Curve scene lane nearest preceding vehicle screening method and storage medium

Abstract

The invention discloses a curve scene local lane nearest preceding vehicle screening method, which comprises the following steps: S1, based on target information, calculating an overlapping rate of a target and a local vehicle and a target lane attribution, selecting a target with the nearest distance in a local lane as a nearest preceding vehicle, and recording a distance Xc between the nearest preceding vehicle and the local vehicle; s2, judging whether the vehicle is located at a curve of the vehicle or not; if the vehicle is in the curve, executing the step S3, otherwise, executing the step S4; s3, according to the curvature mean value T of the left and right lane lines and the vehicle speed V, obtaining a longitudinal distance threshold Xt for avoiding error screening through two-dimensional table look-up; if Xc is greater than Xt, correcting the target as a vehicle which is not closest to the lane; and S4, transmitting the screened information of the nearest preceding vehicle on the lane to an expected acceleration planning module of the adaptive cruise control system. According to the invention, the situation that vehicles in other lanes are wrongly identified as the nearest preceding vehicle in the lane in the curve scene can be avoided, the accuracy of identifying the nearest preceding vehicle in the lane in the curve scene can be improved, and mass production is easy to realize and popularize.

Description

Technical Field

[0001] The present invention relates to the field of automobiles, and in particular to a method for screening the nearest preceding vehicle in a lane in a curve scene and a storage medium. Background Art

[0002] Adaptive cruise control system is an important part of advanced driver assistance and unmanned driving systems. The key is to provide reliable longitudinal control capabilities to ensure vehicle driving safety and riding comfort. Adaptive cruise control systems usually consist of target recognition, the nearest preceding vehicle screening in the same lane, expected acceleration planning and longitudinal control modules. The requirement for the nearest preceding vehicle screening in the same lane is to accurately identify the nearest vehicle in the same lane to avoid misjudgment and wrong response to vehicles in other lanes.

[0003] The existing mass-produced adaptive cruise control system has limitations in perception, especially in curved scenarios, where the accuracy of target recognition and the insufficient effective length of lane line recognition are more prominent. Due to these limitations, the system may mistakenly identify vehicles in other lanes as the nearest preceding vehicle in the lane, resulting in misjudgment and triggering unnecessary braking operations. This misbraking behavior not only seriously affects the smoothness and comfort of driving, but also reduces the user's trust and satisfaction with the system, and may even lead to user dissatisfaction and vehicle withdrawal. Therefore, it is necessary to propose an effective method to accurately identify the nearest preceding vehicle in the lane to avoid the above problems. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention, which are all simplifications of the prior art in the field, and will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention of the present invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] The technical problem to be solved by the present invention is to provide a method for screening the nearest preceding vehicle in a lane in a curved scene, which can avoid misidentification of the nearest preceding vehicle in the lane in a curved scene.

[0006] In order to solve the above technical problems, the present invention provides a method for screening the nearest preceding vehicle in a lane in a curve scene, comprising the following steps:

[0007] S1, based on the target information, calculate the overlap rate between the target and the vehicle and the target lane, select the closest target in the lane as the nearest preceding vehicle, and record the distance X between the nearest preceding vehicle and the vehicle. c ;

[0008] S2, based on the curvature of the lane lines on the left and right sides of the vehicle, determine whether the vehicle is in a curve; if the vehicle is in a curve, execute step S3, otherwise execute step S4;

[0009] S3, according to the curvature mean T of the left and right lane lines and the vehicle speed V, obtain the longitudinal distance threshold X to avoid misselection through a two-dimensional table lookup t , the two-dimensional table is obtained by calibration; if X c Greater than X t Correct the target to the nearest preceding vehicle in a non-entity lane;

[0010] S4, transmitting the filtered information of the nearest preceding vehicle in the lane to the expected acceleration planning module of the adaptive cruise control system.

[0011] Preferably, the method for screening the nearest preceding vehicle in the lane in a curve scene is further improved, and step S1 comprises:

[0012] S1.1, establish the lane coordinate system and the ego vehicle coordinate system; the lane coordinate system can be established based on the lane line, curb and fence information; the ego vehicle coordinate system can be established based on the rear axle center of the ego vehicle as the origin;

[0013] S1.2, obtaining surrounding target information; the surrounding target information is obtained based on a single on-board sensor (radar, camera, lidar, etc.) or multi-sensor fusion information;

[0014] S1.3, converting the target information to the ego vehicle coordinate system and calculating the overlap rate between the ego vehicle and each target;

[0015] The overlap rate between the vehicle and each target can be calculated by any of the following methods: Axis-Aligned Bounding Box IoU, Rotated or Oriented Bounding Box IoU, Multi-dimensional IoU, Weighted IoU, Pixel-level IoU, Deep learning model to calculate overlap rate, Geometric library to calculate overlap rate, Computer vision technology to calculate overlap rate;

[0016] 1.4, convert the target information into the road coordinate system and determine the lane to which each target belongs;

[0017] The lane to which each target belongs can be determined by any of the following methods: judgment based on map and lane marking data, visual recognition, sensor fusion, machine learning and deep learning, V2X communication, GPS and inertial measurement unit;

[0018] S1.5, based on the overlap rate between the target and the vehicle and the target lane affiliation, select the closest target in the lane as the nearest preceding vehicle.

[0019] Preferably, the method for screening the nearest preceding vehicle in the lane in a curve scenario is further improved, and the target information includes target position information, target speed and target direction.

[0020] Preferably, the method for screening the nearest preceding vehicle in the lane in the curved scene is further improved, when the average curvature T1 of the left and right lane lines is greater than the preset threshold value T t , it is judged that the vehicle is in a curve.

[0021] In order to solve the above technical problems, the present invention provides a computer-readable storage medium, which stores a computer program therein. When the computer program is executed, it is used to implement the steps in any one of the above-mentioned methods for screening the nearest preceding vehicle in the lane in a curve scenario.

[0022] The present invention calculates the overlap rate between the target and the own vehicle and the target lane affiliation, preliminarily screens and obtains the closest preceding vehicle in the own lane, and then determines whether the current scene is prone to misjudgment. If it is a curve scene, the longitudinal distance threshold for avoiding misjudgment is obtained according to the mean curvature of the left and right lane lines and the own vehicle speed V. The preliminarily screened and obtained nearest preceding vehicle in the own lane is corrected by the longitudinal distance threshold, which can avoid the situation where vehicles in other lanes are mistakenly identified as the nearest preceding vehicle in the own lane in a curve scene. The present invention can improve the accuracy of identifying the nearest preceding vehicle in the own lane in a curve scene, and is easy to implement and promote in mass production. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings of the present invention are intended to illustrate the general characteristics of the methods, structures and / or materials used in specific exemplary embodiments of the present invention, and to supplement the description in the specification. However, the drawings of the present invention are schematic diagrams not drawn to scale, and thus may not accurately reflect the precise structure or performance characteristics of any given embodiment, and the drawings of the present invention should not be interpreted as limiting or restricting the range of values ​​or properties covered by the exemplary embodiments of the present invention. The present invention is further described in detail below in conjunction with the drawings and specific embodiments:

[0024] Figure 1 It is a schematic diagram of the vehicle coordinate system.

[0025] Figure 2 It is a schematic diagram of the two-dimensional query of the longitudinal distance threshold of the present invention. DETAILED DESCRIPTION

[0026] The following is an explanation of the embodiments of the present invention by specific specific embodiments, and those skilled in the art can fully understand other advantages and technical effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through different specific embodiments, and the details in this specification can also be applied based on different viewpoints, and various modifications or changes can be made without deviating from the general design concept of the invention. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. The following exemplary embodiments of the present invention can be implemented in a variety of different forms and should not be interpreted as being limited to the specific embodiments described herein. It should be understood that these embodiments are provided to make the disclosure of the present invention thorough and complete, and to fully convey the technical solutions of these exemplary specific embodiments to those skilled in the art. It should be understood that when an element is referred to as "connected" or "coupled" to another element, the element can be directly connected or coupled to another element, or there can be an intermediate element. The difference is that when an element is referred to as "directly connected" or "directly coupled" to another element, there is no intermediate element. In all figures, the same reference numerals always represent the same element. As used herein, the term "and / or" includes any combination and all combinations of one or more related listed items.

[0027] First embodiment,

[0028] The present invention provides a method for screening the nearest preceding vehicle in a lane in a curve scene, comprising the following steps:

[0029] S1, based on the target information, calculate the overlap rate between the target and the vehicle and the target lane, select the closest target in the lane as the nearest preceding vehicle, and record the distance X between the nearest preceding vehicle and the vehicle. c ;

[0030] S2: Based on the curvature of the lane lines on the left and right sides of the vehicle, determine whether the vehicle is in a curve; when the average value T of the curvature of the lane lines on the left and right sides is greater than the preset threshold value T t When the vehicle is in a curve, it is determined that the vehicle is in a curve; if the vehicle is in a curve, step S3 is executed, otherwise step S4 is executed;

[0031] S3, according to the curvature mean T of the left and right lane lines and the vehicle speed V, obtain the longitudinal distance threshold X to avoid misselection through a two-dimensional table lookup t , the two-dimensional table is obtained by calibration; if X c Greater than X t Correct the target to the nearest preceding vehicle in a non-entity lane;

[0032] S4, transmitting the filtered information of the nearest preceding vehicle in the lane to the expected acceleration planning module of the adaptive cruise control system.

[0033] Wherein, step S1 comprises:

[0034] S1.1, establish the lane coordinate system and the vehicle coordinate system;

[0035] S1.2, obtain surrounding target information;

[0036] S1.3, converting the target information to the ego vehicle coordinate system and calculating the overlap rate between the ego vehicle and each target;

[0037] S1.4, converting the target information into a road coordinate system and determining the lane to which each target belongs;

[0038] S1.5, based on the overlap rate between the target and the vehicle and the target lane affiliation, select the closest target in the lane as the nearest preceding vehicle.

[0039] Optionally, the surrounding target information is obtained based on a single on-board sensor or multi-sensor fusion information. The vehicle coordinate system is established based on the center of the rear axle of the vehicle as the origin. The target information includes target position information, target speed and target orientation.

[0040] Second embodiment;

[0041] The present invention provides a computer-readable storage medium, which stores a computer program therein. When the computer program is executed, it is used to implement the steps of the method for screening the nearest preceding vehicle in the lane in a curve scenario described in the first embodiment.

[0042] The computer-readable medium includes permanent and non-permanent, removable and non-removable media and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0043] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. It will also be understood that, unless expressly defined herein, terms such as those defined in general dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not interpreted in an ideal or overly formal sense.

[0044] The present invention has been described in detail above through specific implementation modes and embodiments, but these do not constitute limitations of the present invention. Without departing from the principles of the present invention, those skilled in the art may also make many variations and improvements, which should also be regarded as the protection scope of the present invention.

Claims

1. A method for screening the nearest preceding vehicle in a lane in a curve scene, characterized in that: The following steps are involved: S1, based on the target information, calculate the overlap rate between the target and the vehicle and the target lane, select the closest target in the lane as the nearest preceding vehicle, and record the distance X between the nearest preceding vehicle and the vehicle. c ; S2, based on the curvature of the lane lines on the left and right sides of the vehicle, determine whether the vehicle is in a curve; if the vehicle is in a curve, execute step S3, otherwise execute step S4; S3, according to the curvature mean T of the left and right lane lines and the vehicle speed V, obtain the longitudinal distance threshold X to avoid misselection through a two-dimensional table lookup t , the two-dimensional table is obtained by calibration; if X c Greater than X t Correct the target to the nearest preceding vehicle in a non-entity lane; S4, transmitting the filtered information of the nearest preceding vehicle in the lane to the expected acceleration planning module of the adaptive cruise control system.

2. The method for screening the nearest preceding vehicle in a lane in a curve scene according to claim 1, characterized in that: Step S1 includes: S1.1, establish the lane coordinate system and the vehicle coordinate system; S1.2, obtain surrounding target information; S1.3, converting the target information to the ego vehicle coordinate system and calculating the overlap rate between the ego vehicle and each target; S1.4, converting the target information into a road coordinate system and determining the lane to which each target belongs; S1.5, based on the overlap rate between the target and the vehicle and the target lane affiliation, select the closest target in the lane as the nearest preceding vehicle.

3. The method for screening the nearest preceding vehicle in a lane in a curve scene according to claim 2, characterized in that: The surrounding target information is obtained based on a single on-board sensor or multi-sensor fusion information.

4. The method for screening the nearest preceding vehicle in a lane in a curve scene according to claim 2, characterized in that: The vehicle coordinate system is established with the center of the rear axle of the vehicle as the origin.

5. The method for screening the nearest preceding vehicle in a lane in a curve scene according to claim 2, characterized in that: Target information includes target position information, target speed and target direction.

6. The method for screening the nearest preceding vehicle in a lane in a curve scene according to claim 1, characterized in that: When the average curvature of the left and right lane lines T is greater than the preset threshold value T t , it is judged that the vehicle is in a curve.

7. A computer-readable storage medium, characterized in that: A computer program is stored therein, and when the computer program is executed, it is used to implement the steps in the method for screening the nearest preceding vehicle in the lane in a curve scene as described in any one of claims 1-6.

Images