Screening method and apparatus for crossing vehicle target, vehicle, and storage medium

Abstract

The present application relates to the technical field of intelligent driving, and in particular to a screening method and apparatus for a crossing vehicle target, a vehicle, and a storage medium. The method comprises: acquiring vehicle information of a current vehicle and attribute information of a plurality of surrounding targets; on the basis of the attribute information, screening from the plurality of surrounding targets at least one target vehicle meeting a preset condition, and determining all crossing vehicles in preset transverse and longitudinal detection areas on the basis of the vehicle information and attribute information of the at least one target vehicle; and calculating the final collision time of the current vehicle and each crossing vehicle on the basis of attribute information of all the crossing vehicles and the vehicle information, and, on the basis of the final collision time, screening a collision vehicle meeting a preset collision risk condition. Thus, crossing vehicles in transverse and longitudinal detection areas are screened, the collision time of a collision-risk vehicle is calculated on the basis of the crossing vehicles, so that the problems in the related art such as it being difficult to accurately identify and classify crossing vehicles, and algorithm computation being complex are solved, the required computing power is small, and the computation speed is high.

Description

Method and device for screening crossing vehicle target, vehicle and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] The present application is based on the Chinese patent application No. 202410408706.5, filed on April 7, 2024, and claims priority to the Chinese patent application No. 202410408706.5, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present application relates to the field of intelligent driving technology, in particular to a method and device for screening crossing vehicle target, vehicle and storage medium. BACKGROUND

[0004] With the development of intelligent driving technology, it provides strong support for safer and more efficient road travel. By effectively monitoring the crossing vehicles, the intelligent driving system can identify the crossing vehicles on the road in real time, and take braking or avoidance measures in time, thereby reducing the probability of traffic accidents and ensuring the safety of drivers and other road users.

[0005] In related technologies, a camera and image processing technology are usually used to identify the crossing vehicle target, and a deep learning algorithm is used for detection and identification of the vehicle target.

[0006] However, the above-mentioned technology is easily disturbed by environmental factors, and it is difficult to accurately identify and classify the crossing vehicles, and the output target accuracy is low and cannot distinguish targets with higher danger levels. At the same time, the algorithm is complex, and the system requires high computing resources and power consumption, which needs to be improved.

[0007] SUMMARY

[0008] The present application provides a method and device for screening crossing vehicle target, vehicle and storage medium to solve the problems of related technologies, such as difficulty in accurately identifying and classifying crossing vehicles and complex algorithm.

[0009] The first aspect of the present application provides a method for screening crossing vehicle target of a vehicle, comprising the following steps:

[0010] Obtaining vehicle information of a current vehicle and attribute information of a plurality of surrounding targets;

[0011] Based on the attribute information, at least one target vehicle satisfying a preset condition is screened from the plurality of surrounding targets, and all crossing vehicles in a preset horizontal and longitudinal detection region are determined according to the vehicle information and the attribute information of the at least one target vehicle;

[0012] The final collision time of the current vehicle and each crossing vehicle is calculated according to the attribute information of all the crossing vehicles and the vehicle information, and a collision vehicle meeting a preset collision risk condition is screened out according to the final collision time.

[0013] According to the technical means described above, the problems such as difficulty in accurately identifying and classifying crossing vehicles and complex algorithm calculation in the related art are solved, the crossing vehicles and their types can be accurately identified, the collision time of the collision risk vehicle can be calculated, and the required computing power is small and the calculation speed is fast.

[0014] According to an embodiment of the present application, the vehicle information includes the speed of the current vehicle, the width of the current vehicle, the distance from the front edge of the current vehicle to the center of the rear axle of the current vehicle, the distance from the current vehicle to the two sides of the road, the lateral sensing accuracy of the current vehicle, and the longitudinal sensing accuracy of the current vehicle; the attribute information includes the confidence of each target, the type of each target, the lateral speed of each target relative to the current vehicle, the lateral acceleration of each target relative to the current vehicle, the lateral width of each target relative to the current vehicle, the longitudinal length of each target relative to the current vehicle, the longitudinal distance between the geometric center of each target and the center of the rear axle of the current vehicle, and the lateral distance between the geometric center of each target and the center of the rear axle of the current vehicle.

[0015] According to the technical means described above, the distance and relative motion state of other targets can be calculated and predicted according to the vehicle information, the target type can be used to identify different types of targets, such as distinguishing between cars, trucks, bicycles, etc., the lateral speed and lateral acceleration of the target relative to the current vehicle can predict the future state and trajectory of the target, and the lateral width and longitudinal length of the target relative to the current vehicle can determine the size and dimensions of the target, thereby determining the distance to the target and performing collision risk assessment.

[0016] According to an embodiment of the present application, the at least one target vehicle meeting the preset condition is screened out from the plurality of surrounding targets based on the attribute information, comprising:

[0017] At least one initial target with a confidence greater than a preset confidence threshold is screened out based on the confidence of each target.

[0018] Non-vehicle targets are screened out from the at least one initial target based on the type of each target, and the at least one target vehicle is obtained.

[0019] According to the technical means, the initial target with a confidence higher than the threshold is screened out by setting the threshold, the interference of unreliable targets is reduced, and the accuracy of the system is improved. By classifying the targets and filtering out non-vehicle targets, the target vehicle is obtained, so that the system can focus on processing the vehicle targets and reduce the calculation amount.

[0020] According to one embodiment of the application, the all crossing vehicles in the preset lateral and longitudinal detection region are determined according to the vehicle information and the attribute information of the at least one target vehicle, including:

[0021] The lateral distance of the geometric center of each target vehicle from the center line of the lane where the current vehicle is located is calculated based on the lane line coordinate system of the current vehicle, to obtain the mapping lateral coordinate of each target vehicle, and the mapping longitudinal coordinate of each target vehicle is obtained by integrating the center line of the lane where the current vehicle is located based on the position of the current vehicle and the projection point of the lateral distance from the geometric center of each target to the rear axle center of the current vehicle to the center line of the lane where the current vehicle is located.

[0022] The lateral detection region and the longitudinal detection region are determined according to the speed of the current vehicle, the distance of the current vehicle from the two sides of the road, the lateral sensing accuracy of the current vehicle, and the longitudinal sensing accuracy of the current vehicle.

[0023] The target vehicles not in the lateral detection region and the longitudinal detection region are filtered out based on the mapping lateral coordinate of each target vehicle and the mapping longitudinal coordinate of each target vehicle to obtain the all crossing vehicles.

[0024] According to the technical means, the lateral distance and the geometric center distance of the target vehicle from the center line of the lane where the current vehicle is located can be accurately calculated based on the lane line coordinate system of the current vehicle, and accurate position information is provided for subsequent processing. The detection region is determined according to the speed of the current vehicle, the distance from the two sides of the road, the lateral sensing accuracy, and the longitudinal sensing accuracy, so that the size of the detection region can be flexibly adjusted according to the actual situation, and the calculation amount and redundant information are reduced. The target vehicles in the lateral detection region and the longitudinal detection region are screened out, irrelevant target vehicles are filtered out, and the accuracy and efficiency of target detection and tracking are improved.

[0025] According to one embodiment of the application, the final collision time of the current vehicle and each crossing vehicle is calculated according to the attribute information of the all crossing vehicles and the vehicle information, including:

[0026] According to the longitudinal distance between the geometric center of each target and the rear axle center of the current vehicle, the distance from the front of the current vehicle to the rear axle center of the current vehicle, and the lateral width of each target relative to the current vehicle, the maximum distance and the minimum distance between the current vehicle and each target vehicle are calculated according to the first preset margin and the second preset margin respectively;

[0027] According to the maximum distance, the minimum distance, and the speed of the current vehicle, the maximum collision time and the minimum collision time between the current vehicle and each target vehicle are calculated, and the passable domain of the current vehicle is determined according to the width of the current vehicle and the bias amount determined according to the type of each crossing vehicle. The left boundary and the right boundary between the current vehicle and each crossing vehicle are calculated according to the lateral distance between the geometric center of each target and the rear axle center of the current vehicle and the lateral width of each target relative to the current vehicle.

[0028] According to the maximum collision time, the minimum collision time, the lateral speed of each crossing vehicle, the passable domain of the current vehicle, the left boundary and the right boundary between the current vehicle and each crossing vehicle, the final collision time between the current vehicle and each crossing vehicle is calculated.

[0029] According to the above technical means, by calculating the collision time, the safety distance between the current vehicle and the target vehicle can be evaluated, so that timely warning or corresponding measures can be taken to ensure road safety. By calculating the left boundary and the right boundary between the current vehicle and the crossing vehicle, the safety space range between the current vehicle and the target vehicle can be further limited. By comprehensively considering various factors, the final collision time between the current vehicle and the crossing vehicle is calculated, which can more accurately evaluate the collision risk between the current vehicle and the crossing vehicle, and provide an important reference for driving decision.

[0030] According to an embodiment of the present application, after the collision vehicles meeting the preset collision risk condition are screened out according to the final collision time, the method further comprises:

[0031] According to the lateral distance between the geometric center of each target and the rear axle center of the current vehicle, the collision vehicles are divided into a first side risk vehicle set and a second side risk vehicle set;

[0032] The longitudinal distance of the collision vehicles in the first side risk vehicle set and the second side risk vehicle set is calculated respectively to obtain the first side minimum longitudinal distance vehicle and the second side minimum longitudinal distance vehicle.

[0033] According to the technical means, the risk vehicle set is divided, vehicles with close lateral relative positions are grouped, and potential collision risks of different sides are processed more specifically. By calculating the longitudinal distance of different sides, the collision risks in different directions can be evaluated more specifically, and multi-dimensional safety warnings are provided.

[0034] According to the method for screening a target vehicle provided in the embodiments of the present application, attribute information of a vehicle and surrounding targets is obtained, target vehicles meeting a condition are screened, a crossing vehicle is determined and a final collision time is calculated, and a collision vehicle meeting a collision risk condition is screened. Thus, by screening the crossing vehicle in the lateral and longitudinal detection area and calculating the collision time of the collision risk vehicle based on the crossing vehicle, the problems of related technologies, such as difficulty in accurately identifying and classifying the crossing vehicle and complex algorithm calculation, are solved, and the required computing power is small and the calculation speed is fast.

[0035] The second aspect of the embodiments of the present application provides a screening device for a target vehicle, comprising:

[0036] The acquisition module is configured to acquire vehicle information of a current vehicle and attribute information of a plurality of surrounding targets.

[0037] The first screening module is configured to screen at least one target vehicle meeting a preset condition from the plurality of surrounding targets based on the attribute information, and determine all crossing vehicles in a preset lateral and longitudinal detection area according to the vehicle information and the attribute information of the at least one target vehicle.

[0038] The second screening module is configured to calculate a final collision time of the current vehicle and each crossing vehicle according to the attribute information of the all crossing vehicles and the vehicle information, and screen a collision vehicle meeting a preset collision risk condition according to the final collision time.

[0039] According to an embodiment of the present application, the vehicle information includes a speed of the current vehicle, a width of the current vehicle, a distance from a front edge of the current vehicle to a rear axle center of the current vehicle, distances of the current vehicle from two sides of a road, a lateral sensing accuracy of the current vehicle, and a longitudinal sensing accuracy of the current vehicle; and the attribute information includes a confidence of each target, a type of each target, a lateral speed of each target relative to the current vehicle, a lateral acceleration of each target relative to the current vehicle, a lateral width of each target relative to the current vehicle, a longitudinal length of each target relative to the current vehicle, a longitudinal distance between a geometric center of each target and a rear axle center of the current vehicle, and a lateral distance between the geometric center of each target and the rear axle center of the current vehicle.

[0040] According to an embodiment of the present application, the first screening module is configured to:

[0041] screening at least one initial target whose confidence is greater than a preset confidence threshold based on the confidence of each target;

[0042] screening out non-vehicle targets from the at least one initial target based on the type of each target to obtain the at least one target vehicle.

[0043] According to an embodiment of the present application, the first screening module is configured to:

[0044] calculating a mapping horizontal coordinate of each target vehicle by calculating a lateral distance between a geometric center of each target vehicle and a lane center line where the current vehicle is located based on a lane line coordinate system of the current vehicle, and integrating the lane center line where the current vehicle is located based on a lateral distance between the geometric center of each target and a rear axle center of the current vehicle to a projection point of the lane center line where the current vehicle is located, to obtain a mapping vertical coordinate of each target vehicle;

[0045] determining a lateral detection area and a longitudinal detection area according to a vehicle speed of the current vehicle, a distance between the current vehicle and two sides of a road, a lateral sensing accuracy of the current vehicle, and a longitudinal sensing accuracy of the current vehicle;

[0046] screening out target vehicles not in the lateral detection area and the longitudinal detection area based on the mapping horizontal coordinate of each target vehicle and the mapping vertical coordinate of each target vehicle to obtain all the crossing vehicles.

[0047] According to an embodiment of the present application, the second screening module is configured to:

[0048] calculating a maximum distance and a minimum distance between the current vehicle and each target vehicle according to a first preset margin and a second preset margin based on a longitudinal distance between the geometric center of each target and the rear axle center of the current vehicle, a distance from a front edge of the current vehicle to the rear axle center of the current vehicle, and a lateral width of each target relative to the current vehicle;

[0049] calculating a maximum collision time and a minimum collision time between the current vehicle and each target vehicle according to the maximum distance, the minimum distance, and a vehicle speed of the current vehicle, determining a passable domain of the current vehicle according to a bias amount determined according to a width of the current vehicle and a type of each crossing vehicle, and calculating a left boundary and a right boundary between the current vehicle and each crossing vehicle according to a lateral distance between the geometric center of each target and the rear axle center of the current vehicle, and the lateral width of each target relative to the current vehicle;

[0050] The final collision time of the current vehicle and each crossing vehicle is calculated according to the maximum collision time, the minimum collision time, the lateral speed of each crossing vehicle, the passable region of the current vehicle, and the left boundary and the right boundary of the current vehicle and each crossing vehicle.

[0051] According to an embodiment of the present application, after the collision vehicle meeting the preset collision risk condition is screened out according to the final collision time, the second screening module is further configured to:

[0052] The collision vehicle is divided into a first side risk vehicle set and a second side risk vehicle set based on the lateral distance between the geometric center of each target and the rear axle center of the current vehicle.

[0053] The collision vehicle in the first side risk vehicle set and the second side risk vehicle set is respectively subjected to longitudinal distance calculation, and a first side minimum longitudinal distance vehicle and a second side minimum longitudinal distance vehicle are obtained.

[0054] The screening device for the crossing vehicle target provided by the embodiment of the present application acquires the attribute information of the vehicle and the surrounding target, screens out the target vehicle meeting the condition, determines the crossing vehicle and calculates the final collision time, and screens out the collision vehicle meeting the collision risk condition. Therefore, the crossing vehicle in the horizontal and longitudinal detection region is screened out, and the collision time of the collision risk vehicle is calculated based on the crossing vehicle, which solves the problems of the related art, such as the difficulty in accurately identifying and classifying the crossing vehicle, the complex algorithm calculation, and the like, and the required computing power is small and the calculation speed is fast.

[0055] The third aspect embodiment of the present application provides a vehicle, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor executes the program to implement the screening method for the crossing vehicle target as described in the above embodiments.

[0056] The fourth aspect embodiment of the present application provides a computer readable storage medium, which stores computer instructions for causing the computer to execute the screening method for the crossing vehicle target as described in the above embodiments.

[0057] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be known by the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0058] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

[0059] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description, taken in conjunction with the following drawings of which:

[0060] Fig. 1 is a flow chart of a method for screening a cross-vehicle target according to an embodiment of the present application;

[0061] Fig. 2 is a schematic diagram of a lane line coordinate system in which a current vehicle is located according to an embodiment of the present application;

[0062] Fig. 3 is a schematic diagram of a current vehicle mapped to a lane line coordinate system according to an embodiment of the present application;

[0063] Fig. 4 is a schematic diagram of a target vehicle left boundary on the right side of a current vehicle right boundary and a target vehicle speed direction to the left according to an embodiment of the present application;

[0064] Fig. 5 is a schematic diagram of a target vehicle left boundary on the left side of a current vehicle left boundary and a target vehicle speed direction to the right according to an embodiment of the present application;

[0065] Fig. 6 is a schematic diagram of a target vehicle left boundary on the left side of a current vehicle right boundary, a target vehicle right boundary on the right side of a current vehicle left boundary and a target vehicle speed direction to the left according to an embodiment of the present application;

[0066] Fig. 7 is a schematic diagram of a target vehicle left boundary on the left side of a current vehicle right boundary, a target vehicle right boundary on the right side of a current vehicle left boundary and a target vehicle speed direction to the right according to an embodiment of the present application;

[0067] Fig. 8 is a block schematic diagram of a screening device for a cross-vehicle target according to an embodiment of the present application;

[0068] Fig. 9 is a schematic diagram of a structure of a vehicle according to an embodiment of the present application.

[0069] In the drawings: 10 - screening device for a cross-vehicle target, 100 - acquisition module, 200 - first screening module, 300 - second screening module, 901 - memory, 902 - processor, 903 - communication interface. DETAILED DESCRIPTION

[0070] Embodiments of the present application are described in detail below with reference to the attached drawing figures, wherein the same or like reference numerals are used throughout the drawing figures to refer to the same or like elements or elements having the same or similar functionality. The embodiments described below are illustrative examples that are intended to provide an explanation of the present application. Thus, they are not intended to be limiting in scope.

[0071] A method for screening a crossing vehicle target, a device, a vehicle, and a storage medium are described below with reference to the accompanying drawings. To address the problems of inaccurate identification and classification of a crossing vehicle and complex algorithm calculation mentioned in the background, the present application provides a method for screening a crossing vehicle target, which obtains attribute information of a vehicle and surrounding targets, screens target vehicles that meet the conditions, determines a crossing vehicle and calculates the final collision time, and screens a collision vehicle that meets the collision risk conditions. Thus, by screening the crossing vehicles in the horizontal and vertical detection areas and calculating the collision time of the collision risk vehicle based on the crossing vehicles, the problems of inaccurate identification and classification of a crossing vehicle and complex algorithm calculation in related technologies are solved, and the required computing power is small and the calculation speed is fast.

[0072] Specifically, FIG. 1 is a flowchart of a method for screening a crossing vehicle target provided by an embodiment of the present application.

[0073] As shown in FIG. 1, the method for screening a crossing vehicle target includes the following steps:

[0074] In step S101, vehicle information of a current vehicle and attribute information of a plurality of surrounding targets are obtained.

[0075] In some embodiments, the vehicle information includes the speed of the current vehicle, the width of the current vehicle, the distance from the front edge of the current vehicle to the center of the rear axle of the current vehicle, the distance between the current vehicle and the two sides of the road, the lateral sensing accuracy of the current vehicle, and the longitudinal sensing accuracy of the current vehicle; and the attribute information includes the confidence of each target, the type of each target, the lateral speed of each target relative to the current vehicle, the lateral acceleration of each target relative to the current vehicle, the lateral width of each target relative to the current vehicle, the longitudinal length of each target relative to the current vehicle, the longitudinal distance between the geometric center of each target and the center of the rear axle of the current vehicle, and the lateral distance between the geometric center of each target and the center of the rear axle of the current vehicle.

[0076] Optionally, the type of each target can be a truck (including a bus), a car, a two-wheeled vehicle, an unknown type, etc.

[0077] Specifically, the speed, width, distance from the front edge to the center of the rear axle, and distance from the road of the current vehicle can be obtained by sensors such as radar, camera, lidar, etc. installed on the vehicle, and the confidence, type, lateral speed, lateral acceleration, lateral width, longitudinal length, and longitudinal and lateral distance from the center of the rear axle of the current vehicle of the surrounding targets can also be obtained. In addition, the attribute information of the surrounding targets, such as the type, speed, and distance of the vehicle, can also be obtained by using communication technology between the vehicle and the infrastructure (such as V2X (Vehicle to X, vehicle wireless communication technology)), which is not limited here.

[0078] In step S102, at least one target vehicle meeting a preset condition is selected from the plurality of surrounding targets based on the attribute information, and all crossing vehicles in a preset horizontal and longitudinal detection region are determined according to the vehicle information and the attribute information of the at least one target vehicle.

[0079] The preset horizontal and longitudinal detection region can be a specific region for detecting surrounding targets preset by the vehicle or the system when driving, or a detection region determined according to the speed of the current vehicle, the distance between the current vehicle and the two sides of the road, the horizontal sensing accuracy of the current vehicle, and the longitudinal sensing accuracy of the current vehicle. Preferably, the preset condition can be that the confidence of the target is greater than a preset threshold, which is not limited here.

[0080] Specifically, the embodiments of the present application can use the attribute information of the target vehicle, and select at least one target vehicle meeting the condition from the plurality of surrounding targets according to the preset condition by using logical judgment or classification algorithm or machine learning method. For the horizontal and longitudinal region to be detected, a detection region is set within a certain range of vehicle perception, the position information of the target vehicle is compared with the set horizontal and longitudinal detection region, and it is further determined whether the target vehicle is in the preset detection region, and then the attribute information of the vehicle is used to further identify whether the target vehicle is a crossing vehicle.

[0081] Further, in some embodiments, selecting at least one target vehicle meeting a preset condition from the plurality of surrounding targets based on the attribute information comprises: selecting at least one initial target with a confidence greater than a preset confidence threshold based on the confidence of each target; and excluding non-vehicle targets from the at least one initial target based on the type of each target to obtain at least one target vehicle.

[0082] The preset confidence threshold can be a confidence threshold preset by a person skilled in the art, a confidence threshold obtained through a limited number of experiments, or a confidence threshold obtained through computer simulation, which is not limited here.

[0083] Specifically, according to the input confidence signal of each target, targets with too low confidence are excluded to obtain initial targets, and then non-vehicle targets in the initial targets are excluded according to the type of the target (such as trucks, cars, two-wheeled vehicles, etc.) to obtain target vehicles.

[0084] Further, in some embodiments, determining all crossing vehicles in the preset lateral and longitudinal detection region according to the vehicle information and the attribute information of the at least one target vehicle comprises: taking the lane line coordinate system of the current vehicle as a reference, calculating the lateral distance between the geometric center of each target vehicle and the lane center line where the current vehicle is located to obtain the mapping lateral coordinate of each target vehicle, and based on the position of the current vehicle and the projection point of the lateral distance between the geometric center of each target and the rear axle center of the current vehicle to the lane center line where the current vehicle is located, integrating the lane center line where the current vehicle is located to obtain the mapping longitudinal coordinate of each target vehicle; determining the lateral detection region and the longitudinal detection region according to the speed of the current vehicle, the distance of the current vehicle to the two sides of the road, the lateral sensing accuracy of the current vehicle and the longitudinal sensing accuracy of the current vehicle; and based on the mapping lateral coordinate of each target vehicle and the mapping longitudinal coordinate of each target vehicle, excluding the target vehicles not in the lateral detection region and the longitudinal detection region to obtain all crossing vehicles.

[0085] It should be noted that in the embodiments of the present application, the current vehicle travels along the center line of the lane, at this time, the lateral distance between the geometric center of each target vehicle and the lane center line where the current vehicle is located is equal to the lateral distance between the geometric center of each target and the rear axle center of the current vehicle.

[0086] Wherein, the lane line coordinate system where the current vehicle is located is shown in FIG. 2, and the center line equation of the lane where the current vehicle is located is: Y=C0+C1X+C2X 2 +C3X 3 (1)

[0087] Wherein, Y is the lateral distance of the lane line from the current vehicle at the X meter longitudinal distance position in the lane line coordinate system of the current vehicle, C0, C1, C2 and C3 are constants, and X is the distance.

[0088] Specifically, as shown in FIG. 3, the lateral distance OBJ y between the geometric center of the target vehicle and the lane center line where the current vehicle is located is calculated according to the projection of the target vehicle to the lane center line where the current vehicle is located, so as to obtain the mapping lateral coordinate Obj y of the target vehicle, and taking the position of the current vehicle as the starting point and the projection point of OBJ y to the lane center line where the current vehicle is located as the ending point, the lane center line where the current vehicle is located is integrated, so as to obtain the longitudinal distance OBJ x between the geometric center of the target vehicle and the lane center line where the current vehicle is located, i.e. the mapping longitudinal coordinate Obj x of the target vehicle in the lane line coordinate system of the current vehicle.

[0089] Furthermore, the lateral distances of the left and right boundaries of the current vehicle from the curb (i.e., the distances between the current vehicle and the curbs on both sides) are obtained based on the curb information, and combined with the maximum value Y of the lateral sensing accuracy range of the current vehicle OBJ , get the horizontal detection area X dec is min(the distance between the current vehicle and the curb on both sides, Y OBJ ). According to the maximum value of the longitudinal sensing accuracy range of the current vehicle X OBJ And the current vehicle speed, get the longitudinal detection area Y dec is min(X OBJ , T a V self ); where T a is the calibration quantity, ranging from 4 to 8, V self is the current vehicle speed.

[0090] Furthermore, according to the mapped horizontal coordinate and the mapped vertical coordinate of the target vehicle, the position of the target vehicle (Obj c ,Obj y ), and will not be in the lateral detection area X dec and Y in the longitudinal detection area dec The target vehicles within the range are filtered out to obtain all crossing vehicles.

[0091] In step S103, the final collision time between the current vehicle and each crossing vehicle is calculated based on the attribute information and vehicle information of all crossing vehicles, and collision vehicles that meet the preset collision risk conditions are screened out based on the final collision time.

[0092] Among them, the preset collision risk conditions can be collision risk conditions pre-set by technical personnel in this field, can be collision risk conditions obtained through a limited number of experiments, or can be collision risk conditions obtained through computer simulation, and are not specifically limited here.

[0093] Specifically, by calculating the attributes and vehicle information of all crossing vehicles, a comprehensive dataset is obtained, providing a more accurate time-to-collision estimate. By filtering based on the final time-to-collision, vehicles that meet the pre-defined collision risk criteria can be selected, effectively reducing collision risk.

[0094] Further, in some embodiments, the final collision time of the current vehicle with each crossing vehicle is calculated according to all attribute information of the crossing vehicles and vehicle information, including: calculating the maximum distance and the minimum distance of the current vehicle from each target vehicle based on the longitudinal distance of the geometric center of each target from the rear axle center of the current vehicle, the distance from the front edge of the current vehicle to the rear axle center of the current vehicle, the lateral width of each target relative to the current vehicle according to the first preset margin and the second preset margin respectively; calculating the maximum collision time and the minimum collision time of the current vehicle from each target vehicle according to the maximum distance, the minimum distance and the speed of the current vehicle, and determining the passable domain of the current vehicle according to the bias amount determined by the width of the current vehicle and the type of each crossing vehicle, and calculating the left boundary and the right boundary of the current vehicle from each crossing vehicle according to the lateral distance of the geometric center of each target from the rear axle center of the current vehicle and the lateral width of each target relative to the current vehicle; calculating the final collision time of the current vehicle from each crossing vehicle according to the maximum collision time, the minimum collision time, the lateral speed of each crossing vehicle, the passable domain of the current vehicle, the left boundary and the right boundary of the current vehicle from each crossing vehicle.

[0095] In order to ensure the safety of the vehicle, the first preset margin and the second preset margin are set in the embodiments of the present application. The first preset margin and the second preset margin can be the margin preset by the person skilled in the art, can be the margin obtained through a limited number of experiments, or can be the margin obtained through computer simulation, which is not limited here. Preferably, the first preset margin is 0.5 and the second preset margin is 1.5.

[0096] Alternatively, the distance of the current vehicle from each target vehicle can be the distance from the tail of the target vehicle to the front edge of the current vehicle.

[0097] Specifically, in order to facilitate the person skilled in the art to understand the maximum distance of the current vehicle from each target vehicle in the embodiments of the present application, the maximum distance can be represented by formula (2): end OBJx x -l self +a1*OBJ wid +a2 (2)

[0098] wherein OBJx end is the maximum distance of the current vehicle from each target vehicle, OBJ x is the longitudinal distance of the geometric center of each target from the rear axle center of the current vehicle, l self is the distance from the front edge of the current vehicle to the rear axle center of the current vehicle, a1 is the first preset margin, OBJ wid is the lateral width of each target relative to the current vehicle, and a2 is the second preset margin.

[0099] Further, the minimum distance between the current vehicle and each target vehicle can be expressed as: OBJ xstart = OBJ x - l self - a1*OBJ wid - a2 (3)

[0100] wherein OBJ xstart is the minimum distance between the current vehicle and each target vehicle, OBJ x is the longitudinal distance between the geometric center of each target and the rear axle center of the current vehicle, l self is the distance from the front edge of the current vehicle to the rear axle center of the current vehicle, a1 is a first preset margin, OBJ wid is the lateral width of each target relative to the current vehicle, and a2 is a second preset margin.

[0101] Further, according to the maximum distance and the speed of the current vehicle, the maximum collision time between the current vehicle and each target vehicle can be calculated by the following formula:

[0102] wherein self Te is the maximum collision time between the current vehicle and each target vehicle, OBJ xend is the maximum distance between the current vehicle and each target vehicle, and V self is the speed of the current vehicle.

[0103] Further, according to the minimum distance and the speed of the current vehicle, the minimum collision time between the current vehicle and each target vehicle can be calculated by the following formula:

[0104] wherein self Ts is the minimum collision time between the current vehicle and each target vehicle, OBJ xstart is the minimum distance between the current vehicle and each target vehicle, and V self is the speed of the current vehicle.

[0105] Further, the passable region of the current vehicle can be determined by formula (6) and formula (7) according to the width of the current vehicle and the bias amount determined according to the type of each target vehicle: self CL = 0.5wid self + Offset (6) self CR = -0.5wid self - Offset (7)

[0106] wherein self CL is the left boundary of the passable region of the current vehicle, and wid selfWidth is the width of the current vehicle, Offset is the offset determined according to the type of each crossing vehicle, self CR Width is the right boundary of the passable region of the current vehicle.

[0107] Exemplarily, taking the types of the crossing vehicles as truck, car and two-wheeler as examples, it is assumed that the offset when the type of the crossing vehicle is truck is Offset1, the offset when the type of the crossing vehicle is car is Offset2, and the offset when the type of the crossing vehicle is two-wheeler is Offset3, then Offset1, Offset2 and Offset3 can be represented by the following formulas respectively: Offset1 = 0.0075OBJ x + 0.05 (OBJ type = truck) (8) Offset2 = 0.0005OBJ x + 0.05 (OBJ type = car) (9) Offset3 = 0.008OBJ x + 0.05 (OBJ type = two-wheeler) (10)

[0108] Wherein, Offset1 is the offset when the type of the crossing vehicle is truck, OBJ x is the longitudinal distance from the geometric center of the target vehicle to the center line of the lane where the current vehicle is located, OBJ type is the type of the crossing vehicle, Offset2 is the offset when the type of the crossing vehicle is car, and Offset3 is the offset when the type of the crossing vehicle is two-wheeler.

[0109] Further, the left boundary and the right boundary of the current vehicle and each crossing vehicle can be calculated according to the lateral distance between the geometric center of each target and the center of the rear axle of the current vehicle and the lateral width of each target relative to the current vehicle, and the left boundary and the right boundary of the crossing vehicle can be calculated by the following formulas: OBJ LeB = OBJ y + 0.5 * OBJ wid (11) OBJ RiB = OBJ y - 0.5 * OBJ wid (12)

[0110] Wherein, OBJ LeB is the left boundary of the crossing vehicle, OBJ y is the lateral distance between the geometric center of the target and the center of the rear axle of the current vehicle, OBJ wid is the lateral width of the target relative to the current vehicle, and OBJ RiB is the right boundary of the crossing vehicle.

[0111] Further, the maximum collision time, the minimum collision time, the passable region of the current vehicle, the left and right boundaries of the current vehicle and each crossing vehicle, and the lateral speed of each crossing vehicle are calculated according to the above, so that the final collision time of the current vehicle and each crossing vehicle can be calculated.

[0112] Further, in some embodiments, after the collision vehicles meeting the preset collision risk condition are screened according to the final collision time, the collision vehicles are further divided into a first side risk vehicle set and a second side risk vehicle set based on the lateral distance between the geometric center of each target and the rear axle center of the current vehicle; and the collision vehicles in the first side risk vehicle set and the second side risk vehicle set are respectively subjected to longitudinal distance calculation to obtain a first side minimum longitudinal distance vehicle and a second side minimum longitudinal distance vehicle.

[0113] Optionally, the first side risk vehicle set can be a left side risk vehicle set, and the second side risk vehicle set can be a right side risk vehicle set, which are not limited herein.

[0114] Preferably, when the lateral distance between the geometric center of each target and the rear axle center of the current vehicle is greater than 0, the collision vehicles are divided into the first side risk vehicle set; and when the lateral distance between the geometric center of each target and the rear axle center of the current vehicle is less than or equal to 0, the collision vehicles are divided into the second side risk vehicle set.

[0115] Further, the collision vehicles in the left and right side risk vehicle sets are respectively subjected to longitudinal distance calculation to obtain a left side minimum longitudinal distance vehicle and a right side minimum longitudinal distance vehicle. In this way, the two crossing vehicles with the highest risk degree on the left and right sides of the current vehicle are obtained by calculation, so as to reduce the risk of vehicle collision and accident and improve the safety of the driver and passengers.

[0116] In order to enable those skilled in the art to understand the screening method of the crossing vehicle target of the present application, the following will be described in detail in combination with specific embodiments.

[0117] Specifically, in combination with Table 1 and FIG. 4, FIG. 4 is a schematic diagram of a target vehicle left boundary on the right side of the right boundary of the current vehicle and the speed direction of the target vehicle to the left (i.e. working condition 1 in Table 1) according to an embodiment of the present application, at this time, the lateral speed OBJ Vl of the target vehicle relative to the current vehicle is greater than the crossing speed judgment calibration value VL cal (the value range is between 0.3-0.6), and the left boundary OBJ LeB of the target vehicle is less than the right boundary self CR of the passable region of the current vehicle, the right boundary self CRthe difference between the left boundary of the target vehicle OBJ LeB and the left boundary of the current vehicle passable region self CL , the collision start distance threshold Objs Ts is obtained, and the square of the start speed threshold Vs sq is calculated by formula (13): OBJ Vl 2 + 2OBJ al * Objs Ts (13)

[0118] wherein OBJ Vl is the lateral speed of the target vehicle relative to the current vehicle, OBJ al is the lateral acceleration of the target vehicle relative to the current vehicle, and Objs Ts is the collision start distance threshold.

[0119] Further, the square of the end speed threshold Ve eq is calculated by formula (14): OBJ Vl 2 + 2OBJ al * Objs Te (14)

[0120] wherein OBJ Vl is the lateral speed of the target vehicle relative to the current vehicle, OBJ al is the lateral acceleration of the target vehicle relative to the current vehicle, and Objs Te is the collision end distance threshold.

[0121] Further, as shown in Table 1 and FIG. 5, FIG. 5 is a schematic diagram of the left boundary of the target vehicle on the left side of the left boundary of the current vehicle and the speed direction of the target vehicle being right (i.e. working condition 2 in Table 1) according to an embodiment of the present application, at this time, the lateral speed OBJ Vl of the target vehicle relative to the current vehicle is less than the opposite of the lateral crossing speed judgment calibration quantity VL cal , and the right boundary OBJ RiB of the target vehicle is greater than the left boundary self CL of the current vehicle passable region, the collision start distance threshold Objs Ts is obtained by calculating the difference between the right boundary OBJ RiB of the target vehicle and the left boundary self CL of the current vehicle passable region, and the collision end distance threshold Objs LeB is obtained by calculating the difference between the left boundary OBJ CR of the target vehicle and the right boundary self Te of the current vehicle passable region.CR , the collision start distance threshold Objs Te , and the square of the start speed threshold Vs sq and the square of the end speed threshold Ve eq .

[0122] Further, as shown in Table 1 and Fig. 6, Fig. 6 is a schematic diagram of the target vehicle left boundary being on the left side of the current vehicle right boundary, the target vehicle right boundary being on the right side of the current vehicle left boundary, and the target vehicle speed direction being leftward (i.e., Case 3 in Table 1) according to an embodiment of the present application, at this time the target vehicle transverse speed OBJ Vl relative to the current vehicle is greater than the transverse speed judgment calibration value VL cal , and the target vehicle left boundary OBJ LeB is greater than the current vehicle passable region right boundary self CR , and the target vehicle right boundary OBJ RiB is less than or equal to the current vehicle passable region left boundary self CL , at this time the collision start distance threshold Objs Ts is 0, the collision end distance threshold Objs CL is obtained by calculating the difference between the current vehicle passable region left boundary self RiB and the target vehicle right boundary OBJ Te , at this time the square of the start speed threshold Vs sq is 0, and the square of the end speed threshold Ve eq is obtained by formula (14).

[0123] Further, as shown in Table 1 and Fig. 7, Fig. 7 is a schematic diagram of the target vehicle left boundary being on the left side of the current vehicle right boundary, the target vehicle right boundary being on the right side of the current vehicle left boundary, and the target vehicle speed direction being rightward (i.e., Case 4 in Table 1) according to an embodiment of the present application, at this time the target vehicle transverse speed OBJ Vl relative to the current vehicle is less than the opposite of the transverse speed judgment calibration value VL cal , and the target vehicle right boundary OBJ RiB is less than or equal to the current vehicle passable region left boundary self CL , and the target vehicle left boundary OBJ LeB is greater than or equal to the current vehicle passable region right boundary self CR , at this time the collision start distance threshold Objs Ts is 0, the collision end distance threshold Objs LeB is obtained by calculating the difference between the target vehicle left boundary OBJ CR and the current vehicle passable region right boundary selfTe , the square of the start speed threshold value Vs sq is 0, and the square of the end speed threshold value Ve eq .

[0124] Table 1

[0125] Further, the minimum and maximum collision times of each target vehicle that can occur are calculated in the form of pseudo code for each of the four working conditions in Table 1: Ts ,OBJ Te ]:

[0126] For working condition 1 and working condition 2:

[0127] For working condition 3 and working condition 4:

[0128] wherein aL cal is a lateral acceleration judgment calibration quantity, and the value range is between 0.05 and 0.15.

[0129] Further, the final collision time with each target vehicle is calculated according to the minimum and maximum collision times of the current vehicle and each target vehicle, and the pseudo code is as follows:

[0130] wherein Tsf is the collision start time, and Tef is the collision end time.

[0131] Further, it is judged whether each target vehicle has a collision risk according to Tsf and Tef. If Tef≤Tsf, there is no collision risk, otherwise, there is a collision risk, and the target vehicle is accumulated when there is a collision risk.

[0132] Further, the target vehicles with a collision risk are classified, and are divided into a left vehicle set (number n l ) and a right vehicle set (number n r ) according to the positions of the target vehicles relative to the current vehicle, and the longitudinal distances of the vehicles in the left vehicle set (number n l ) and the right vehicle set (number n r ) are calculated, so as to obtain the vehicles OBJ_L and OBJ_R at the nearest longitudinal positions on the left and right sides.

[0133] Therefore, the vehicle set crossing the current vehicle can be detected, and the two target vehicles with the highest danger degree on the left and right sides of the current vehicle and the collision time of the vehicle with the collision risk can be calculated, thereby improving the safety.

[0134] According to the screening method for the crossing vehicle target provided in the embodiments of the present application, the attribute information of the vehicle and the surrounding targets is obtained, the target vehicle meeting the condition is screened out, the crossing vehicle is determined and the final collision time is calculated, and the collision vehicle meeting the collision risk condition is screened out. Therefore, the crossing vehicle in the horizontal and longitudinal detection area is screened out, and the collision time of the collision vehicle is calculated based on the crossing vehicle, thereby solving the problems in the related art, such as the difficulty in accurately identifying and classifying the crossing vehicle and the complexity of the algorithm, and the required computing power is small and the calculation speed is fast.

[0135] Next, the screening device for the crossing vehicle target provided in the embodiments of the present application is described with reference to the accompanying drawings.

[0136] FIG. 8 is a block schematic diagram of the screening device for the crossing vehicle target according to the embodiments of the present application.

[0137] As shown in FIG. 8, the screening device for the crossing vehicle target 10 includes an obtaining module 100, a first screening module 200 and a second screening module 300.

[0138] The obtaining module 100 is configured to obtain vehicle information of a current vehicle and attribute information of a plurality of surrounding targets. The first screening module 200 is configured to screen at least one target vehicle meeting a preset condition from the plurality of surrounding targets based on the attribute information, and determine all crossing vehicles in a preset horizontal and longitudinal detection area according to the vehicle information and the attribute information of the at least one target vehicle. The second screening module 300 is configured to calculate a final collision time of the current vehicle and each crossing vehicle according to the attribute information of the all crossing vehicles and the vehicle information, and screen a collision vehicle meeting a preset collision risk condition according to the final collision time.

[0139] Further, in some embodiments, the vehicle information includes a vehicle speed of the current vehicle, a width of the current vehicle, a distance from a front edge of the current vehicle to a rear axle center of the current vehicle, a distance between the current vehicle and two sides of a road, a horizontal sensing accuracy of the current vehicle and a longitudinal sensing accuracy of the current vehicle. The attribute information includes a confidence of each target, a type of each target, a horizontal speed of each target relative to the current vehicle, a horizontal acceleration of each target relative to the current vehicle, a horizontal width of each target relative to the current vehicle, a longitudinal length of each target relative to the current vehicle, a longitudinal distance between a geometric center of each target and a rear axle center of the current vehicle, and a horizontal distance between the geometric center of each target and the rear axle center of the current vehicle.

[0140] Further, in some embodiments, the first screening module 200 is configured to: screen at least one initial target whose confidence is greater than a preset confidence threshold based on the confidence of each target; and exclude non-vehicle targets from the at least one initial target to obtain at least one target vehicle based on the type of each target.

[0141] Further, in some embodiments, the first screening module 200 is configured to: calculate a mapping lateral coordinate of each target vehicle by calculating a lateral distance between a geometric center of each target vehicle and a lane center line of a current vehicle based on a lane line coordinate system of the current vehicle, and integrating the lane center line of the current vehicle based on a position of the current vehicle and a projection point of a lateral distance between the geometric center of each target vehicle and a rear axle center of the current vehicle to the lane center line of the current vehicle; determine a lateral detection area and a longitudinal detection area based on a speed of the current vehicle, distances of the current vehicle to two sides of a road, a lateral sensing accuracy of the current vehicle, and a longitudinal sensing accuracy of the current vehicle; and exclude target vehicles not in the lateral detection area and the longitudinal detection area based on the mapping lateral coordinate of each target vehicle and the mapping longitudinal coordinate of each target vehicle to obtain all crossing vehicles.

[0142] Further, in some embodiments, the second screening module 300 is configured to: calculate a maximum distance and a minimum distance between the current vehicle and each target vehicle according to a first preset margin and a second preset margin based on a longitudinal distance between a geometric center of each target vehicle and a rear axle center of the current vehicle, a distance from a front edge of the current vehicle to the rear axle center of the current vehicle, and a lateral width of each target vehicle relative to the current vehicle; calculate a maximum collision time and a minimum collision time between the current vehicle and each target vehicle based on the maximum distance, the minimum distance, and a speed of the current vehicle, and determine a passable area of the current vehicle based on a bias amount determined based on a width of the current vehicle and a type of each crossing vehicle, and calculate a left boundary and a right boundary between the current vehicle and each crossing vehicle based on a lateral distance between the geometric center of each target vehicle and the rear axle center of the current vehicle, and the lateral width of each target vehicle relative to the current vehicle; and calculate a final collision time between the current vehicle and each crossing vehicle based on the maximum collision time, the minimum collision time, a lateral speed of each crossing vehicle, the passable area of the current vehicle, the left boundary and the right boundary between the current vehicle and each crossing vehicle.

[0143] Further, in some embodiments, after the collision vehicles meeting the preset collision risk condition are screened out according to the final collision time, the second screening module 300 is further configured to: divide the collision vehicles into a first side risk vehicle set and a second side risk vehicle set based on the lateral distance between the geometric center of each target and the rear axle center of the current vehicle; and perform longitudinal distance calculation on the collision vehicles in the first side risk vehicle set and the second side risk vehicle set respectively to obtain a first side minimum longitudinal distance vehicle and a second side minimum longitudinal distance vehicle.

[0144] It should be noted that the foregoing explanation of the embodiment of the screening method for the crossing vehicle target also applies to the screening device for the crossing vehicle target of this embodiment, which will not be described here again.

[0145] The screening device for the crossing vehicle target according to the embodiment of the present application obtains the attribute information of the vehicle and the surrounding targets, screens out the target vehicles meeting the conditions, determines the crossing vehicles and calculates the final collision time, and screens out the collision vehicles meeting the collision risk condition. Therefore, by screening out the crossing vehicles in the horizontal and longitudinal detection area and calculating the collision time of the collision risk vehicles based on the crossing vehicles, the problems such as the difficulty in accurately identifying and classifying the crossing vehicles and the complex algorithm calculation in the related art are solved, and the required computing power is small and the calculation speed is fast.

[0146] FIG. 9 is a structural schematic diagram of a vehicle according to an embodiment of the present application. The vehicle can include:

[0147] The memory 901, the processor 902, and the computer program stored in the memory 901 and executable on the processor 902.

[0148] The processor 902 implements the screening method for the crossing vehicle target provided in the above embodiments when executing the program.

[0149] Further, the vehicle further includes:

[0150] The communication interface 903 is configured to communicate between the memory 901 and the processor 902.

[0151] The memory 901 is configured to store the computer program executable on the processor 902.

[0152] The memory 901 can include a high-speed RAM memory, and can also include a non-volatile memory such as at least one disk memory.

[0153] If the memory 901, the processor 902 and the communication interface 903 are implemented independently, the communication interface 903, the memory 901 and the processor 902 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in FIG. 9, but it does not mean that there is only one bus or only one type of bus.

[0154] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can complete communication between each other through an internal interface.

[0155] The processor 902 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0156] The embodiment also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the above-mentioned screening method for crossing vehicle targets.

[0157] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0158] Moreover, the terms "first", "second", "third", etc. are used herein only to describe different steps or categories of steps in a claim for patent purposes, and are not to be construed as implying or implying relative importance of one feature to another feature. Thus, features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise explicitly specified.

[0159] Any process or method descriptions or descriptions of the flow diagrams described herein, or otherwise described herein, can be understood as representing the modules, segments, or portions of code that include executable instructions for performing custom logic functions or processes, and the scope of preferred embodiments of the present application includes additional implementations that can not be expressly shown or described herein, including implementations that can be performed in a different order, including substantially simultaneously, or in reverse order, depending on the functionality involved, as would be understood by those skilled in the art of the embodiments described herein.

[0160] The logic and / or steps represented in the flow diagrams described herein, or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, which can be specifically embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a processor-based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with these instructions. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device, or in conjunction with these instructions. More specific examples (non-exhaustive list) of computer-readable medium include the following: electrical connections having one or more wires (electronic devices), portable computer diskette (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by electronic editing, interpretation, or necessary processing, and then stored in a computer memory, if necessary.

[0161] It should be understood that portions of the application can be realized with a combination of hardware, software, firmware, or their combination. In the above-described embodiments, the N steps or methods can be realized with software or firmware stored in a memory and executed by a suitable instruction execution system. As in another embodiment, if realized with hardware, any one or their combination of the following technologies known in the art can be used: discrete logic circuit with logic gate circuit for implementing logic functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0162] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiments can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0163] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0164] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A method for screening a crossing vehicle target, characterized in that: The following steps are involved: Obtain vehicle information of the current vehicle and attribute information of multiple surrounding targets; Based on the attribute information, at least one target vehicle that meets a preset condition is screened out from the plurality of surrounding targets, and all crossing vehicles in a preset transverse and longitudinal detection area are determined based on the vehicle information and the attribute information of the at least one target vehicle; The final collision time between the current vehicle and each crossing vehicle is calculated based on the attribute information of all crossing vehicles and the vehicle information, and collision vehicles that meet a preset collision risk condition are screened out based on the final collision time.

2. The method according to claim 1, characterized in that The vehicle information includes the speed of the current vehicle, the width of the current vehicle, the distance from the front edge of the current vehicle to the center of the rear axle of the current vehicle, the distance between the current vehicle and the curbs on both sides, the lateral sensing accuracy of the current vehicle and the longitudinal sensing accuracy of the current vehicle; the attribute information includes the confidence of each target, the type of each target, the lateral speed of each target relative to the current vehicle, the lateral acceleration of each target relative to the current vehicle, the lateral width of each target relative to the current vehicle, the longitudinal length of each target relative to the current vehicle, the longitudinal distance between the geometric center of each target and the center of the rear axle of the current vehicle, and the lateral distance between the geometric center of each target and the center of the rear axle of the current vehicle.

3. The method for screening crossing vehicle targets according to claim 2, characterized in that: The step of selecting at least one target vehicle that meets a preset condition from the plurality of surrounding targets based on the attribute information includes: Based on the confidence of each target, screening out at least one initial target whose confidence is greater than a preset confidence threshold; Based on the type of each target, non-vehicle targets are filtered out from the at least one initial target to obtain the at least one target vehicle.

4. The method for screening a crossing vehicle target according to claim 2 or 3, characterized in that: The determining, based on the vehicle information and the attribute information of the at least one target vehicle, all crossing vehicles in a preset transverse and longitudinal detection area includes: Taking the lane line coordinate system of the current vehicle as a reference, calculating the lateral distance between the geometric center of each target vehicle and the center line of the lane in which the current vehicle is located to obtain the mapped abscissa of each target vehicle, and integrating the center line of the lane in which the current vehicle is located based on the current vehicle position and the lateral distance between the geometric center of each target and the center of the rear axle of the current vehicle to the projection point of the lane in which the current vehicle is located to obtain the mapped ordinate of each target vehicle; Determining a lateral detection area and a longitudinal detection area according to the current vehicle speed, the distance between the current vehicle and the curbs on both sides, the lateral sensing accuracy of the current vehicle, and the longitudinal sensing accuracy of the current vehicle; The target vehicles that are not in the lateral detection area and the longitudinal detection area are screened out based on the mapped horizontal coordinate of each target vehicle and the mapped vertical coordinate of each target vehicle to obtain all the crossing vehicles.

5. The method for screening a crossing vehicle target according to claim 4, characterized in that: The calculating, based on the attribute information of all crossing vehicles and the vehicle information, a final collision time between the current vehicle and each crossing vehicle, includes: Based on the longitudinal distance between the geometric center of each target and the center of the rear axle of the current vehicle, the distance from the front edge of the current vehicle to the center of the rear axle of the current vehicle, and the lateral width of each target relative to the current vehicle, respectively calculating the maximum distance and the minimum distance between the current vehicle and each target vehicle according to a first preset margin and a second preset margin; The distance between the current vehicle and each target vehicle is calculated based on the maximum distance, the minimum distance and the speed of the current vehicle. The maximum collision time and the minimum collision time of the target vehicle are determined, and the traversable area of ​​the current vehicle is determined according to the offset determined by the width of the current vehicle and the type of each crossing vehicle, and the left boundary and the right boundary between the current vehicle and each crossing vehicle are calculated according to the lateral distance between the geometric center of each target and the center of the rear axle of the current vehicle and the lateral width of each target relative to the current vehicle; The final collision time between the current vehicle and each crossing vehicle is calculated according to the maximum collision time, the minimum collision time, the lateral speed of each crossing vehicle, the traversable area of ​​the current vehicle, and the left and right boundaries of the current vehicle and each crossing vehicle.

6. The method for screening crossing vehicle targets according to claim 2, characterized in that: After selecting the collision vehicles that meet the preset collision risk condition according to the final collision time, the method further includes: Based on the lateral distance between the geometric center of each target and the rear axle center of the current vehicle, dividing the collision vehicles into a first side risk vehicle set and a second side risk vehicle set; Longitudinal distances are calculated for the collision vehicles in the first side risk vehicle set and the second side risk vehicle set respectively to obtain a first side minimum longitudinal distance vehicle and a second side minimum longitudinal distance vehicle.

7. A screening device for a target crossing a vehicle, characterized in that: include: The acquisition module is used to obtain vehicle information of the current vehicle and attribute information of multiple surrounding targets; a first screening module, configured to screen out at least one target vehicle that meets a preset condition from the plurality of surrounding targets based on the attribute information, and determine all crossing vehicles in a preset transverse and longitudinal detection area based on the vehicle information and the attribute information of the at least one target vehicle; The second screening module is used to calculate the final collision time between the current vehicle and each crossing vehicle based on the attribute information of all crossing vehicles and the vehicle information, and to screen out collision vehicles that meet the preset collision risk conditions based on the final collision time.

8. The device for screening objects crossing a vehicle according to claim 7, characterized in that: The vehicle information includes the speed of the current vehicle, the width of the current vehicle, the distance from the front edge of the current vehicle to the center of the rear axle of the current vehicle, the distance between the current vehicle and the curbs on both sides, the lateral sensing accuracy of the current vehicle and the longitudinal sensing accuracy of the current vehicle; the attribute information includes the confidence of each target, the type of each target, the lateral speed of each target relative to the current vehicle, the lateral acceleration of each target relative to the current vehicle, the lateral width of each target relative to the current vehicle, the longitudinal length of each target relative to the current vehicle, the longitudinal distance between the geometric center of each target and the center of the rear axle of the current vehicle, and the lateral distance between the geometric center of each target and the center of the rear axle of the current vehicle.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for screening a crossing vehicle target according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for screening a crossing vehicle target according to any one of claims 1 to 6.

Images