | 2020-07-24 | Non-signalized intersection vehicle behavior analysis method and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010723673.5A CN111968365B (en) | 2020-07-24 | 2020-07-24 | Non-signalized intersection vehicle behavior analysis method and system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111968365A CN111968365A (en) | 2020-11-20 |
| CN111968365B true CN111968365B (en) | 2022-02-15 |
Family
ID=73362547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010723673.5A Active CN111968365B (en) | 2020-07-24 | 2020-07-24 | Non-signalized intersection vehicle behavior analysis method and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111968365B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103377555A (en) * | 2012-04-25 | 2013-10-30 | 施乐公司 | Method and system for automatically detecting anomalies at a traffic intersection |
| CN103902655A (en) * | 2014-02-28 | 2014-07-02 | 小米科技有限责任公司 | Clustering method and device and terminal device |
| CN105225541A (en) * | 2015-10-29 | 2016-01-06 | 中国民航大学 | Based on the method for Trajectory Prediction in short-term that blank pipe historical data is excavated |
| CN106394559A (en) * | 2016-11-17 | 2017-02-15 | 吉林大学 | Multi-target driving behavior evaluation analytical method based on environmental perception information |
| CN107585164A (en) * | 2017-09-04 | 2018-01-16 | 交通运输部公路科学研究所 | A kind of method and device for the driver that classifies |
| CN108091133A (en) * | 2017-11-27 | 2018-05-29 | 银江股份有限公司 | A kind of safe driving of vehicle behavior analysis method based on huge traffic data analysis |
| CN108764111A (en) * | 2018-05-23 | 2018-11-06 | 长安大学 | A kind of detection method of vehicle abnormality driving behavior |
| CN109087534A (en) * | 2018-10-09 | 2018-12-25 | 王业宝 | A kind of traffic conflict detection method based on vehicle driving trace |
| CN109345020A (en) * | 2018-10-02 | 2019-02-15 | 北京航空航天大学 | A kind of unsignalized intersection vehicle drive behavior prediction model under Complete Information |
| CN110164130A (en) * | 2019-04-29 | 2019-08-23 | 北京北大千方科技有限公司 | Traffic incidents detection method, apparatus, equipment and storage medium |
| CN110458589A (en) * | 2019-02-01 | 2019-11-15 | 吉林大学 | Trackside formula taxi bus stop addressing preferred method based on track big data |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002163750A (en) * | 2000-11-27 | 2002-06-07 | Katsuya Matsunaga | Managing apparatus for measuring driving behavior |
| JP5499277B2 (en) * | 2008-01-22 | 2014-05-21 | 株式会社国際電気通信基礎技術研究所 | Dangerous driving prevention awareness judgment system and dangerous driving prevention awareness judgment method |
| JP5585229B2 (en) * | 2010-06-16 | 2014-09-10 | 富士通株式会社 | Vehicle behavior estimation apparatus, program, and method |
| US10018703B2 (en) * | 2012-09-13 | 2018-07-10 | Conduent Business Services, Llc | Method for stop sign law enforcement using motion vectors in video streams |
| CN105023428B (en) * | 2014-04-15 | 2017-09-29 | 高德软件有限公司 | Traffic information appraisal procedure and device |
| CN105740904B (en) * | 2016-01-29 | 2019-10-11 | 东南大学 | A kind of trip based on DBSCAN clustering algorithm and activity pattern recognition methods |
| US20170344855A1 (en) * | 2016-05-24 | 2017-11-30 | Agt International Gmbh | Method of predicting traffic collisions and system thereof |
| US10392022B1 (en) * | 2018-02-28 | 2019-08-27 | Calamp Corp. | Systems and methods for driver scoring with machine learning |
| US11194331B2 (en) * | 2018-10-30 | 2021-12-07 | The Regents Of The University Of Michigan | Unsupervised classification of encountering scenarios using connected vehicle datasets |
| CN109544914B (en) * | 2018-11-09 | 2021-08-03 | 西南交通大学 | Shared bicycle reverse behavior identification method based on historical GPS track |
| CN110135450B (en) * | 2019-03-26 | 2020-06-23 | 中电莱斯信息系统有限公司 | Hot spot path analysis method based on density clustering |
| CN110728842B (en) * | 2019-10-23 | 2021-10-08 | 江苏智通交通科技有限公司 | Abnormal driving early warning method based on reasonable driving range of vehicles at intersection |
| CN110570658B (en) * | 2019-10-23 | 2022-02-01 | 江苏智通交通科技有限公司 | Method for identifying and analyzing abnormal vehicle track at intersection based on hierarchical clustering |
-
2020
- 2020-07-24 CN CN202010723673.5A patent/CN111968365B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103377555A (en) * | 2012-04-25 | 2013-10-30 | 施乐公司 | Method and system for automatically detecting anomalies at a traffic intersection |
| CN103902655A (en) * | 2014-02-28 | 2014-07-02 | 小米科技有限责任公司 | Clustering method and device and terminal device |
| CN105225541A (en) * | 2015-10-29 | 2016-01-06 | 中国民航大学 | Based on the method for Trajectory Prediction in short-term that blank pipe historical data is excavated |
| CN106394559A (en) * | 2016-11-17 | 2017-02-15 | 吉林大学 | Multi-target driving behavior evaluation analytical method based on environmental perception information |
| CN107585164A (en) * | 2017-09-04 | 2018-01-16 | 交通运输部公路科学研究所 | A kind of method and device for the driver that classifies |
| CN108091133A (en) * | 2017-11-27 | 2018-05-29 | 银江股份有限公司 | A kind of safe driving of vehicle behavior analysis method based on huge traffic data analysis |
| CN108764111A (en) * | 2018-05-23 | 2018-11-06 | 长安大学 | A kind of detection method of vehicle abnormality driving behavior |
| CN109345020A (en) * | 2018-10-02 | 2019-02-15 | 北京航空航天大学 | A kind of unsignalized intersection vehicle drive behavior prediction model under Complete Information |
| CN109087534A (en) * | 2018-10-09 | 2018-12-25 | 王业宝 | A kind of traffic conflict detection method based on vehicle driving trace |
| CN110458589A (en) * | 2019-02-01 | 2019-11-15 | 吉林大学 | Trackside formula taxi bus stop addressing preferred method based on track big data |
| CN110164130A (en) * | 2019-04-29 | 2019-08-23 | 北京北大千方科技有限公司 | Traffic incidents detection method, apparatus, equipment and storage medium |
Non-Patent Citations (6)
| Title |
|---|
| "Live Stop-Controlled Intersection Data Collection";ZACHARY R. DOERZAP等;《Virginia Transportation Research Council》;20071231;第1-82页 * |
| "ST-DBSCAN: An algorithm for clustering spatial–temporal data";Derya Birant等;《Elsevier》;20071231;第208-221页 * |
| "Trajectory Clustering Aided Personalized Driver Intention Prediction for Intelligent Vehicles";Dewei Yi等;《IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS》;20190630;第15卷(第6期);第3693-3702页 * |
| "基于视频跟踪和FSA的车辆行为模式分析";岳恒军等;《计算机工程》;20120131;第38卷(第1期);第160-162页 * |
| "无信号控制公路平面交叉口支路左转驾驶行为研究";郑元;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20170215;C034-1289 * |
| "面向交叉口冲突分析的车辆轨迹学习技术";尹卓;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20200315;C034-993 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111968365A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829403B (en) | Vehicle anti-collision early warning method and system based on deep learning | |
| CN107492251B (en) | Driver identity recognition and driving state monitoring method based on machine learning and deep learning | |
| Ma et al. | Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry | |
| Morris et al. | Real-time video-based traffic measurement and visualization system for energy/emissions | |
| CN111862606B (en) | Illegal operating vehicle identification method based on multi-source data | |
| CN111860274A (en) | Traffic police command gesture recognition method based on head orientation and upper half body skeleton characteristics | |
| CN111931683B (en) | Image recognition method, device and computer readable storage medium | |
| CN113635897B (en) | Safe driving early warning method based on risk field | |
| CN115035491A (en) | Driving behavior road condition early warning method based on federal learning | |
| CN108573600A (en) | A kind of induction of driving behavior and the flow-optimized method of local traffic | |
| CN112927511A (en) | Vehicle early warning method based on driver age and gender identification | |
| Zardosht et al. | Identifying driver behavior in preturning maneuvers using in-vehicle CANbus signals | |
| Mammeri et al. | Design of a semi-supervised learning strategy based on convolutional neural network for vehicle maneuver classification | |
| Van Hinsbergh et al. | Vehicle point of interest detection using in-car data | |
| Scora et al. | Real-time roadway emissions estimation using visual traffic measurements | |
| CN111968365B (en) | Non-signalized intersection vehicle behavior analysis method and system and storage medium | |
| Yarlagadda et al. | Heterogeneity in the driver behavior: an exploratory study using real-time driving data | |
| CN116092037B (en) | Vehicle type identification method integrating track space-semantic features | |
| CN116955943A (en) | Driving distraction state identification method based on eye movement sequence space-time semantic feature analysis | |
| CN110555425A (en) | Video stream real-time pedestrian detection method | |
| CN113284338B (en) | Method for calculating influence of motor vehicle emergency avoidance no-lamp control pedestrian crossing on traffic flow | |
| CN114973211A (en) | Object identification method, device, equipment and storage medium | |
| Grigoropoulos et al. | Detection and Classification of Bicyclist Group Behavior for Automated Vehicle Applications | |
| CN114091581A (en) | Vehicle operation behavior type identification method based on sparse track | |
| CN113147781A (en) | Intelligent driving information display system for automobile |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |