Vehicle adaptive cruise target screening method, device and equipment and storage medium

Abstract

The invention provides a vehicle adaptive cruise target screening method and device, equipment and a storage medium, and can be applied to the technical field of vehicle adaptive cruise. The method comprises the following steps: acquiring image detection data in front of a vehicle through a vehicle-mounted camera, and acquiring an image tracking target and a current lane where the vehicle is located based on the image detection data; acquiring radar detection data in front of a vehicle through a vehicle-mounted radar, and acquiring a radar tracking target based on the radar detection data; performing target fusion on the image tracking target and the radar tracking target to obtain a fusion target; screening a fusion target which continuously meets a target screening condition within a preset duration as a potential car-following target; wherein the target screening condition comprises a pixel layer screening condition and a world layer screening condition; and screening the potential car-following target with the minimum longitudinal distance from the car as a cruise car-following target. According to the method provided by the invention, the pixel layer screening and the world layer screening are combined, so that the accuracy of adaptive cruise target screening is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle adaptive cruise technology, and in particular to a vehicle adaptive cruise target screening method, device, equipment and storage medium. Background Art

[0002] Adaptive Cruise Control (ACC) is an intelligent automatic control system designed to improve driving comfort and safety. ACC is developed based on traditional cruise control technology, which allows the vehicle cruise control system to adapt to traffic conditions by adjusting the speed.

[0003] During the operation of the vehicle's adaptive cruise control system, target screening is a key step in adaptive cruise control, which determines which vehicles or obstacles will be regarded by the vehicle cruise control system as objects that need to be tracked or kept at a safe distance.

[0004] However, the existing target screening methods have the problem of low accuracy in cruise following target screening. This is because the existing target screening methods perform target screening based on the relative position between the target vehicle and the cruise vehicle. In complex road conditions, vehicles are prone to frequent bumps and shakes, which can cause changes in the vehicle's posture and even the installation posture of the on-board sensors (on-board cameras, on-board radars), resulting in deviations between the data of the target vehicle and lane lines after coordinate conversion and the actual position, causing ACC to mis-follow or miss the target, or even cause a collision, which significantly affects the accuracy of adaptive cruise control and the safety of the system. Summary of the invention

[0005] The present application provides a vehicle adaptive cruise target screening method, device, equipment and storage medium, which are used to solve the problem of low accuracy of cruise following target screening in existing target screening methods.

[0006] According to a first aspect disclosed in the present application, the present application provides an adaptive cruise target screening method, comprising:

[0007] Acquire image detection data in front of the vehicle through a vehicle-mounted camera, and acquire an image tracking target and a current lane where the vehicle is located based on the image detection data;

[0008] Acquire radar detection data in front of the vehicle through the vehicle-mounted radar, and acquire a radar tracking target based on the radar detection data;

[0009] Fusing the image tracking target and the radar tracking target to obtain a fused target;

[0010] Filtering fused targets that continuously meet target screening conditions within a preset time as potential vehicle-following targets; wherein the target screening conditions include pixel layer screening conditions and world layer screening conditions;

[0011] Select the potential following target with the smallest longitudinal distance to the vehicle as the cruising following target.

[0012] In a feasible implementation manner, the pixel layer screening condition includes that the fusion target is in the current lane, and the intrusion rate of the fusion target intruding into the current lane is greater than a first judgment threshold;

[0013] The world layer screening condition includes that the distance between the fusion target and the center line of the current lane is less than the tightening width.

[0014] In a feasible implementation manner, the pixel layer screening condition includes that the fusion target is in the current lane, and the intrusion rate of the fusion target intruding into the current lane is greater than a second judgment threshold;

[0015] The world layer screening condition includes that a lateral distance between the fusion target and the vehicle is less than a minimum value of a minimum turning radius screening threshold and a lane width of the current lane.

[0016] In a feasible implementation manner, obtaining the image tracking target and the current lane where the vehicle is located based on the image detection data includes:

[0017] Input the image detection data into the detection and recognition model to obtain image tracking target and lane line point data; wherein the detection and recognition model includes a tracking target recognition sub-model and a lane recognition sub-model obtained based on neural network model training;

[0018] Tracking the image tracking target based on a target tracking model, and obtaining a target frame and target motion attributes of the image tracking target; wherein the target tracking model is constructed based on a visual target tracking algorithm, and the target motion attributes include a longitudinal distance and a lateral distance from the vehicle, and a longitudinal speed and a lateral speed relative to the vehicle;

[0019] The lane line point data is subjected to curve fitting and filtering tracking processing to obtain the lane line and lane information of the current lane; wherein the lane information includes lane width and the distance between the image tracking target and the center line of the current lane.

[0020] In a feasible implementation manner, the method further includes:

[0021] If any point of the bottom edge of the target frame is within the lane line of the current lane, it is determined that the image tracking target is within the current lane, and the intrusion rate of the image tracking target into the current lane is obtained; wherein the intrusion rate is the ratio between the area of ​​the target frame intruding into the current lane and the area of ​​the target frame.

[0022] In a feasible implementation manner, the method further includes:

[0023] If any point of the bottom edge of the target frame is not within the current lane, it is determined that the image tracking target is not within the current lane.

[0024] In a feasible implementation manner, the image tracking target and the radar tracking target are fused to obtain a fused target, including:

[0025] The image tracking target and the radar tracking target are matched and screened, and when the deviation between the target motion attribute of the image tracking target and the target motion attribute of the radar tracking target is within a preset deviation range, the image tracking target and the radar tracking target are associated as a fusion target.

[0026] According to a second aspect disclosed in the present application, the present application provides an adaptive cruise target screening device, comprising:

[0027] An image detection module is used to obtain image detection data in front of the vehicle through a vehicle-mounted camera, and obtain an image tracking target and a current lane where the vehicle is located based on the image detection data;

[0028] A radar monitoring module, used to obtain radar detection data in front of the vehicle through a vehicle-mounted radar, and obtain a radar tracking target based on the radar detection data;

[0029] A target fusion module is used to fuse the image tracking target and the radar tracking target to obtain a fused target;

[0030] The target screening module is used to screen the fused targets that continuously meet the target screening conditions within a preset time as potential following targets; wherein the target screening conditions include world layer screening conditions or pixel layer screening conditions; and screen the potential following targets with the smallest longitudinal distance to the vehicle as cruising following targets.

[0031] According to a third aspect disclosed in the present application, the present application provides an electronic device, including a processor, and a memory communicatively connected to the processor;

[0032] The memory stores computer-executable instructions;

[0033] The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of the first aspects.

[0034] According to the fourth aspect disclosed in the present application, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement any method in the first aspect.

[0035] According to a fifth aspect disclosed in the present application, the present application provides a computer program product, including a computer program, and when the computer program is executed, it is used to implement any one of the methods in the first aspect.

[0036] Compared with the prior art, this application has the following beneficial effects:

[0037] The present application provides a vehicle adaptive cruise target screening method, device, equipment and storage medium, which utilizes the characteristic that the relative position relationship of the target on the image at the pixel level will not be affected by the calibration conversion accuracy of the coordinate system, combines the pixel layer screening and the world layer screening to complement each other, and performs multiple screening judgments through pixel layer screening and world layer screening, thereby effectively improving the accuracy of adaptive cruise target screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] Figure 1 A flowchart of an adaptive cruise target screening method provided in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of a flow chart of another adaptive cruise target screening method provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of target intrusion determination provided in an embodiment of the present application;

[0042] Figure 4 A schematic diagram of a target screening area provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of the structure of an adaptive cruise target screening device provided in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0045] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0046] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0047] Adaptive Cruise Control (ACC) is an intelligent automatic control system designed to improve driving comfort and safety. ACC is developed based on traditional cruise control technology, which allows the vehicle cruise control system to adapt to traffic conditions by adjusting the speed. The vehicle cruise control system relies on the on-board sensors (on-board cameras, on-board radars, etc.) installed in front of the vehicle to obtain perception information. When the road ahead is clear, ACC will maintain the set maximum cruising speed to move forward; when there is a vehicle ahead, ACC will reduce the speed as needed to maintain the distance from the vehicle ahead based on the selected time until the appropriate cruising speed is reached. Thanks to this, adaptive cruise can greatly reduce the driver's fatigue during long-distance driving.

[0048] During the operation of the vehicle's adaptive cruise control system, target screening is a key step in adaptive cruise control, which determines which vehicles or obstacles will be regarded by the vehicle cruise control system as objects that need to be tracked or kept at a safe distance.

[0049] However, the existing target screening methods have the problem of low accuracy in cruise following target screening. This is because the existing target screening methods screen targets based on the relative position between the target vehicle and the cruise vehicle. Before the target data and lane line data obtained by the vehicle's onboard sensors (onboard cameras, onboard radars, etc.) are output to the target screening module of the vehicle cruise control system, they generally need to go through steps such as coordinate conversion to convert the positions of the target vehicle and the lane line to the world layer coordinate system with the cruise vehicle's front position (or onboard sensor) as the origin, so as to obtain the relative position between the target vehicle and the cruise vehicle.

[0050] In this process, the accuracy of the on-board sensor calibration largely determines the accuracy of target screening. In complex road conditions, the vehicle is prone to frequent bumps and shakes, which causes changes in the vehicle posture and even the installation posture of the on-board sensor, resulting in deviations between the data of the target vehicle and lane line after coordinate conversion and the actual position, causing ACC to mis-follow or miss the target, or even cause a collision, which significantly affects the accuracy of adaptive cruise control and the safety of the system.

[0051] In response to the above technical problems, the present application proposes an adaptive cruise target screening method, which effectively improves the accuracy of adaptive cruise target screening by combining pixel layer screening and world layer screening.

[0052] The following is a detailed description of the technical solution for adaptive cruise target screening provided by the present application through specific embodiments. It should be noted that the following embodiments may exist alone or in combination with each other, and the same or similar contents may not be repeatedly described in different embodiments.

[0053] It should be noted that the executor of the adaptive cruise target screening method provided in the embodiment of the present application is the vehicle cruise control system, and accordingly, the adaptive cruise target screening device is also provided in the vehicle cruise control system.

[0054] Figure 1 A flowchart of an adaptive cruise target screening method provided in an embodiment of the present application is shown in FIG. Figure 1 In some embodiments, the process of the adaptive cruise target screening method includes the following steps:

[0055] S101, obtaining image detection data in front of the vehicle through the vehicle-mounted camera, and obtaining an image tracking target and a current lane where the vehicle is located based on the image detection data.

[0056] Among them, after the vehicle turns on the adaptive cruise mode, the on-board camera can collect image data in front of the vehicle, and use the collected image data as detection data to detect and track target objects (vehicles, pedestrians, obstacles, etc.) in front of the vehicle, as well as detect the current lane in which the vehicle is traveling.

[0057] Specifically, the vehicle-mounted camera is usually installed at the front of the vehicle to collect images of the road and environment in front of the vehicle.

[0058] Specifically, after the vehicle-mounted camera collects the image detection data, it can also pre-process the collected image, such as denoising, contrast enhancement, etc., to improve the image quality.

[0059] S102, obtaining radar detection data in front of the vehicle through the vehicle-mounted radar, and obtaining a radar tracking target based on the radar detection data.

[0060] Among them, after the vehicle turns on the adaptive cruise mode, the on-board radar can collect radar detection data in front of the vehicle, and perceive the target object in front of the vehicle through the radar detection data and track it.

[0061] Specifically, the vehicle-mounted radar can be a millimeter-wave radar, which transmits millimeter waves through the antenna. These millimeter waves will be reflected back when they encounter the target object, and the radar antenna will receive these reflected signals. The radar system can calculate the distance, speed, angle and other information of the target based on the time difference between the transmitted signal and the received signal, as well as the frequency change of the signal.

[0062] At the same time, the vehicle-mounted radar system can process the received signals and identify the type (such as vehicles, pedestrians, etc.), position, speed, etc. of the object in front. After identifying the object in front, the radar system starts to track it. The tracking process involves continuous observation and position update of the object to ensure that the system can grasp the movement status of the object in real time.

[0063] S103, fusing the image tracking target and the radar tracking target to obtain a fused target.

[0064] Among them, image tracking targets can provide rich visual information, such as the shape, color, texture, etc. of the target, which is conducive to the accurate identification, classification and tracking of the target. However, image recognition technology is easily affected by factors such as lighting, shadows, and occlusions, resulting in reduced accuracy and stability of target tracking. Radar technology is not affected by lighting and weather conditions, can work stably in various environments, and has a long detection distance and high-precision measurement capabilities. However, radar data is usually sparse and lacks detailed visual information of the target, which may lead to insufficient accuracy in target identification and tracking in some cases.

[0065] Therefore, target fusion of image tracking targets tracked by image recognition and radar tracking targets tracked by radar recognition can make full use of the respective advantages of images and radars and improve the accuracy and robustness of target detection and tracking.

[0066] S104, screening fused targets that continuously meet target screening conditions within a preset time period as potential vehicle-following targets; wherein the target screening conditions include pixel layer screening conditions and world layer screening conditions;

[0067] Among them, the pixel layer refers to the pixel coordinate system level on the image of the image detection data, and the world layer refers to the world coordinate system level constructed with the vehicle-mounted camera as the origin. Therefore, under complex road conditions, the world layer coordinates may deviate due to bumps and jitters, resulting in reduced target screening accuracy.

[0068] However, at the image pixel level, the relative position relationship between the tracked target and the lane line and the cruise vehicle on the image will not be affected. Therefore, by combining the pixel layer filtering conditions with the world layer filtering conditions, the pixel layer filtering can be performed at the pixel level of the image detection data, and its filtering results are not affected by the on-board sensor calibration, thereby improving the accuracy and robustness of target filtering.

[0069] Specifically, the potential following targets are selected as much as possible to select targets in the same lane as the cruise vehicle. Vehicles in the same lane usually have similar driving speeds and directions, which makes the following process more stable. In addition, the relative position and speed changes between vehicles driving in the same lane and the cruise vehicle are more direct and close. Tracking vehicles in the same lane can more easily predict their driving trajectories and possible actions (such as braking, acceleration, lane changing, etc.), so as to react in advance and ensure driving safety.

[0070] S105, selecting a potential following target with the smallest longitudinal distance from the vehicle as a cruising following target.

[0071] Among them, in the process of adaptive cruise control, maintaining lane stability is crucial for driving safety. Selecting the vehicle with the smallest longitudinal distance from the vehicle as the target to follow can ensure that the cruise control system responds to the dynamic changes of the vehicle in front in a timely manner, such as sudden braking or sudden acceleration, thereby preventing potential collision risks. At the same time, the cruise control system can also intelligently adjust the vehicle speed to keep the vehicle at a safe distance from the vehicle in front, avoiding rear-end collisions caused by following too closely. In addition, it also helps the vehicle to maintain stable driving in the current lane and reduce safety hazards caused by lane changes.

[0072] In this embodiment, the characteristic that the relative position relationship of the target on the image at the pixel level will not be affected by the calibration conversion accuracy of the coordinate system is utilized, and the pixel layer filtering and the world layer filtering are combined and complemented. Multiple screening and judgment are performed through pixel layer filtering and world layer filtering, thereby effectively improving the accuracy of adaptive cruise target screening.

[0073] exist Figure 1 Based on the embodiment shown, the following Figure 2 , the technical solution of the above-mentioned adaptive cruise target screening method is further introduced.

[0074] Figure 2 A flow chart of another adaptive cruise target screening method provided in an embodiment of the present application is shown in FIG. Figure 2 In some embodiments, the process of the adaptive cruise target screening method includes the following steps:

[0075] S201, obtaining image detection data in front of the vehicle through the vehicle-mounted camera.

[0076] S202, inputting the image detection data into the detection and recognition model to obtain the image tracking target and lane line point data; wherein the detection and recognition model includes a tracking target recognition sub-model and a lane recognition sub-model obtained based on the training of the neural network model.

[0077] Among them, by collecting a large amount of information about vehicles, pedestrians and lane lines on real roads, the target recognition sub-model and lane recognition sub-model are trained using the neural network model for target recognition and lane line recognition respectively.

[0078] Specifically, the tracking target recognition sub-model may adopt a YOLO model, an R-CNN model, or the like.

[0079] Specifically, the lane recognition sub-model may adopt a CIrNet model, which obtains the initial lane line point data of the world layer through preprocessing and world coordinate conversion.

[0080] S203, tracking the image tracking target based on the target tracking model, and obtaining the target frame and target motion attributes of the image tracking target; wherein the target tracking model is constructed based on the visual target tracking algorithm, and the target motion attributes include the longitudinal distance and lateral distance from the vehicle, and the longitudinal speed and lateral speed relative to the vehicle.

[0081] Among them, the target tracking model is built with a visual target tracking algorithm. First, a tracking method combining a matching loss matrix and Hungarian matching is used. When the target detection output result is stable, the target tracking is stable. Since it does not have an AI reasoning model, the module is simple and easy to use. The target distance estimation uses the UKF Kalman filter. Based on different conditions, a hybrid ranging method of width ranging and landing point ranging is used for distance calculation, and then the UKF Kalman filter is used to perform position and speed filtering on the same target to output the final target result. The main output image tracking target is the category, position, and speed of pedestrians and vehicles, etc., and the target box, target box size and other information are annotated on the image of the image detection data.

[0082] Specifically, for the target motion attribute of the image tracking target, X is used to represent the lateral distance from the vehicle, and Y is used to represent the longitudinal distance from the vehicle. represents the lateral velocity relative to the vehicle, Indicates the longitudinal velocity relative to the ego vehicle.

[0083] S204, performing curve fitting and filter tracking processing on the lane line point data to obtain the lane line and lane information of the current lane; wherein the lane information includes the lane width and the distance between the image tracking target and the center line of the current lane.

[0084] After the lane line point data is obtained, curve fitting is performed on the lane line point data to obtain the lane line formed by the fitting. At the same time, relevant information of the lane line is further obtained based on the lane line, and the lane line is displayed on the image of the image detection data.

[0085] Specifically, the curve fitting adopts the cubic curve algorithm, which can accurately fit the data points, especially when the number of data points is large and the distribution is complex, the algorithm can still maintain a good fitting effect. By solving the cubic polynomial coefficients between each data point, it can ensure that the curve passes through all data points, thereby achieving high-precision fitting and obtaining high-precision lane lines. The lane lines formed by fitting satisfy the following formula:

[0086]

[0087] Among them, y represents the vertical coordinate of the lane line, and x represents the horizontal coordinate of the lane line. Represents polynomial coefficients.

[0088] Specifically, assuming that the lane lines on the left and right sides of the current lane are , then the curve formula of the two lane lines is Adding, we can further get the lane width as , and the distance d between the image tracking target and the center line of the current lane.

[0089] Specifically, the filter tracking process uses a filter algorithm to predict and update the target, thereby achieving continuous tracking of the target. Among them, the filter algorithms for filter tracking and prediction include Kalman filter algorithm, Meanshift tracking algorithm, correlation filter tracking algorithm, particle filter tracking algorithm, filter tracking algorithm based on deep learning, etc.

[0090] S205, if any point of the bottom edge of the target frame is within the lane line of the current lane, it is determined that the image tracking target is within the current lane, and the intrusion rate of the image tracking target into the current lane is obtained; wherein the intrusion rate is the ratio between the area of ​​the target frame intruding into the current lane and the area of ​​the target frame.

[0091] Among them, at the pixel level, by judging whether any point on the bottom edge of the target box is within the lane line of the current lane, it is judged at the pixel level whether the target has invaded the current lane of the cruising vehicle, and the intrusion rate is calculated through the intrusion area.

[0092] For example, see Figure 3, the lane between the two middle lane lines is taken as the current lane, and any point on the bottom edge of the target frame of the tracked target is judged to be within the convex polygon formed by the four lane line points of the current lane. Then, the tracked target is considered to be in the current lane, and then the intersection point is calculated based on the area formed by the target frame point and the lane line point, and the intersection area (i.e. Figure 3 The area of ​​the target frame in the current lane is calculated by dividing it by the area of ​​the target frame of the tracked target. Finally, whether the tracked target is in the current lane and the proportion are assigned to the attributes of the tracked target.

[0093] Specifically, InLaneFlag is used to indicate whether the tracking target invades the current lane. If the tracking target invades the current lane, InLaneFlag is assigned a value of 1. If the tracking target does not invade the current lane, InLaneFlag is assigned a value of 0. InLaneRate is used to indicate the intrusion rate, that is, the proportion of the tracking target invading the current lane, where 0 <InLaneRate≤1。

[0094] S206: If any point of the bottom edge of the target frame is not in the current lane, it is determined that the image tracking target is not in the current lane.

[0095] Among them, any point on the bottom edge of the target box is not in the current lane, which means that the image tracking target does not invade the current lane of the vehicle, but is in other lanes next to it.

[0096] S207, obtaining radar detection data in front of the vehicle through the vehicle-mounted radar, and obtaining a radar tracking target based on the radar detection data.

[0097] S208, matching and screening the image tracking target and the radar tracking target, when the deviation between the target motion attribute of the image tracking target and the target motion attribute of the radar tracking target is within a preset deviation range, the image tracking target and the radar tracking target are associated as a fusion target.

[0098] The target tracking results of the vehicle-mounted radar and the vehicle-mounted camera are received, and then the timestamps of the two are compared, and the most recent data is selected for matching and screening. When the horizontal and vertical positions and speeds of the image tracking target and the radar tracking target meet the threshold range and reach a certain time, the image tracking target and the radar tracking target are associated to form a fusion target.

[0099] After target fusion, the relevant attributes of the image tracking target and the radar tracking target are also summarized together, and the fused target also has the intrusion mark, intrusion rate and other parameters possessed by the image tracking target.

[0100] S209, screening fused targets that continuously meet target screening conditions within a preset time period as potential vehicle-following targets; wherein the target screening conditions include pixel layer screening conditions and world layer screening conditions.

[0101] Preferably, the pixel layer screening conditions include that the fusion target is in the current lane, and that the intrusion rate of the fusion target into the current lane is greater than a first judgment threshold;

[0102] The world layer filtering condition includes that the distance of the fusion target from the center line of the current lane is less than the tightening width.

[0103] Among them, in complex road conditions, the target position information and lane line parameters of the world layer are easily affected by road bumps, resulting in inconsistency with the real coordinates in some special cases, thus leading to misscreening. Therefore, on this basis, the pixel layer screening conditions are used to compensate for the world layer screening, so as to screen out potential following targets in the same lane as the cruising vehicle as accurately as possible.

[0104] Specifically, the fusion target is in the current lane, and the intrusion rate of the fusion target into the current lane is greater than the first judgment threshold, and specifically satisfies the following formula:

[0105]

[0106]

[0107] Among them, InLaneFlag represents the intrusion flag, InLaneRate represents the intrusion rate, Indicates the first judgment threshold.

[0108] Specifically, the distance between the fusion target and the center line of the current lane is less than the tightening width, which satisfies the following formula:

[0109]

[0110] Where d represents the distance between the fusion target and the center line of the current lane. Indicates tightening width, Indicates lane width, Indicates the tightening factor.

[0111] For example, see Figure 5 Assuming that the cruising vehicle in the figure is A, the distance between the fusion target B and the center line of the current lane of the cruising vehicle A is 4 meters, and the current lane width is 3 meters. The distance between the fusion target B and the center line of the current lane, the tightening coefficient is 0.8, then 4 meters is greater than 3.2 meters, and it is obvious that the fusion target B is outside the current lane of the cruising vehicle A.

[0112] In the figure, the distance between the fusion target C and the center line of the current lane of the cruise vehicle A is 0 meters, which is less than 3.2 meters. It is obvious that the fusion target C is within the current lane of the cruise vehicle A.

[0113] Specifically, the tightening coefficient is linearly affected by the longitudinal distance between the target and the vehicle. The closer the longitudinal distance is, the closer the tightening coefficient is to 1, and the farther the longitudinal distance is, the closer the tightening coefficient is to 0.

[0114] Preferably, the pixel layer screening conditions include that the fusion target is in the current lane, and that the intrusion rate of the fusion target into the current lane is greater than a second judgment threshold;

[0115] The world layer filtering conditions include the longitudinal distance between the fused target and the ego vehicle being less than the minimum value of the minimum turning radius filtering threshold and the lane width of the current lane.

[0116] Among them, in the close-range situation, due to the installation angle of the on-board camera, the target frame detected at close distance will be much larger than the actual size of the target, resulting in errors in the pixel layer filtering results. Therefore, the pixel layer filtering is compensated by the world layer filtering conditions to filter out potential following targets in the same lane as the cruising vehicle as accurately as possible.

[0117] At the same time, through the complementarity and multiple judgments of pixel layer screening and world layer screening, the probability of misidentification of following vehicles is reduced when following a vehicle on a curve, and the requirements for the fitting accuracy of the lane line algorithm are also reduced.

[0118] Specifically, the fusion target is in the current lane, and the intrusion rate of the fusion target into the current lane is greater than the second judgment threshold, and specifically satisfies the following formula:

[0119]

[0120]

[0121] Among them, InLaneFlag represents the intrusion flag, InLaneRate represents the intrusion rate, Indicates the second judgment threshold.

[0122] Specifically, the lateral distance between the fusion target and the vehicle is less than the minimum value of the minimum turning radius screening threshold and the lane width of the current lane, and specifically satisfies the following formula:

[0123]

[0124] in, Represents the absolute value of the horizontal distance, Indicates the minimum turning radius screening threshold, Indicates lane width.

[0125] See also Figure 5 ,It can be seen that if the fused target is outside the turning radius area formed by the cruising vehicle turning, it means that the fused target will not affect the cruising vehicle driving and will not be used as a potential following target, so as to exclude the erroneous judgment of pixel layer screening under close distance conditions.

[0126] For the above two target screening conditions, the fusion target only needs to pass any one of the screening conditions and maintain it for a certain period of time to be considered as a potential vehicle-following target.

[0127] Preferably, before performing target screening, the received target data and lane line data may be processed for outliers, and then the lane line may be determined to be complete. If the lane line is incomplete, the electronic fence screening mode based on the steering wheel angle may be entered. When the lane line is complete, the screening mode combining pixel layer screening and world layer screening may be entered.

[0128] Specifically, the electronic fence screening mode means that the system first sets one or more predefined areas, which can be key traffic nodes such as roads, intersections, and highway entrances. These areas are marked on electronic maps and set corresponding boundaries and rules. When a vehicle enters the predefined area, the cruise control system automatically adjusts the following vehicle target based on the current traffic conditions and the set speed and distance.

[0129] S210, selecting a potential following target with the smallest longitudinal distance from the ego vehicle as a cruising following target.

[0130] Specifically, after determining the cruise following target, the cruise control system calculates the currently required throttle and brake control values, and then publishes the topic to the chassis for longitudinal control of the entire vehicle, thereby realizing the adaptive cruise function.

[0131] In this embodiment, the image detection end determines whether the target is in the current lane of the vehicle based on the original data of the image, and calculates the intrusion rate of the target into the current lane. The whole process is not affected by the conversion of external parameters, which reduces the requirements for the calibration accuracy of the vehicle camera.

[0132] Figure 5 is a schematic diagram of the structure of an adaptive cruise target screening device provided in an embodiment of the present application, see Figure 5 The adaptive cruise target screening device includes various functional modules for implementing the aforementioned adaptive cruise target screening method, and any functional module can be implemented by software and / or hardware.

[0133] In some embodiments, the adaptive cruise target screening device 500 includes an image detection module 501, a radar monitoring module 502, a target fusion module 503 and a target screening module 504. Among them:

[0134] The image detection module 501 is used to obtain image detection data in front of the vehicle through the vehicle-mounted camera, and obtain the image tracking target and the current lane where the vehicle is located based on the image detection data;

[0135] The radar monitoring module 502 is used to obtain radar detection data in front of the vehicle through the vehicle-mounted radar, and obtain radar tracking targets based on the radar detection data;

[0136] The target fusion module 503 is used to fuse the image tracking target and the radar tracking target to obtain a fused target;

[0137] The target screening module 504 is used to screen the fused targets that continuously meet the target screening conditions within a preset time period as potential following targets; wherein the target screening conditions include world layer screening conditions or pixel layer screening conditions; and to screen the potential following targets with the smallest longitudinal distance to the vehicle as cruising following targets.

[0138] In some embodiments, the pixel layer screening conditions include that the fusion target is in the current lane, and the intrusion rate of the fusion target intruding into the current lane is greater than a first judgment threshold;

[0139] The world layer filtering condition includes that the distance of the fusion target from the center line of the current lane is less than the tightening width.

[0140] In some embodiments, the pixel layer screening conditions include that the fusion target is in the current lane, and the intrusion rate of the fusion target intruding into the current lane is greater than a second judgment threshold;

[0141] The world layer filtering conditions include the lateral distance between the fused target and the ego vehicle being less than the minimum value of the minimum turning radius filtering threshold and the lane width of the current lane.

[0142] In some embodiments, the image detection module 501 is specifically used for:

[0143] Input the image detection data into the detection and recognition model to obtain the image tracking target and lane line point data; wherein the detection and recognition model includes a tracking target recognition sub-model and a lane recognition sub-model obtained by training the neural network model;

[0144] Track the image tracking target based on the target tracking model, and obtain the target frame and target motion attributes of the image tracking target; wherein the target tracking model is constructed based on the visual target tracking algorithm, and the target motion attributes include the longitudinal distance and lateral distance from the vehicle, and the longitudinal speed and lateral speed relative to the vehicle;

[0145] The lane line point data is subjected to curve fitting and filtering tracking processing to obtain the lane line and lane information of the current lane; wherein the lane information includes the lane width and the distance between the image tracking target and the center line of the current lane.

[0146] In some embodiments, the image detection module 501 is further used to:

[0147] If any point of the bottom edge of the target frame is within the lane line of the current lane, it is determined that the image tracking target is within the current lane, and the intrusion rate of the image tracking target into the current lane is obtained; where the intrusion rate is the ratio between the area of ​​the target frame intruding into the current lane and the area of ​​the target frame.

[0148] In some embodiments, the image detection module 501 is further used to:

[0149] If any point of the bottom edge of the target frame is not in the current lane, it is determined that the image tracking target is not in the current lane.

[0150] In some embodiments, the target fusion module 503 is specifically used to:

[0151] The image tracking target and the radar tracking target are matched and screened. When the deviation between the target motion attribute of the image tracking target and the target motion attribute of the radar tracking target is within a preset deviation range, the image tracking target and the radar tracking target are associated as a fusion target.

[0152] The adaptive cruise target screening device 500 provided in the embodiment of the present application is used to execute the technical solution provided in the aforementioned adaptive cruise target screening method embodiment. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment, and will not be repeated here.

[0153] It should be noted that it should be understood that the division of the various modules of the above device is only a division of a logical function. When actually implemented, it can be fully or partially integrated into a physical entity, or it can be physically separated. And these modules can all be implemented in the form of software called by a processing element, or they can all be implemented in the form of hardware. Some modules can also be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the target screening module 504 can be a separately established processing element, or it can be integrated in a certain chip of the above device to be implemented. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device. The function of the above target screening module 504. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or the instruction in the form of software.

[0154] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, see Figure 6 The electronic device 600 includes a processor 601 and a memory 602 communicatively connected to the processor 601;

[0155] Memory 602 stores computer executable instructions;

[0156] The processor 601 executes the computer-executable instructions stored in the memory 602 to implement the technical solution of the aforementioned adaptive cruise target screening method.

[0157] In the above-mentioned electronic device 600, the memory 602 and the processor 601 are electrically connected directly or indirectly to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines, such as through a bus. 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., but it does not mean that there is only one bus or one type of bus. The memory 602 stores computer execution instructions for implementing the above-mentioned adaptive cruise target screening method, including at least one software function module that can be stored in the memory 02 in the form of software or firmware. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602.

[0158] The memory 602 includes at least one type of readable storage medium, including but not limited to random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), and electrically erasable read-only memory (EEPROM). The memory 602 is used to store programs, and the processor 601 executes the programs after receiving the execution instruction. Furthermore, the software programs and modules in the above-mentioned memory 602 may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components.

[0159] The processor 601 may be an integrated circuit chip having the ability to process signals. The above-mentioned processor 601 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), etc. The disclosed methods, steps and logic block diagrams in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor, or the processor 601 may be any conventional processor, etc.

[0160] The electronic device 600 is used to execute the technical solution provided by the aforementioned adaptive cruise target screening method embodiment. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment and will not be repeated here.

[0161] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the technical solution of the aforementioned adaptive cruise target screening method.

[0162] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The computer-readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0163] An exemplary readable storage medium is coupled to the processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, abbreviated as: ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the control device of the adaptive cruise target screening device.

[0164] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, is used to implement the technical solution of the aforementioned adaptive cruise target screening method.

[0165] In the above embodiments, those skilled in the art will appreciate that the implementation of the above method embodiments can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless network, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0166] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the appended claims.

[0168] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. An adaptive cruise target screening method, characterized in that: include: Acquire image detection data in front of the vehicle through a vehicle-mounted camera, and acquire an image tracking target and a current lane where the vehicle is located based on the image detection data; Acquire radar detection data in front of the vehicle through the vehicle-mounted radar, and acquire a radar tracking target based on the radar detection data; Fusing the image tracking target and the radar tracking target to obtain a fused target; Filtering fused targets that continuously meet target screening conditions within a preset time as potential vehicle-following targets; wherein the target screening conditions include pixel layer screening conditions and world layer screening conditions; Select the potential following target with the smallest longitudinal distance to the vehicle as the cruising following target.

2. The method according to claim 1, characterized in that The pixel layer screening condition includes that the fusion target is in the current lane, and the intrusion rate of the fusion target into the current lane is greater than a first judgment threshold; The world layer screening condition includes that the distance between the fusion target and the center line of the current lane is less than the tightening width.

3. The method according to claim 1, characterized in that The pixel layer screening condition includes that the fusion target is in the current lane, and the intrusion rate of the fusion target into the current lane is greater than a second judgment threshold; The world layer screening condition includes that a lateral distance between the fusion target and the vehicle is less than a minimum value of a minimum turning radius screening threshold and a lane width of the current lane.

4. The method according to any one of claims 1 to 3, characterized in that: Acquiring an image tracking target and a current lane where the vehicle is located based on the image detection data includes: Input the image detection data into the detection and recognition model to obtain image tracking target and lane line point data; wherein the detection and recognition model includes a tracking target recognition sub-model and a lane recognition sub-model obtained based on neural network model training; Tracking the image tracking target based on a target tracking model, and obtaining a target frame and target motion attributes of the image tracking target; wherein the target tracking model is constructed based on a visual target tracking algorithm, and the target motion attributes include a longitudinal distance and a lateral distance from the vehicle, and a longitudinal speed and a lateral speed relative to the vehicle; The lane line point data is subjected to curve fitting and filtering tracking processing to obtain the lane line and lane information of the current lane; wherein the lane information includes lane width and the distance between the image tracking target and the center line of the current lane.

5. The method according to claim 4, characterized in that The method further comprises: If any point of the bottom edge of the target frame is within the lane line of the current lane, it is determined that the image tracking target is within the current lane, and the intrusion rate of the image tracking target into the current lane is obtained; wherein the intrusion rate is the ratio between the area of ​​the target frame intruding into the current lane and the area of ​​the target frame.

6. The method according to claim 5, characterized in that The method further comprises: If any point of the bottom edge of the target frame is not within the current lane, it is determined that the image tracking target is not within the current lane.

7. The method according to claim 4, characterized in that The image tracking target and the radar tracking target are subjected to target fusion to obtain a fused target, including: The image tracking target and the radar tracking target are matched and screened, and when the deviation between the target motion attribute of the image tracking target and the target motion attribute of the radar tracking target is within a preset deviation range, the image tracking target and the radar tracking target are associated as a fusion target.

8. An adaptive cruise target screening device, characterized in that: include: An image detection module is used to obtain image detection data in front of the vehicle through a vehicle-mounted camera, and obtain an image tracking target and a current lane where the vehicle is located based on the image detection data; A radar monitoring module, used to obtain radar detection data in front of the vehicle through a vehicle-mounted radar, and obtain a radar tracking target based on the radar detection data; A target fusion module is used to fuse the image tracking target and the radar tracking target to obtain a fused target; The target screening module is used to screen the fused targets that continuously meet the target screening conditions within a preset time as potential following targets; wherein the target screening conditions include world layer screening conditions or pixel layer screening conditions; and screen the potential following targets with the smallest longitudinal distance to the vehicle as cruising following targets.

9. An electronic device, characterized in that: comprising a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method according to any one of claims 1 to 7.

Images