CN114155715A - Conflict point detection method, device, equipment and readable storage medium - Google Patents

Conflict point detection method, device, equipment and readable storage medium Download PDF

Info

Publication number
CN114155715A
CN114155715A CN202210115476.4A CN202210115476A CN114155715A CN 114155715 A CN114155715 A CN 114155715A CN 202210115476 A CN202210115476 A CN 202210115476A CN 114155715 A CN114155715 A CN 114155715A
Authority
CN
China
Prior art keywords
vehicle
conflict
target vehicle
determining
point detection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210115476.4A
Other languages
Chinese (zh)
Other versions
CN114155715B (en
Inventor
韩珂
侯鲁杰
邓量
李俊彪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Mapabc Technology Co Ltd
Original Assignee
Beijing Mapabc Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Mapabc Technology Co Ltd filed Critical Beijing Mapabc Technology Co Ltd
Priority to CN202210115476.4A priority Critical patent/CN114155715B/en
Publication of CN114155715A publication Critical patent/CN114155715A/en
Application granted granted Critical
Publication of CN114155715B publication Critical patent/CN114155715B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions

Landscapes

  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a conflict point detection method, which is used for monitoring a real-time track of a vehicle, determining whether other vehicles exist in a conflict area of the vehicle or not after monitoring that the vehicle stops in an intersection area, and judging that the vehicle is a parking event caused by the track conflict of other vehicles if the vehicle stops in the conflict area. According to the method, the phenomenon that one vehicle stops due to the fact that two running vehicles collide is detected according to the actual running track, and the actually detected conflict point is the traffic conflict event which actually occurs, so that errors caused by the fact that two vehicles which are originally judged to have the conflict point mutually avoid the situation of normally passing through the intersection and the like can be avoided, the conflict point detection accuracy is remarkably improved, and the requirement for high-precision road network planning can be met. The invention also discloses a conflict point detection device, equipment and a readable storage medium, and has corresponding technical effects.

Description

Conflict point detection method, device, equipment and readable storage medium
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a conflict point detection method, a conflict point detection device, conflict point detection equipment and a readable storage medium.
Background
With the economic development and the growth of population, the automobile holding capacity is larger and the traffic pressure is increased. Traffic management becomes a great challenge, and conflict point detection belongs to an important factor in traffic management.
The conflict point is also called as traffic conflict, and is characterized in that under the condition of observability, two or more road users approach each other at the same time and space, if one of the road users takes abnormal traffic behaviors, such as direction conversion, speed change, sudden stop and the like, and unless the other road user also takes danger avoiding behaviors correspondingly, collision can occur. Therefore, the detection aiming at the conflict points can provide the truest information for traffic management and traffic organization optimization, and the traffic police can adjust and optimize the intersection organization and signal lamp scheme aiming at the conflict and multiple points, so that the traffic efficiency can be improved, the occurrence probability of accidents and the occurrence probability of congestion can be effectively reduced, and the traffic police has profound significance for traffic management.
In the current conflict point detection, the vehicle track is predicted according to vehicle running parameters such as the vehicle position, the running speed and the running angle, and then the conflict point is predicted according to the predicted vehicle track. However, in practical application, the method has limited detection accuracy, is difficult to meet the requirement of high-precision road network planning, and cannot realize effective intersection organization optimization.
In summary, how to improve the accuracy of detecting the overshoot point is a technical problem that needs to be solved urgently by those skilled in the art.
Disclosure of Invention
The invention aims to provide a conflict point detection method, a conflict point detection device, conflict point detection equipment and a readable storage medium, so that the conflict point detection accuracy is improved.
In order to solve the technical problems, the invention provides the following technical scheme:
a method of conflict point detection, comprising:
determining a target vehicle for carrying out conflict point detection, and taking a vehicle from a different road entrance with the target vehicle as a reference vehicle;
judging whether the target vehicle stops in the intersection area or not;
if the vehicle is parked, determining the driving direction of the target vehicle before parking;
defining a driving obstructing area in the head direction of the target vehicle according to the driving direction, and taking the driving obstructing area as a conflict area;
judging whether the reference vehicle with the running speed reaching a normal running threshold exists in the conflict area;
and if so, judging that the conflict point exists.
Optionally, the determining the driving direction of the target vehicle before stopping comprises:
extracting the last two frames, namely a T-1 frame and a T frame, of the target vehicle with the speed larger than a threshold value before parking;
determining the position connecting line direction pointing to the T frame from the T-1 frame as a contrast direction;
and taking the comparison direction as the driving direction.
Optionally, before the step of taking the comparison direction as the driving direction, the method further comprises:
reading a position connecting line direction determined according to a T-2 frame and the T-1 frame in historical data to serve as a reference direction;
calculating a direction difference between the comparison direction and the reference direction, and judging whether the direction difference is greater than a threshold value;
if yes, taking the T-1 frame as the T frame, taking the T-2 frame as the T-1 frame, and executing the step of determining the position connecting line direction pointing to the T frame from the T-1 frame;
and if not, executing the step of taking the comparison direction as the driving direction.
Optionally, before the determining whether the target vehicle is parked in the intersection region, the method further includes:
calculating whether a trend of running track conflict exists between the target vehicle and each reference vehicle;
and if so, executing the step of judging whether the target vehicle stops in the intersection area.
Optionally, before the determining the driving direction of the target vehicle before stopping, further comprising:
judging whether the parking area of the target vehicle belongs to a to-be-transferred area or not;
if yes, judging that no conflict point exists, and enabling the target vehicle to be normally parked;
and if not, executing the step of determining the driving direction of the target vehicle before the vehicle stops.
Optionally, after the determining that the conflict point exists, further comprising:
determining conflict vehicles and conflict point positions;
and outputting conflict point events according to the conflict vehicles and the conflict point positions.
Optionally, before the determining the target vehicle for conflict point detection, the method further includes:
performing lane matching on all vehicles in the intersection area according to the lane position information and the vehicle position information, and determining the intersection direction of each vehicle;
grouping and counting the vehicles according to the crossing direction to generate a plurality of direction groups;
accordingly, the determining a target vehicle for conflict point detection and using a vehicle from a different road entrance from the target vehicle as a reference vehicle comprises: determining a target vehicle for carrying out conflict point detection in the vehicles, and determining a direction group to which the target vehicle belongs as a target direction group; and taking the vehicle in each direction group except the target direction group as the reference vehicle.
A bump point detection device comprising:
a vehicle determination unit configured to determine a target vehicle for performing collision point detection, and to use a vehicle from a different road entrance from the target vehicle as a reference vehicle;
the parking judgment unit is used for judging whether the target vehicle parks in the intersection area or not; if the vehicle stops, triggering a direction determining unit;
the direction determining unit is used for determining the running direction of the target vehicle before the target vehicle stops;
the region dividing unit is used for dividing a region for hindering the driving in the direction of the head of the target vehicle according to the driving direction and taking the region as a conflict region;
a collision determination unit configured to determine whether there is the reference vehicle whose travel speed reaches a normal travel threshold in the collision area; if yes, triggering a conflict judgment unit;
and the conflict judging unit is used for judging that the conflict point exists.
A computer device, comprising:
a memory for storing a computer program;
and the processor is used for realizing the steps of the conflict point detection method when executing the computer program.
A readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the above-mentioned conflict point detection method.
The method provided by the embodiment of the invention monitors the real-time track of the vehicle, determines whether other vehicles exist in the collision area of the vehicle after the vehicle is monitored to stop in the intersection area, and can judge that the vehicle is a parking event caused by the track collision of other vehicles if the vehicle exists. According to the method, the phenomenon that one vehicle stops due to the fact that two running vehicles collide is detected according to the actual running track, and the actually detected conflict point is the traffic conflict event which actually occurs, so that errors caused by the fact that two vehicles which are originally judged to have the conflict point mutually avoid the situation of normally passing through the intersection and the like can be avoided, the conflict point detection accuracy is remarkably improved, and the requirement for high-precision road network planning can be met.
Accordingly, embodiments of the present invention further provide a conflict point detection apparatus, a device and a readable storage medium corresponding to the conflict point detection method, which have the above technical effects and are not described herein again.
Drawings
In order to more clearly illustrate the embodiments of the present invention or technical solutions in related arts, the drawings used in the description of the embodiments or related arts will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating an embodiment of a method for detecting a collision point according to the present invention;
FIG. 2 is a schematic diagram of an intersection area according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a traffic conflict in an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a conflict point detection apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The core of the invention is to provide a conflict point detection method which has high identification accuracy.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The conflict point is also called as traffic conflict, and is characterized in that under the condition of observability, two or more road users approach each other at the same time and space, if one of the road users takes abnormal traffic behaviors, such as direction conversion, speed change, sudden stop and the like, the collision can occur unless the other road user also takes danger avoiding behaviors correspondingly.
Traffic conflicts can be expressed as the result of the spatial movement of a traffic participant interacting with other participants or transportation facilities. In a sense, the traffic accident belongs to the category of traffic conflict, the cause and the occurrence process of the traffic accident and the traffic conflict are completely similar, and the only difference between the two is whether the damage consequence exists or not. In other words, a traffic accident is a traffic accident, or a traffic conflict, in which casualties or vehicle loss occurs. Traffic conflicts can also be expressed as traffic encounters where a traffic actor apparently feels an accident hazard and takes an active corresponding risk avoidance action. The traffic conflict technology is a technology for quantitatively measuring and judging the occurrence process and the severity of traffic conflicts according to a certain measuring method and a certain judging standard, and is a traffic safety evaluation method of non-accident statistics.
The applicant finds that the current conflict point detection is carried out conflict point prediction according to a predicted vehicle track, but due to the fact that the prediction of the vehicle track has errors and other factors, the conflict point detection method is low in detection accuracy, and two vehicles which are originally judged to have the conflict points can avoid passing through the intersection normally.
Based on this, the present application provides a method for detecting a conflict point, which can avoid a prediction error, specifically referring to fig. 1, where fig. 1 is a flowchart of a method for detecting a conflict point in an embodiment of the present invention, the method including the following steps:
s101, determining a target vehicle for carrying out conflict point detection, and taking a vehicle from a different road entrance with the target vehicle as a reference vehicle;
the target vehicle is an object for performing the collision point detection. The target vehicle can be any vehicle in the monitoring area, and the target vehicle can be specified according to the actual detection requirement.
The reference vehicle is a vehicle that performs conflict point detection with the target vehicle. Since the collision generally occurs between two vehicles in different driving directions, in this embodiment, all vehicles in the monitoring area from different road entrances with the target vehicle are used as reference vehicles to detect the collision points, where the different road entrances refer to different lane directions, for example, a left-turn lane and a straight lane belong to different road entrances. Of course, if the conflict point between two vehicles is detected, a vehicle may also be designated as a reference vehicle, and only the former vehicle is described as an example in this embodiment, and the implementation of the latter vehicle may also refer to the description in this embodiment, and details thereof are not described here.
S102, judging whether a target vehicle stops in an intersection area; if the vehicle is stopped, triggering S103;
after the target vehicle and the reference vehicle are determined, parking detection is performed on the target vehicle in the intersection area to detect whether the target vehicle parks in the intersection area.
For example, displacement and vehicle speed of the vehicle may be calculated according to positioning information in frame-by-frame data of the vehicle to determine whether the vehicle is parked or not, and whether the vehicle is parked or not may be determined according to driving parameters of the vehicle, such as vehicle angular speed, and the like.
The intersection area refers to an area defined by a plurality of side stop lines, taking a cross intersection as an example, a shadow area defined by the east-west stop lines and the south-north stop lines shown in fig. 2 is the intersection area, and other types of intersections such as a Y intersection or a t intersection can refer to fig. 2, and details are not repeated herein.
If the target vehicle stops in the intersection area, indicating that the target vehicle is abnormal in running, triggering step S103 to carry out further conflict point identification; if the target vehicle does not stop in the intersection region and runs until the target vehicle exits the intersection region, it may be directly determined that the vehicle is not abnormal.
S103, determining the running direction of the target vehicle before parking;
if the target vehicle stops in the intersection area, it is described that the target vehicle is abnormal in running, in this embodiment, it is necessary to determine the running direction of the target vehicle before stopping, so as to further determine whether there is a traffic obstacle according to the running direction.
Wherein the traveling direction before parking refers to a traveling direction of the vehicle within a short time interval before parking. The traveling direction before parking indicates the parking direction, and the present embodiment achieves the detection of the conflict point by determining the traveling direction of the target vehicle before parking to determine whether there is a vehicle obstructing the travel of the target vehicle in the vehicle parking direction.
The running direction of the target vehicle before parking is determined, and the running direction can be calculated in real time during running and is directly obtained after parking; the running data of the target vehicle in a preset time interval before parking can be acquired after parking for calculation; the driving direction calculated by the third-party device according to the real-time monitoring target vehicle may be directly obtained, which is not limited in this embodiment.
In addition, for the calculation manner of the driving direction, reference may be made to implementation of related technologies, for example, the driving direction of a wheel or the driving direction of a vehicle body may be calculated, and corresponding setting may be specifically performed according to actual use needs, which is not described herein again.
S104, defining a driving hindering area in the head direction of the target vehicle according to the driving direction to serve as a collision area;
in the embodiment, after the vehicle is monitored to stop, the area possibly obstructing the vehicle from running is identified, and whether other vehicles exist is judged to identify whether the traffic conflict exists.
The area where the vehicle is likely to be obstructed, that is, the advancing area of the vehicle in the original traveling direction is defined in the front direction of the target vehicle according to the traveling direction, the area where the target vehicle is likely to be obstructed is used as a collision area, and whether a vehicle which normally travels from another road entrance exists in the collision area is further judged.
The specific defining manner of the conflict area may be correspondingly set according to actual monitoring needs and data such as vehicle parameters and road parameters, which is not limited in this embodiment, for example, a sector area with the start point as a center, the two sides of the sector area as a center and the driving direction as two sides of the sector area as a radius of 5m, and the start point as a start point may be used as the conflict area. Other defining manners may also be adopted, and the other defining manners of the conflict area may refer to the description of the embodiment, which is not described herein again.
S105, judging whether a reference vehicle with the running speed reaching a normal running threshold exists in the conflict area; if yes, triggering S106;
after a conflict area of a target vehicle is defined, whether vehicles which come from different road entrances and normally run exist in the conflict area or not is judged, wherein the purpose of setting the condition of normal running is to distinguish the condition that the two vehicles stop in an intersection area with high probability as an accident, and after the conflict occurs, even if the two vehicles stop to avoid the accident, the condition that one vehicle starts to leave firstly and then the other vehicle starts to leave exists as long as the accident does not occur, so the condition that abnormal parking such as the accident and the like can be eliminated by judging whether a reference vehicle with running speed reaching a normal running threshold value exists in the conflict area to detect the conflict point, and comprehensive and accurate detection of the conflict is realized.
If there are vehicles from different road entrances and traveling normally in the conflict area, it is indicated that the vehicles from different road entrances and traveling normally obstruct normal traveling of the monitored vehicle, that is, the target vehicle stops to avoid the vehicles from different road entrances and traveling normally, and a traffic conflict occurs between the target vehicle and the vehicle, and S103 is triggered to output a conflict point event. If there is no reference vehicle whose driving speed reaches the normal driving threshold, it may be determined directly that the next target vehicle performs the detection of the conflict point without processing, and may also perform further determination of an abnormal stop or an accident.
And S106, judging that the conflict point exists.
Based on the steps, the detection of the conflict point can be realized. After the conflict point is monitored, follow-up optimization measures such as road organization optimization and the like can be further carried out according to the conflict point. For example, the severity (such as collision frequency) of the conflict point can be analyzed according to historical conflict point data, intersection canalization and organization marking lines are optimized according to the severity of the conflict, for example, a left-turn waiting area can be increased when the left-turn conflict is serious, a right-turn special lane can be set when the right-turn conflict is serious, and the turn-around is prohibited when the turn-around conflict is particularly serious; the signal scheme can be optimized according to historical conflict point data, for example, a left-turn lane single-passing signal scheme can be added to optimize channelized intersection traffic when left-turn or turn-around conflict is serious. In this embodiment, the processing procedure after the conflict point is detected is not limited, and corresponding setting may be performed according to the requirement of actual road organization optimization, which is not described herein again.
And in order to help the behaviors such as traffic organization optimization based on the conflict points, after the conflict points are judged to exist, the following steps can be further executed: determining conflict vehicles and conflict point positions; and outputting the conflict point event according to the conflict vehicle and the conflict point position. The related art can know the existence of the conflict point and also know the information of the vehicle where the conflict occurs (such as the license plate number, the type of the vehicle, etc.) and the position where the conflict point occurs (such as the xx crossing xx lane, etc.) so as to perform accurate traffic organization optimization according to the conflict information including the information of the vehicle and the conflict position, etc. In addition to the vehicle information and the conflict point position, other outputs, such as a conflict time, may be further output, and may be specifically set according to actual needs.
Based on the above description, in the technical scheme provided by the embodiment of the invention, the vehicle is monitored in real time track, if the vehicle is monitored to stop in the intersection area, whether other vehicles exist in the collision area of the vehicle is determined, and if so, it can be determined that the vehicle is a parking event caused by the track collision of other vehicles. According to the method, the phenomenon that one vehicle stops due to the fact that two running vehicles collide is detected according to the actual running track, and the actually detected conflict point is the traffic conflict event which actually occurs, so that errors caused by the fact that two vehicles which are originally judged to have the conflict point mutually avoid the situation of normally passing through the intersection and the like can be avoided, the conflict point detection accuracy is remarkably improved, and the requirement for high-precision road network planning can be met.
It should be noted that, based on the above embodiments, the embodiments of the present invention also provide corresponding improvements. In the preferred/improved embodiment, the same steps as those in the above embodiment or corresponding steps may be referred to each other, and corresponding advantageous effects may also be referred to each other, which are not described in detail in the preferred/improved embodiment herein.
The determination method of the driving direction in the above embodiment is not limited, and the embodiment provides a determination method, which can implement accurate measurement.
Specifically, determining the traveling direction of the target vehicle before stopping includes the steps of:
(1) extracting the last two frames, namely a T-1 frame and a T frame, of the target vehicle with the speed larger than a threshold value before parking;
in order to avoid calculation errors caused by poor position monitoring accuracy before parking, the method provides that the last two frames of the target vehicle with the speed greater than the threshold value before parking are extracted for calculating the driving direction, wherein the last frame is the T-th frame, and the frame before the T-th frame is the T-1 frame.
The specific data set for the threshold value is not limited, and may be set according to the minimum speed of travel, i.e., the vehicle is still in a traveling state with a speed greater than the threshold value, and the traveling direction of the vehicle corresponds to the change in the vehicle body position, so that the traveling direction of the vehicle before the vehicle stops can be estimated from the change in the vehicle body position. However, if there is an interference factor such as poor definition of the last two frames of the target vehicle whose speed is greater than the threshold before the vehicle stops, the time interval between the extracted images may be short, although the extraction is not limited to the extraction of two consecutive frames of images. Of course, the image frame may not be limited to be extracted according to the driving speed, which is not limited in this embodiment, and two consecutive image frames may be extracted according to actual situations.
It should be noted that the extracted two consecutive frame positions need to be as close as possible to the parking time to accurately reflect the driving direction during parking.
(2) Determining the position connecting line direction pointing to the T frame from the T-1 frame as a contrast direction;
the position of the previous frame (i.e. the T-1 frame) points to the connection line direction of the position of the next frame (i.e. the T frame), i.e. the direction in which the vehicle actually runs, and may also be referred to as the wheel direction, and the wheel direction is calculated as the running direction.
(3) The comparison direction is taken as the driving direction.
According to the method, the driving direction acquired by the third-party equipment is not directly acquired, calculation is directly performed according to the image acquired by monitoring, so that the problem that the calculation accuracy of the third-party equipment is difficult to guarantee as uncertain factors brought by conflict point detection is avoided, and meanwhile, the wheel direction is calculated as the driving direction under the method, so that the detection of the driving direction can be more accurately realized compared with the method that the vehicle body direction is taken as the driving direction.
On the basis of the above steps, to further avoid disturbance interference and ensure the accuracy of the driving direction calculation, before the comparison direction is taken as the driving direction, the following steps may be performed:
(4) reading a position connecting line direction determined according to the T-2 frame and the T-1 frame in the historical data as a reference direction;
in order to avoid the disturbance error, the embodiment further proposes to constrain the currently calculated driving direction according to the reference direction, and if the difference between the two directions is too large, abandon the currently calculated comparison direction and re-determine the driving direction; if the direction difference is small, it is judged that no disturbance error occurs in the currently calculated driving direction, and the currently calculated contrast direction can be directly used as the driving direction for output.
Determination of reference direction in this embodiment, a direction of a connection line between positions determined according to the T-2 frame and the T-1 frame in the read history data is provided as a reference direction.
By comparing two determined directions of three continuous frames, the time difference between the historical direction and the current driving direction can be reduced as much as possible, so that the difficulty in determining the direction caused by long time is avoided, and the constraint of the historical direction on the current driving direction is weak. Of course, the travel direction determined at another time may be acquired as the historical direction, but it is necessary to ensure that the time difference between the acquired another time and the calculation of the current travel direction key is as small as possible.
(5) Calculating a direction difference between the comparison direction and the reference direction, and judging whether the direction difference is greater than a threshold value; if yes, triggering (6); if not, triggering (3);
the value setting of the threshold is not limited in this embodiment, and may be set according to an actual application scenario, which is not described herein again.
(6) And (2) taking the T-1 frame as a T frame, extracting a T-2 frame as a T-1 frame, and triggering.
If the direction difference is greater than the threshold, it indicates that the error of the position connecting line direction determined according to the T frame and the T-1 frame is larger, in this embodiment, go forward, go through, discard the position connecting line direction determined according to the T frame and the T-1 frame, continue to forward determine whether the position connecting line direction determined according to the T-2 frame and the T-1 frame and the position connecting line direction determined according to the T-3 frame and the T-2 frame are greater than the threshold, if the position connection direction is larger than the threshold value, continuously judging whether the position connection direction determined according to the T-3 frame and the T-2 frame and the position connection direction determined according to the T-4 frame and the T-3 frame are larger than the threshold value, and repeating the steps until three frames with the direction difference not larger than the threshold value are found, and taking the position connecting line direction determined by the two frames as the driving direction.
According to the method, the current driving direction is subjected to calculation constraint through the historical direction, so that disturbance calculation interference can be avoided, and the accuracy of driving direction calculation is improved. Of course, other driving direction calculation methods may be used, and are not limited herein.
Based on the above embodiment, when comprehensively monitoring the road vehicles, it is necessary to perform the calculation of collision point detection by using all vehicles on the road as target vehicles, and in order to reduce the calculation amount in the comprehensive monitoring, the present embodiment proposes that before determining whether the target vehicle stops in the intersection area, the following steps may be further performed: calculating whether a trend of running track conflict exists between the target vehicle and each reference vehicle; if so, re-triggering S102.
Specifically, the trend of calculating whether the travel track conflict exists between the target vehicle and each reference vehicle means that whether the track conflict exists in the future of the current vehicle is predicted based on the current travel data according to a ranging collision algorithm, and if the track conflict exists, the trend of determining that the travel track conflict exists is determined. The selection of the specific ranging collision algorithm is not limited in this embodiment, and the implementation of the related art may be referred to.
If the conflict point does not exist, the current target vehicle can be directly used as the vehicle without the traffic conflict, and then other target vehicles are switched to detect the conflict point. This is not limited in this embodiment, and corresponding setting may be performed according to actual use requirements, which is not described herein again.
According to the method provided by the embodiment, before conflict point detection is carried out on the vehicle, conflict prediction is carried out on the vehicle, if conflict exists in prediction, the method provided by the embodiment is executed to carry out accurate conflict point detection, and if conflict does not exist in prediction, conflict point detection is not needed.
On the basis of the above embodiment, to further improve the accuracy of the collision point detection and avoid false detection, before determining the driving direction of the target vehicle before stopping in S103, the following steps may be further performed: judging whether the parking area of the target vehicle belongs to a to-be-transferred area or not; if yes, judging that no conflict point exists, and enabling the target vehicle to be normally parked. If not, executing the step of determining the running direction of the target vehicle before the vehicle stops.
In the method, after a vehicle is detected to stop in an intersection area, whether a stopping place belongs to a waiting area is further judged, for example, a left-turn waiting area, a right-turn waiting area, a straight-going waiting area and the like in the intersection area are detected, and the vehicle stopping in the waiting area belongs to a normal stopping condition according to a traffic signal lamp; and if the parking area is not the waiting area, continuing the subsequent conflict point detection step.
Therefore, the method eliminates the condition that the vehicle normally stops at the intersection, can reduce the detection calculation amount, and can improve the detection accuracy. The above arrangement is not required, and the present invention is not limited thereto.
On the basis of the above embodiment, to simplify the determination of the target vehicle and the reference vehicle, before determining the target vehicle for the collision point detection in S101, the following steps may be performed first:
a. performing lane matching on all vehicles in the intersection area according to the lane position information and the vehicle position information, and determining the intersection direction of each vehicle;
in the step, the lanes where all vehicles travel in the intersection area are counted, a matching relation between the lanes and the vehicles is generated, each lane (straight lane and left-turning lane) has a corresponding intersection direction (the intersection direction describes, for example, a straight first intersection of the xx intersection from west to east, or a corresponding intersection number replaces, for example, 01), and after the lane to which the vehicle belongs is determined, the intersection direction corresponding to the lane can be matched.
Because the difficulty of directly confirming the road entrance where the vehicle runs is higher for realizing the technical requirement, in order to simplify the realization, the method expands the relation between the vehicle and the road entrance into the direction of the vehicle → the lane → the road entrance, wherein the realization mode is simpler no matter whether the lane to which the vehicle belongs is determined or the intersection direction of the lane is determined, thereby simplifying the realization mode of the intersection direction in which the vehicle enters, reducing the realization difficulty and correspondingly reducing the realization cost.
b. And carrying out grouping statistics on the vehicles according to the crossing direction to generate a plurality of direction groups.
In order to conveniently extract data, the vehicles are grouped and counted according to the crossing direction in the method, so that after the target vehicle is determined, the crossing directions of all other vehicles do not need to be determined one by one, and only the vehicles which belong to different groups from the target vehicle are extracted as reference vehicles. Accordingly, under the above setting, the step of S101 determining a target vehicle for performing the collision point detection, and using a vehicle from a different road entrance from the target vehicle as a reference vehicle is specifically: determining a target vehicle for carrying out conflict point detection in the vehicles, and determining a direction group to which the target vehicle belongs as a target direction group; the vehicles in each direction group other than the target direction group are taken as reference vehicles.
It should be noted that, in order to further facilitate the determination of the parking state of the vehicle, the vehicles in the groups in different directions may be further grouped according to the normal running vehicle and the parked vehicle, which of course may not be provided, and is not limited herein.
According to the method provided by the embodiment, the vehicles entering from different entrances are grouped according to the entering direction of the intersection according to the lane information and the vehicle speed which are matched with each other at high precision, so that the determining modes of the target vehicle and the reference vehicle can be simplified, and the conflict point detection efficiency is improved.
Based on the foregoing embodiments, in order to deepen understanding of the foregoing method embodiments, in this embodiment, an overall implementation flow of the overshoot point detection is described, which specifically includes the following steps:
1. receiving real-time track data of a vehicle;
2. matching the real-time track data of the vehicle into map data;
3. judging whether the vehicle is in the intersection area, if so, carrying out the next step, otherwise, not carrying out processing;
4. judging whether the vehicle is in the zone to be transferred, if so, not processing, otherwise, entering the next step to eliminate the vehicle normally parked in the intersection zone;
5. according to the lane information in the map data and the position and speed data in the real-time track data of the vehicles, grouping the vehicles entering from different entrances according to the direction of the entering intersection, and then grouping the vehicles in the groups in different directions again according to the normal running vehicles and the stopped vehicles;
6. detecting whether the vehicles have the Collision tendency (predicting whether the vehicle tracks are intersected) by using TTC (Time-To-Collision algorithm); if yes, executing the next step; if not, the following flow is not continued, and the conflict point detection for the next vehicle is skipped.
7. Tracking each stopped vehicle (such as a stopped vehicle in the left-to-right direction shown in fig. 3), monitoring whether vehicles which normally run in other direction groups exist in a sector area (such as the sector area in front of the stopped vehicle in fig. 3) within the range of 5 meters at the left and right sides of the extension line of the running direction of the vehicle at 60 degrees respectively, if so, indicating that the vehicles which normally run in other direction groups obstruct the normal running of the current monitored vehicle (such as the vehicles which run in other directions from north to south in fig. 3), and outputting a conflict point event; if not, no treatment is carried out.
Based on the above, the conflict point detection scheme for the vehicle is completed, and the conflict point detection can be performed for each vehicle to be detected according to the steps. The method can provide the most real information for traffic management and traffic organization optimization. The traffic police can adjust and optimize the scheme of the intersection organization and the signal lamp aiming at the conflict and multiple points, thereby not only improving the vehicle passing efficiency, but also effectively reducing the occurrence probability of accidents and the occurrence probability of congestion.
Other implementation manners based on the present application can refer to the description of the embodiment, and are not described herein again.
Corresponding to the above method embodiments, the embodiments of the present invention further provide a conflict point detection apparatus, and the conflict point detection apparatus described below and the conflict point detection method described above may be referred to in correspondence.
Referring to fig. 4, the apparatus includes the following modules:
the vehicle determination unit 110 is mainly configured to determine a target vehicle for performing conflict point detection, and use a vehicle from a different road entrance from the target vehicle as a reference vehicle;
the parking determination unit 120 is mainly used for determining whether the target vehicle is parked in the intersection region; if the vehicle is parked, the direction determining unit 130 is triggered;
the direction determination unit 130 is mainly used to determine the traveling direction of the target vehicle before the parking;
the area dividing unit 140 is mainly configured to divide an area hindering driving in the direction of the head of the target vehicle according to the driving direction, and use the area as a collision area;
the collision determination unit 150 is mainly used for determining whether there is a reference vehicle whose travel speed reaches a normal travel threshold value in the collision area; if yes, triggering the conflict determination unit 160;
the collision determination unit 160 is mainly used to determine that a conflict point exists.
Corresponding to the above method embodiment, an embodiment of the present invention further provides a computer device, and a computer device described below and a conflict point detection method described above may be referred to in correspondence.
The computer device includes:
a memory for storing a computer program;
a processor for implementing the steps of the conflict point detection method of the above method embodiments when executing the computer program.
Specifically, referring to fig. 5, a specific structural diagram of a computer device provided in this embodiment is a schematic diagram, where the computer device may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 322 (e.g., one or more processors) and a memory 332, where the memory 332 stores one or more computer applications 342 or data 344. Memory 332 may be, among other things, transient or persistent storage. The program stored in memory 332 may include one or more modules (not shown), each of which may include a sequence of instructions operating on a data processing device. Still further, the central processor 322 may be configured to communicate with the memory 332 to execute a series of instruction operations in the memory 332 on the computer device 301.
The computer device 301 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input-output interfaces 358, and/or one or more operating systems 341.
The steps in the above described conflict point detection method may be implemented by the structure of a computer device.
Corresponding to the above method embodiment, the embodiment of the present invention further provides a readable storage medium, and a readable storage medium described below and a conflict point detection method described above may be referred to in correspondence.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the conflict point detection method of the above-mentioned method embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

Claims (10)

1. A method for detecting a collision point, comprising:
determining a target vehicle for carrying out conflict point detection, and taking a vehicle from a different road entrance with the target vehicle as a reference vehicle;
judging whether the target vehicle stops in the intersection area or not;
if the vehicle is parked, determining the driving direction of the target vehicle before parking;
defining a driving obstructing area in the head direction of the target vehicle according to the driving direction, and taking the driving obstructing area as a conflict area;
judging whether the reference vehicle with the running speed reaching a normal running threshold exists in the conflict area;
and if so, judging that the conflict point exists.
2. The conflict point detection method according to claim 1, wherein the determining a driving direction of the target vehicle before stopping comprises:
extracting the last two frames, namely a T-1 frame and a T frame, of the target vehicle with the speed larger than a threshold value before parking;
determining the position connecting line direction pointing to the T frame from the T-1 frame as a contrast direction;
and taking the comparison direction as the driving direction.
3. The conflict point detection method according to claim 2, further comprising, before the setting the comparison direction as the traveling direction:
reading a position connecting line direction determined according to a T-2 frame and the T-1 frame in historical data to serve as a reference direction;
calculating a direction difference between the comparison direction and the reference direction, and judging whether the direction difference is greater than a threshold value;
if yes, taking the T-1 frame as the T frame, taking the T-2 frame as the T-1 frame, and executing the step of determining the position connecting line direction pointing to the T frame from the T-1 frame;
and if not, executing the step of taking the comparison direction as the driving direction.
4. The conflict point detection method according to claim 1, further comprising, before the determining whether the target vehicle is parked within the intersection region:
calculating whether a trend of running track conflict exists between the target vehicle and each reference vehicle;
and if so, executing the step of judging whether the target vehicle stops in the intersection area.
5. The conflict point detection method according to claim 1, wherein before the determining the traveling direction of the target vehicle before stopping, further comprising:
judging whether the parking area of the target vehicle belongs to a to-be-transferred area or not;
if yes, judging that no conflict point exists, and enabling the target vehicle to be normally parked;
and if not, executing the step of determining the driving direction of the target vehicle before the vehicle stops.
6. The method according to claim 1, further comprising, after said determining that there is a conflict point:
determining conflict vehicles and conflict point positions;
and outputting conflict point events according to the conflict vehicles and the conflict point positions.
7. The conflict point detection method according to any one of claims 1 to 6, further comprising, before the determining the target vehicle for conflict point detection:
performing lane matching on all vehicles in the intersection area according to the lane position information and the vehicle position information, and determining the intersection direction of each vehicle;
grouping and counting the vehicles according to the crossing direction to generate a plurality of direction groups;
accordingly, the determining a target vehicle for conflict point detection and using a vehicle from a different road entrance from the target vehicle as a reference vehicle comprises: determining a target vehicle for carrying out conflict point detection in the vehicles, and determining a direction group to which the target vehicle belongs as a target direction group; and taking the vehicle in each direction group except the target direction group as the reference vehicle.
8. A bump point detection device, comprising:
a vehicle determination unit configured to determine a target vehicle for performing collision point detection, and to use a vehicle from a different road entrance from the target vehicle as a reference vehicle;
the parking judgment unit is used for judging whether the target vehicle parks in the intersection area or not; if the vehicle stops, triggering a direction determining unit;
the direction determining unit is used for determining the running direction of the target vehicle before the target vehicle stops;
the region dividing unit is used for dividing a region for hindering the driving in the direction of the head of the target vehicle according to the driving direction and taking the region as a conflict region;
a collision determination unit configured to determine whether there is the reference vehicle whose travel speed reaches a normal travel threshold in the collision area; if yes, triggering a conflict judgment unit;
and the conflict judging unit is used for judging that the conflict point exists.
9. A computer device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the conflict point detection method according to any one of claims 1 to 7 when executing the computer program.
10. A readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the conflict point detection method according to any one of claims 1 to 7.
CN202210115476.4A 2022-02-07 2022-02-07 Conflict point detection method, device, equipment and readable storage medium Active CN114155715B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210115476.4A CN114155715B (en) 2022-02-07 2022-02-07 Conflict point detection method, device, equipment and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210115476.4A CN114155715B (en) 2022-02-07 2022-02-07 Conflict point detection method, device, equipment and readable storage medium

Publications (2)

Publication Number Publication Date
CN114155715A true CN114155715A (en) 2022-03-08
CN114155715B CN114155715B (en) 2022-05-06

Family

ID=80449983

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210115476.4A Active CN114155715B (en) 2022-02-07 2022-02-07 Conflict point detection method, device, equipment and readable storage medium

Country Status (1)

Country Link
CN (1) CN114155715B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115294797A (en) * 2022-07-26 2022-11-04 内蒙古大学 Intelligent safety control method for highway level crossing

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007188270A (en) * 2006-01-13 2007-07-26 Univ Of Tokyo Method for detecting abnormal phenomenon at intersection by image processing
CN103377555A (en) * 2012-04-25 2013-10-30 施乐公司 Method and system for automatically detecting anomalies at a traffic intersection
CN109087534A (en) * 2018-10-09 2018-12-25 王业宝 A kind of traffic conflict detection method based on vehicle driving trace
CN109102696A (en) * 2018-07-06 2018-12-28 北京工业大学 The frequent section conflict method for early warning of intersection based on active safety
CN110782655A (en) * 2019-02-26 2020-02-11 北京嘀嘀无限科技发展有限公司 Method and device for detecting passing low-efficiency reasons
CN110992675A (en) * 2019-05-10 2020-04-10 当家移动绿色互联网技术集团有限公司 Intersection traffic simulation method, intersection traffic simulation device, intersection traffic simulation medium and electronic equipment
CN111445699A (en) * 2020-04-13 2020-07-24 黑龙江工程学院 Intersection traffic conflict discrimination method based on real-time vehicle track
CN111626275A (en) * 2020-07-30 2020-09-04 江苏金智慧安科技有限公司 Abnormal parking detection method based on intelligent video analysis
CN111640295A (en) * 2020-05-09 2020-09-08 天津市市政工程设计研究院 Intersection accident black point distinguishing method based on potential conflict risk assessment
CN111815943A (en) * 2019-04-11 2020-10-23 杭州海康威视数字技术股份有限公司 Method, device and equipment for detecting vehicle parking times and storage medium
WO2021048583A1 (en) * 2019-09-09 2021-03-18 日産自動車株式会社 Action deciding method of traveling support device, and traveling support device
CN113744529A (en) * 2021-09-06 2021-12-03 上海辉略企业发展集团有限公司 Traffic accident black spot identification method and system based on traffic conflict point

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007188270A (en) * 2006-01-13 2007-07-26 Univ Of Tokyo Method for detecting abnormal phenomenon at intersection by image processing
CN103377555A (en) * 2012-04-25 2013-10-30 施乐公司 Method and system for automatically detecting anomalies at a traffic intersection
CN109102696A (en) * 2018-07-06 2018-12-28 北京工业大学 The frequent section conflict method for early warning of intersection based on active safety
CN109087534A (en) * 2018-10-09 2018-12-25 王业宝 A kind of traffic conflict detection method based on vehicle driving trace
CN110782655A (en) * 2019-02-26 2020-02-11 北京嘀嘀无限科技发展有限公司 Method and device for detecting passing low-efficiency reasons
CN111815943A (en) * 2019-04-11 2020-10-23 杭州海康威视数字技术股份有限公司 Method, device and equipment for detecting vehicle parking times and storage medium
CN110992675A (en) * 2019-05-10 2020-04-10 当家移动绿色互联网技术集团有限公司 Intersection traffic simulation method, intersection traffic simulation device, intersection traffic simulation medium and electronic equipment
WO2021048583A1 (en) * 2019-09-09 2021-03-18 日産自動車株式会社 Action deciding method of traveling support device, and traveling support device
CN111445699A (en) * 2020-04-13 2020-07-24 黑龙江工程学院 Intersection traffic conflict discrimination method based on real-time vehicle track
CN111640295A (en) * 2020-05-09 2020-09-08 天津市市政工程设计研究院 Intersection accident black point distinguishing method based on potential conflict risk assessment
CN111626275A (en) * 2020-07-30 2020-09-04 江苏金智慧安科技有限公司 Abnormal parking detection method based on intelligent video analysis
CN113744529A (en) * 2021-09-06 2021-12-03 上海辉略企业发展集团有限公司 Traffic accident black spot identification method and system based on traffic conflict point

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李宏魁等: "一种新的视频停车事件检测算法", 《计算机测量与控制》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115294797A (en) * 2022-07-26 2022-11-04 内蒙古大学 Intelligent safety control method for highway level crossing
CN115294797B (en) * 2022-07-26 2023-05-05 内蒙古大学 Intelligent safety control method for road level crossing

Also Published As

Publication number Publication date
CN114155715B (en) 2022-05-06

Similar Documents

Publication Publication Date Title
CN106601023B (en) Indoor parking lot vehicle guiding and positioning system and method
KR102323437B1 (en) Method, System for Traffic Monitoring Using Deep Learning
CN114596712B (en) Vehicle following control method and system
CN113936465B (en) Traffic event detection method and device
CN114155715B (en) Conflict point detection method, device, equipment and readable storage medium
CN112526999A (en) Speed planning method, device, electronic equipment and storage medium
US20210027619A1 (en) Traffic monitoring apparatus, traffic monitoring system, traffic monitoring method, and non-transitory computer readable medium storing program
CN114023069B (en) Abnormal parking detection method, device and equipment and readable storage medium
CN113335312B (en) Obstacle-detouring driving method and device, electronic equipment and medium
CN112824198A (en) Trajectory decision method, apparatus, device and storage medium
CN114596704B (en) Traffic event processing method, device, equipment and storage medium
CN109887321B (en) Unmanned vehicle lane change safety judgment method and device and storage medium
CN117218895B (en) Automatic driving vehicle and pedestrian collision detection method based on potential collision judgment
AU2024200010A1 (en) Vehicle Safety Control Method And Apparatus, Electronic Device, And Storage Medium
CN110497906B (en) Vehicle control method, apparatus, device, and medium
CN115273463A (en) Pedestrian target crossing prediction method, device, vehicle and storage medium
CN115123297A (en) Vehicle control method, device, equipment, vehicle and storage medium
CN114701485A (en) Safe path planning method in field, automatic parking method and storage medium
CN114596706A (en) Detection method and device of roadside sensing system, electronic equipment and roadside equipment
CN114248766A (en) Apparatus and method for ensuring travel track of own vehicle
CN113721598A (en) Obstacle trajectory prediction method, device, equipment and storage medium
CN113715846B (en) Lane borrowing control method and device, storage medium and vehicle
CN118430268B (en) Intelligent monitoring method, equipment and medium for tunnel accidents
CN114038191B (en) Method and device for collecting traffic data
CN115675472B (en) Ramp port determining method and device, electronic equipment and storage medium

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