CN-116543555-B - Collision detection method, system, medium, and program product

CN116543555BCN 116543555 BCN116543555 BCN 116543555BCN-116543555-B

Abstract

The application provides a collision detection method, a system, a medium and a program product, wherein the method comprises the steps of obtaining collision data sent by a first vehicle when a suspected collision occurs, wherein the collision data at least comprise the suspected collision occurrence time, the suspected collision occurrence position and the suspected collision occurrence road, obtaining at least one type of second vehicle from other vehicles based on the collision data of the first vehicle and the track data uploaded by the other vehicles, wherein the second vehicle is other vehicles which travel on the suspected collision occurrence road of the first vehicle when the first vehicle is suspected to collide, the travel position is positioned before or after the suspected collision occurrence position of the first vehicle, and the travel behavior of the second vehicles meets the preset behavior condition, counting the number of the second vehicles of different types, and determining whether the first vehicle collides or not according to the number of the second vehicles. The application can improve the accuracy of collision detection.

Inventors

ZHANG TIANLIN
CHEN JIAJIA
DING GUANGLEI
CAI YANG
Xun Haitao
ZHONG YUXIU
FU TIANYU
SHI DAIQI

Assignees

北京高德云图科技有限公司

Dates

Publication Date: 20260512
Application Date: 20230428

Claims (15)

1. A collision detection method, the method comprising: Acquiring collision data sent by a first vehicle when a suspected collision occurs, wherein the collision data at least comprises a suspected collision occurrence time, a suspected collision occurrence position and a suspected collision occurrence road; Acquiring at least one type of second vehicle from other vehicles based on the collision data of the first vehicle and the track data uploaded by the other vehicles, wherein the second vehicle comprises other vehicles which are driven on a suspected collision road of the first vehicle at the time of occurrence of the suspected collision of the first vehicle, the driving position of which is positioned before the suspected collision occurrence position of the first vehicle, and the driving behavior of which meets the preset behavior condition, the type of the second vehicle comprises a first type and a second type, the first type of the second vehicle is the other vehicles which are positioned before the suspected collision occurrence position of the first vehicle and are driven quickly when the suspected collision of the first vehicle occurs, and the second type of the second vehicle is the other vehicles which are positioned before the suspected collision occurrence position of the first vehicle and are driven slowly when the suspected collision of the first vehicle occurs; counting the number of second vehicles of different types, wherein the number of the second vehicles of different types is used for reflecting the surrounding road conditions of the first vehicle; determining whether the first vehicle is involved in a collision based at least on the number of second vehicles.
2. The method of claim 1, wherein the second vehicle further comprises another vehicle whose traveling behavior meets a preset behavior condition after a traveling position is located at a suspected collision occurrence position of the first vehicle on a suspected collision occurrence road of the first vehicle at a suspected collision occurrence time of the first vehicle.
3. The method of claim 1, wherein the obtaining at least one type of second vehicle from the other vehicles based on the collision data of the first vehicle and the trajectory data uploaded by the other vehicles comprises: Screening other vehicles and track data thereof which run on a suspected collision road of the first vehicle at the suspected collision time of the first vehicle and the running position of which is positioned before or after the suspected collision position of the first vehicle based on the collision data of the first vehicle and the track data uploaded by the other vehicles; and based on the obtained other vehicles and the track data thereof, determining the other vehicles with the running behaviors conforming to the preset behavior conditions as second vehicles and classifying the second vehicles.
4. The method according to claim 3, wherein the screening out the other vehicles traveling on the suspected collision road of the first vehicle at the time of occurrence of the suspected collision of the first vehicle, the traveling position of which is located before or after the suspected collision occurrence position of the first vehicle, and the trajectory data thereof based on the collision data of the first vehicle and the trajectory data uploaded by the other vehicles, includes: Determining a track screening time range according to the suspected collision occurrence time of the first vehicle; determining a track screening position range according to the suspected collision position of the first vehicle; acquiring other vehicles and track data of the other vehicles with track time and track position falling into the track screening time range and the track screening position range from track data uploaded by the other vehicles; performing road network matching on the obtained other vehicles and the track data thereof, and determining the road matched with the obtained other vehicles; And if the matched road and the suspected collision road of the first vehicle are the same road, determining that the obtained other vehicles run on the suspected collision road of the first vehicle at the suspected collision time of the first vehicle, and the running position is positioned before or after the suspected collision position of the first vehicle.
5. The method according to claim 4, wherein determining, as the second vehicle, the other vehicle whose traveling behavior meets the preset behavior condition based on the acquired other vehicle and the trajectory data thereof, and classifying the second vehicle, comprises: Determining, based on the acquired other vehicles and trajectory data thereof, the other vehicles located in front of the suspected collision occurrence position of the first vehicle when the first vehicle is suspected to collide; determining, for other vehicles located in front of the first vehicle, whether their travel speeds at the time of the first vehicle suspected collision occurrence satisfy fast travel behavior or slow travel behavior based on their trajectory data; Determining, as a first-type second vehicle, other vehicles whose traveling behavior coincides with that of the first vehicle, which are located in front of a suspected collision occurrence position of the first vehicle and which travel quickly when the first vehicle is suspected to collide; and determining the other vehicles which are positioned in front of the suspected collision occurrence position of the first vehicle and slowly run when the running behavior accords with the suspected collision occurrence position of the first vehicle as second-class second vehicles.
6. The method of claim 5, wherein determining whether the first vehicle is crashing based at least on the number of second vehicles comprises: Determining whether the number of the first type second vehicles is greater than or equal to a first preset threshold value, and whether the number of the second type second vehicles is less than or equal to a second preset threshold value; if not, determining that the first vehicle is not collided; If yes, determining that the first vehicle collides.
7. The method according to claim 5, wherein the method further comprises: determining, based on the acquired other vehicles and trajectory data thereof, other vehicles located behind a suspected collision occurrence position of the first vehicle when the first vehicle is suspected to collide; for other vehicles positioned behind the first vehicle, determining the relation between the running position of the other vehicles after the suspected collision of the first vehicle and the suspected collision position of the first vehicle based on the track data of the other vehicles, and whether the running speed of the other vehicles meets the fast running behavior or the slow running behavior; Determining other vehicles, the driving behaviors of which are consistent with the distance between the other vehicles and the suspected collision position of the first vehicle, which are positioned behind the suspected collision position of the first vehicle when the suspected collision of the first vehicle occurs and have a distance greater than a first preset distance threshold value after a set period of time after the suspected collision of the first vehicle occurs, as third-class second vehicles; determining that the driving behavior accords with other vehicles which are positioned behind the suspected collision occurrence position of the first vehicle when the first vehicle is suspected to collide, are smaller than a second preset distance threshold value from the suspected collision occurrence position of the first vehicle after a set time period after the first vehicle is suspected to collide and rapidly drive, and are a fourth type of second vehicles; The driving behavior is consistent with that of other vehicles which are positioned behind the suspected collision position of the first vehicle when the first vehicle is suspected to collide and are still positioned behind the suspected collision position of the first vehicle after a set time period after the first vehicle is suspected to collide, and the other vehicles are determined to be fifth-class second vehicles; And taking other vehicles with driving behaviors which do not meet the behavior conditions as a sixth class of second vehicles.
8. The method of claim 7, wherein the collision data further comprises inertial navigation data of the first vehicle within a time window to which the suspected collision time belongs, an initial velocity of the first vehicle within the time window, and a negative acceleration of the first vehicle at the suspected collision; The determining whether the first vehicle collides according to at least the number of the second vehicles comprises: Acquiring inertial navigation characteristic parameter values of the first vehicle according to the inertial navigation data; determining whether a collision of the first vehicle occurs based on the inertial navigation feature parameter value, the number of second vehicles of the first to sixth types, the initial speed, and the negative acceleration.
9. The method of claim 8, wherein the determining whether the first vehicle is involved in a collision based on the inertial navigation feature parameter value, the number of second vehicles of the first through sixth classes, the initial speed, and the negative acceleration comprises: And determining whether the first vehicle collides or not by utilizing a collision detection model constructed based on a random forest algorithm according to the inertial navigation characteristic parameter value, the number of the first-class second vehicles to the sixth-class second vehicles, the initial speed and the negative acceleration.
10. A collision detection method, the method comprising: Acquiring running data of a first vehicle in a time window; Detecting whether the first vehicle is suspected to collide according to the running data in the time window, and if so, acquiring the collision data of the first vehicle, wherein the collision data at least comprises suspected collision occurrence time, suspected collision occurrence position and suspected collision occurrence road; a collision detection request carrying the collision data is sent to a server; The method comprises the steps of receiving a collision detection response returned by a service end based on a collision detection request, wherein the collision detection response carries a detection result used for indicating whether a first vehicle collides or not, the detection result is determined based on the number of second vehicles of different types, the second vehicles are at least one type of vehicles which are obtained from other vehicles based on collision data of the first vehicle and track data uploaded by the other vehicles, the second vehicles travel on a suspected collision road of the first vehicle at the time of occurrence of the first vehicle and are other vehicles with traveling behaviors meeting preset behavior conditions before the suspected collision occurrence position of the first vehicle, the number of the second vehicles of different types is used for reflecting the surrounding road conditions of the first vehicle, the second vehicles of the first type are other vehicles which are located in front of the suspected collision occurrence position of the first vehicle and rapidly travel, and the second vehicles of the second type are other vehicles which are located in front of the suspected collision occurrence position of the first vehicle and are suspected to slowly travel when the first vehicle is suspected to collide.
11. The method of claim 10, wherein the travel data within the time window includes positioning data and navigation path information, and wherein the detecting whether the first vehicle is suspected of collision based on the travel data within the time window includes: determining whether the first vehicle is located in a preset type of area according to the navigation path information and the positioning data in the time window; If the first vehicle is not located in the area of the preset type, determining whether the speed change of the first vehicle in the time window meets the speed change expression of the collision of the vehicle according to the positioning data in the time window; if yes, determining that the first vehicle is suspected to collide.
12. The method of claim 11, wherein determining whether the speed change of the first vehicle within the time window satisfies a speed change manifestation of a vehicle collision based on the positioning data within the time window comprises: determining whether an initial speed of the first vehicle within the time window is greater than a first preset speed threshold according to the 1 st to the x-th positioning data of the time window; if yes, determining whether the tail speed of the first vehicle in the time window is smaller than a second preset speed threshold value or not according to the y-th positioning data to the last positioning data of the time window; If yes, determining whether target positioning data exist according to the (x+1) th positioning data to the (x+n) th positioning data of the time window, wherein the target positioning data are positioning data of the first vehicle when the negative acceleration is greater than or equal to a third preset speed threshold value, and n is an integer greater than or equal to 2; If so, determining whether the speed of the first vehicle in the period is smaller than a fourth preset speed threshold according to the target positioning data to the y-1 th positioning data in the time window, wherein the fourth preset speed threshold is larger than the second preset speed threshold; If yes, determining that the speed change of the first vehicle in the time window meets the speed change expression of the collision of the vehicle, and taking the time and the position corresponding to the (x+1) th positioning data as the time and the position of the suspected collision of the first vehicle.
13. A collision detection system is characterized in that the system comprises end-side software and a service end, wherein, End-side software for performing the method of any of claims 10-12; The server is configured to perform the method according to any one of claims 1-9.
14. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-12.
15. A computer program product comprising a computer program or instructions which, when executed by a processor, implements the method of any of claims 1-12.

Description

Collision detection method, system, medium, and program product Technical Field The present application relates to the field of traffic travel technologies, and in particular, to a collision detection method, system, medium, and program product. Background Traffic accidents are one of the factors affecting the life and property safety of traffic participants. After the traffic accident happens, the traffic accident is found in time and the road rescue is carried out rapidly, so that the traffic accident has great significance in saving the lives of wounded persons and guaranteeing the travel safety of traffic participants. Currently, there are some methods for detecting whether a vehicle has a traffic accident, for example, detecting whether a vehicle collides during driving of the vehicle based on the driving data of the vehicle to determine whether the vehicle has a traffic accident, because the vehicles having a traffic accident basically have collision behaviors. Because the behavior that the vehicle appears when driving on the road is more, for example, sudden braking, sharp turn etc., but have some behaviors and do not lead to the vehicle to take place the traffic accident, consequently, provide the technique that can accurately detect whether the vehicle takes place the traffic accident, avoid the rescue resource waste that the mistake detection brought, be the problem that the technical staff in the field need solve. Disclosure of Invention The application provides a collision detection method, a system, a medium and a program product, which can accurately detect whether a vehicle collides or not, further accurately obtain the conclusion of whether the vehicle has traffic accidents or not, and avoid rescue resource waste caused by false detection. In a first aspect, the present application provides a collision detection method, the method comprising: Acquiring collision data sent by a first vehicle when a suspected collision occurs, wherein the collision data at least comprises a suspected collision occurrence time, a suspected collision occurrence position and a suspected collision occurrence road; Acquiring at least one type of second vehicle from other vehicles based on the collision data of the first vehicle and the track data uploaded by the other vehicles, wherein the second vehicle is other vehicles which travel on a suspected collision road of the first vehicle at the suspected collision occurrence time of the first vehicle, have a travel position before or after the suspected collision occurrence position of the first vehicle and have travel behaviors conforming to preset behavior conditions, and the type of the second vehicle is related to the travel behaviors of the travel position before or after the suspected collision occurrence position of the first vehicle; Counting the number of second vehicles of different types; determining whether the first vehicle is involved in a collision based at least on the number of second vehicles. In a second aspect, the present application provides a collision detection method, the method comprising: Acquiring running data of a first vehicle in a time window; Detecting whether the first vehicle is suspected to collide according to the running data in the time window, and if so, acquiring the collision data of the first vehicle, wherein the collision data at least comprises suspected collision occurrence time, suspected collision occurrence position and suspected collision occurrence road; a collision detection request carrying the collision data is sent to a server; And receiving a collision detection response returned by the server based on the collision detection request, wherein the collision detection response carries a detection result for indicating whether the first vehicle collides or not, the detection result is determined based on the number of second vehicles, and the second vehicles are other vehicles which travel on a suspected collision road of the first vehicle at the suspected collision occurrence time of the first vehicle, the travel positions of which are positioned before or after the suspected collision occurrence position of the first vehicle, and the travel behaviors of which meet preset behavior conditions. In a third aspect, the present application provides a collision detection apparatus, the apparatus comprising: The first acquisition module is used for acquiring collision data sent by the first vehicle when the suspected collision occurs, wherein the collision data at least comprises suspected collision occurrence time, suspected collision occurrence position and suspected collision occurrence road; A second obtaining module, configured to obtain, from other vehicles, at least one type of second vehicle based on collision data of the first vehicle and trajectory data uploaded by the other vehicles, where the second vehicle is another vehicle that travels on a suspected collision road of the first vehicle at a suspected collisi