Method for determining longitudinal vehicle following target, electronic equipment, storage medium and vehicle
By considering the target object detection data of multiple consecutive frames in the time dimension, and calculating and comparing the overlap rate of the target object with the bicycle, the problem of unstable vertical follow-up target selection in the prior art is solved, and the following experience and standard accuracy are improved.
Patent Information
- Application Number
- CN202411769511.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-03
- Publication Date
- 2025-04-18
AI Technical Summary
When determining vertical follow-up targets, the prior art only considers the position relationship between the target and the bicycle at the current moment, which is poor in accuracy, resulting in unstable selection or discarding of the target and poor follow-up experience.
Through the detection data of the target object in succession of multiple frames, the first overlap rate between the target object and the bicycle is calculated, and when the multiple overlap rates satisfy the selected overlap rate conditions, the target object is determined to be a vertical follow-up target.
Improve the accuracy of the selection criteria for vertical car follow-up targets, avoid the problems of discontinuous and instability, and improve the car follow-up experience.
Smart Images
Figure CN119840623A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to a method for determining a longitudinal following vehicle target, as well as an electronic device, a computer-readable storage medium and a vehicle. Background Art
[0002] In the related technology, the judgment of the following target only considers the position relationship between the target and the vehicle at the current moment, and judges whether to use the target as the longitudinal following target based on the lateral offset between the target center point and the vehicle. The accuracy is poor, the selection or discarding of the target is unstable, and the following experience is poor. Summary of the invention
[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, one purpose of the present invention is to propose a method for determining a longitudinal following target, which can be considered in the time dimension, and the longitudinal following target can be determined by detecting multiple frames of target objects, thereby avoiding problems such as discontinuity and instability when determining the longitudinal following target, improving the following experience, and improving the accuracy of selecting the longitudinal following target.
[0004] The second objective of the present invention is to provide an electronic device.
[0005] The third object of the present invention is to provide a computer storage medium.
[0006] A fourth objective of the present invention is to provide a vehicle.
[0007] In order to solve the above problems, an embodiment of the first aspect of the present invention provides a method for determining a longitudinal following target, comprising: obtaining a first overlap ratio between the target object and the vehicle based on detection data of the target object; when multiple first overlap ratios obtained based on detection data of the target object in multiple consecutive frames meet a selected overlap ratio condition, determining that the target object is a longitudinal following target.
[0008] According to the method for determining a longitudinal following target in an embodiment of the present invention, when determining the longitudinal following target, it is not limited to the detection data at the current moment, but is considered in the time dimension, and multiple first overlapping rates are obtained through the detection data of multiple consecutive frames of the target object. When the multiple first overlapping rates meet the selected overlapping rate condition, the target object is determined to be the longitudinal following target. The target tracking has continuity and stability, which can avoid problems such as discontinuity and instability when determining the longitudinal following target, thereby improving the following experience and the accuracy of selecting the longitudinal following target.
[0009] In some embodiments, the detection data of the target object includes the target object position, the target object angle and the structural parameters of the target object relative to the vehicle coordinate system.
[0010] In some embodiments, the first overlap rate between the target object and the vehicle is obtained based on the corner coordinates of the target object relative to the vehicle, the target object position and the structural parameters of the target; the corner coordinates of the target object relative to the vehicle are determined based on the target object position, the target object angle and the structural parameters of the target.
[0011] In some embodiments, the corner point coordinates of the target object relative to the self-vehicle are determined based on the corner point rotation coordinates of the target object and the position of the target object; the corner point rotation coordinates of the target object are obtained based on the corner point coordinates of the target object at the origin of the self-vehicle coordinate system and the angle of the target object.
[0012] In some embodiments, the coordinates of the corner points of the target object at the origin of the vehicle coordinate system are determined according to the structural parameters of the target object.
[0013] In some embodiments, the structural parameters of the target object include a length value of the target object and a width value of the target object.
[0014] In some embodiments, the coordinates of the corner points of the target object at the origin of the vehicle coordinate system include the following: ( , / 2 )、( , - / 2 )、(0, / 2 ) and (0, - / 2 ); in, is the length of the target object, is the width of the target object.
[0015] In some embodiments, the first overlap rate between the target object and the ego vehicle is expressed as a function of the ego vehicle coordinates obtained at the ordinate of the target object according to the predicted driving trajectory, the coordinates of the corner points of the target object closest to the ego vehicle, and the structural parameters of the target object, wherein the ego vehicle coordinates are determined based on the position of the target object, and the position of the target object includes the ordinate of the target object relative to the ego vehicle coordinate system.
[0016] In some embodiments, the vehicle coordinates include a horizontal coordinate and a vertical coordinate, wherein the vertical coordinate is taken as the vertical coordinate of the target object, and the horizontal coordinate is determined based on the vertical coordinate and the predicted driving trajectory.
[0017] In some embodiments, the first overlap ratio between the target object and the vehicle is expressed as follows: ; or, ; in, is the first overlap ratio between the target object and the vehicle, is the horizontal coordinate of the vehicle, is the horizontal coordinate of the corner point closest to the target object and the vehicle, is the width of the vehicle.
[0018] In some embodiments, the selected overlap rate condition includes that each of the first overlap rates obtained according to the detection data of the target object in each frame reaches a selected overlap rate threshold and the count value of multiple first overlap rates reaches a first set count threshold.
[0019] In some embodiments, when the first overlap rate reaches the selected overlap rate threshold, the count value of the first overlap rate increases by one; if the first overlap rate obtained by any frame of detection data of the target object does not reach the selected overlap rate threshold, the count value of the first overlap rate is cleared.
[0020] In some embodiments, when there are multiple targets determined according to the selected overlap rate condition, the target with the smallest relative longitudinal distance to the vehicle among the multiple targets is the longitudinal following target.
[0021] In some embodiments, after determining the longitudinal following target, a second overlap ratio between the longitudinal following target and the self-vehicle is obtained based on the detection data of the longitudinal following target; when multiple second overlap ratios obtained based on the detection data of the longitudinal following target in multiple consecutive frames meet the condition of discarding the overlap ratio, the longitudinal following target is discarded.
[0022] In some embodiments, the discarding overlap rate condition includes that each of the second overlap rates obtained according to the detection data of the longitudinal following target in each frame is less than a discarding overlap rate threshold and the count value of multiple second overlap rates reaches a second set count threshold.
[0023] In some embodiments, when the second overlap rate reaches the discard overlap rate threshold, the count value of the second overlap rate increases by one. If the second overlap rate obtained from the detection data of the longitudinal drive target in any frame does not reach the discard overlap rate threshold, the count value of the second overlap rate is cleared.
[0024] A second aspect of the present invention provides an electronic device, comprising: at least one processor; a memory communicatively connected to the at least one processor; a computer program executable by the at least one processor is stored in the memory, and when the at least one processor executes the computer program, the method for determining a longitudinal following target described in the above embodiment is implemented.
[0025] According to the electronic device of the embodiment of the present invention, the corresponding program for determining the longitudinal following target can be stored in the memory. When implementing the charging control method, the processor runs the program in the memory, obtains multiple first overlapping rates based on the detection data of the target object in multiple consecutive frames, and determines that the target object is the longitudinal following target when the multiple first overlapping rates meet the selected overlapping rate conditions, thereby avoiding problems such as discontinuity and instability when determining the longitudinal following target, improving the following experience, and improving the accuracy of selecting the longitudinal following target.
[0026] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the method for determining a longitudinal following target as described in the above embodiment.
[0027] A fourth aspect of the present invention provides a vehicle, comprising the electronic device described in the above embodiment; or, the vehicle comprises: a sensor device, the sensor device is used to detect detection data of a target object; a controller, the controller is connected to the sensor device, and is used to execute the method for determining a longitudinal following target described in the above embodiment.
[0028] According to the vehicle of the embodiment of the present invention, when implementing the method for determining a longitudinal following target, the controller controls the sensor device to obtain detection data of the target object in multiple consecutive frames, and obtains multiple first overlapping rates through the detection data of the target object in multiple consecutive frames. When the multiple first overlapping rates meet the selected overlapping rate conditions, the target object is determined to be a longitudinal following target, thereby avoiding problems such as discontinuity and instability when determining the longitudinal following target, improving the following experience, and improving the accuracy of selecting the longitudinal following target.
[0029] In some embodiments, the sensor device includes: a visual sensor connected to the controller, used to obtain the structural parameters of the target and / or the target angle of the target relative to the vehicle coordinate system; a millimeter wave radar connected to the controller, used to detect the target position of the target relative to the vehicle coordinate system.
[0030] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 is a flow chart of a method for determining a longitudinal following target according to an embodiment of the present invention; Figure 2 is a flow chart of calculating the overlap ratio between a target vehicle and a self-vehicle according to one embodiment of the present invention; Figure 3 is a flowchart of selecting a longitudinal following target according to an embodiment of the present invention; Figure 4 is a flowchart of discarding a longitudinal following vehicle target according to an embodiment of the present invention; Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present invention; Figure 6 is a structural block diagram of a vehicle according to an embodiment of the present invention; Figure 7 is a structural block diagram of a vehicle according to an embodiment of the present invention.
[0032] Reference numerals: Vehicle 200; Electronic device 100; sensor device 210; controller 220; Processor 101; memory 102; visual sensor 211; millimeter wave radar 212. DETAILED DESCRIPTION
[0033] Embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. Embodiments of the present invention are described in detail below.
[0034] In the prior art, in L2 level autonomous driving, it is necessary to perform vehicle following control on the target vehicle in front, so it is necessary to be able to correctly select the vehicle in front or in front of the side as the target to follow. The current solution for selecting targets is generally to set up different arbitration boundaries according to the availability of lane lines. When the center point of the target vehicle in front or on the side and the lateral offset of the vehicle reach the arbitration boundary, the vehicle is selected as the longitudinal target to follow. However, there are many problems with the existing solution. The current solution is not accurate in judging whether to use the lateral offset between the center point of the target and the vehicle as a point-to-point relationship, and the length, width and angle of the target vehicle are not considered. In addition, the current existing solution only considers the positional relationship between the target and the vehicle at the current moment to make a judgment. The selection or discarding of the target selection only in a single frame is inaccurate and unstable, and does not take too much consideration into the time dimension. If the front vehicle happens to be near the critical threshold of the arbitration boundary, the selected target will have problems such as discontinuity and instability, resulting in a poor following experience.
[0035] In order to solve the above problems, an embodiment of the first aspect of the present invention provides a method for determining a longitudinal following target. The method can be considered in the time dimension, and the longitudinal following target can be determined by detecting data of multiple consecutive frames of the target object, thereby avoiding problems such as discontinuity and instability when determining the longitudinal following target, improving the following experience, and improving the accuracy of selecting the longitudinal following target.
[0036] Reference below Figure 1 A method for determining a longitudinal following target according to an embodiment of the first aspect of the present invention is described. Figure 1 As shown, the method at least includes step S1 to step S2.
[0037] Step S1, obtaining a first overlap ratio between the target object and the vehicle according to detection data of the target object.
[0038] Specifically, the overlap rate can be understood as the relative position relationship between the ego vehicle and the target object, that is, the longitudinal vehicle (target vehicle) in a specific dimension, for example, a two-dimensional plane, which is obtained by calculating the ratio of the overlapping part between the two to the total area or total volume; the first overlap rate can be understood as when the ego vehicle follows the driving trajectory to the position of the target object, it will overlap with the target object. The first overlap rate is the overlap rate when the ego vehicle selects the target object as the longitudinal following target.
[0039] When the vehicle is driving, the detection data of the target object is obtained through sensors (such as radar and camera), including information such as position, speed, and direction. The obtained data is processed, such as filtering, denoising, and coordinate conversion, to ensure the accuracy and reliability of the data. Then, based on the position information of the vehicle and the target object, the overlapping part between them is calculated to obtain the first overlap rate.
[0040] Step S2, when a plurality of first overlapping rates obtained based on the detection data of the target object in a plurality of consecutive frames meet a selected overlapping rate condition, determining that the target object is a longitudinal following target.
[0041] Specifically, since the ego vehicle and the target object are moving and their relative positions are different at every moment, when the ego vehicle determines the longitudinal following target, the ego vehicle continuously obtains the detection data of the target object over a period of time, and obtains the first overlap rate of multiple consecutive frames through the detection data of the target object. When the multiple first overlap rates obtained meet the selected overlap rate condition, the target object is determined to be a longitudinal following target. The selected overlap rate condition can be considered in the time dimension, and whether to select it as a longitudinal following target can be determined by the motion trend of multiple consecutive frames.
[0042] According to the method for determining a longitudinal following target in an embodiment of the present invention, when determining the longitudinal following target, it is not limited to the detection data at the current moment, but is considered in the time dimension, and multiple first overlapping rates are obtained through the detection data of multiple consecutive frames of the target object. When the multiple first overlapping rates meet the selected overlapping rate condition, the target object is determined to be the longitudinal following target, thereby avoiding problems such as discontinuity and instability when determining the longitudinal following target, improving the following experience, and improving the accuracy of selecting the longitudinal following target.
[0043] In some embodiments, the detection data of the target object includes the target object position, the target object angle and the structural parameters of the target object relative to the vehicle coordinate system.
[0044] Specifically, the detection data of the target object provides rich data support for the method of determining the longitudinal following target, so that the target object in front can be identified, tracked and responded to more accurately; the target position of the target object relative to the self-vehicle coordinate system refers to the coordinate value of the target object in the self-vehicle coordinate system, usually including the horizontal coordinate and the vertical coordinate and may also include the vertical coordinate in some cases; the target object angle usually refers to the deflection angle of the target object relative to the driving direction of the self-vehicle, which can be the deflection angle relative to the longitudinal axis of the self-vehicle or the deflection angle relative to the lateral axis of the self-vehicle; the structural parameters of the target object include the size (such as length and width), shape and possible other characteristics (such as color, material, etc.) of the target object, and these parameters are usually obtained through image recognition, radar scanning and other technologies.
[0045] In some embodiments, the first overlap rate between the target object and the vehicle is obtained based on the corner point coordinates of the target object relative to the vehicle, the target object position and the structural parameters of the target; the corner point coordinates of the target object relative to the vehicle are determined based on the target object position, the target object angle and the structural parameters of the target.
[0046] Specifically, the first overlap ratio is the degree of overlap between the target object and the ego vehicle on the plane, which is used to quantify the degree of overlap between the target object and the ego vehicle under specific conditions. The calculation of the first overlap ratio involves multiple factors, including the corner point coordinates of the target object relative to the ego vehicle, the position of the target object, and the structural parameters of the target object. If the target object (vehicle) is a rectangle, its corner point coordinates can be expressed as the positions of the four corner points of the target object. By comparing the relationship between these corner points and the corresponding positions of the ego vehicle, the overlapping area between the target object and the ego vehicle can be calculated, thereby obtaining the first overlap ratio.
[0047] Corner point coordinates refer to the vertex position of the target in a certain coordinate system. These coordinates are used to determine the shape and position of the target. The determination of corner point coordinates requires comprehensive consideration of the position, angle and structural parameters of the target. The position of the target is measured by sensors (such as radar, camera, etc.); the angle of the target can be obtained by measuring the direction or deflection angle of the target relative to the vehicle; based on the structural parameters such as the size and shape of the target, its corner point coordinates in a certain coordinate system can be calculated. If the target is a rectangle of known size, and its direction and position relative to the vehicle are known, then its corner point coordinates in the coordinate system relative to the vehicle can be calculated through geometric transformations (such as rotation and translation).
[0048] In some embodiments, the corner coordinates of the target object relative to the vehicle are determined based on the corner rotation coordinates of the target object and the position of the target object; the corner rotation coordinates of the target object are obtained based on the corner coordinates of the target object at the origin of the vehicle coordinate system and the angle of the target object.
[0049] Specifically, the rotation coordinates of the corner points of the target object are the new coordinates of the corner points of the target object after the target object is rotated a certain angle relative to the origin of the self-vehicle coordinate system. These coordinates reflect the position of the target object after rotation. The rotation coordinates of the corner points of the target object are calculated based on the corner point coordinates of the target object at the origin of the self-vehicle coordinate system and the angle of the target object. After the target angle is detected, the corner point coordinates of the target object at the origin are multiplied by the corresponding target angle to obtain the rotated corner point coordinates. The corner point coordinates of the target object relative to the self-vehicle refer to the positions of the corner points of the target object in the self-vehicle coordinate system. These coordinates are used to determine the shape and position of the target object in the self-vehicle coordinate system; the corner point coordinates of the target object relative to the self-vehicle are obtained by rotating the corner point coordinates of the target object at the origin of the self-vehicle coordinate system.
[0050] In some embodiments, the coordinates of the corner points of the target object at the origin of the vehicle coordinate system are determined according to the structural parameters of the target object.
[0051] Specifically, the ego vehicle coordinate system is a reference coordinate system established with the ego vehicle as the center, which is used to describe the position and motion state of objects around the ego vehicle. In the ego vehicle coordinate system, a fixed point of the ego vehicle is usually selected as the origin, and the appropriate coordinate axis direction is selected as needed. After obtaining the structural parameters of the target object, the coordinates of the target object's corner points are obtained according to the structural parameters of the target object.
[0052] In some embodiments, the structural parameter of the target object includes a length value of the target object and a width value of the target object.
[0053] Specifically, the length value of the target object refers to its maximum size in a specific direction (such as the front-to-back direction); the width value of the target object refers to its maximum size in another direction perpendicular to the length direction (such as the left-to-right direction).
[0054] In some embodiments, the coordinates of the corner points of the target object at the origin of the vehicle coordinate system include the following: ( , / 2 )、( , - / 2 )、(0, / 2 ) and (0, - / 2 ); in, is the length of the target object, is the width of the target object.
[0055] Specifically, the data of obstacles and vehicles can be obtained through two types of sensors, namely visual sensors and millimeter-wave radars. After fusion, the coordinates, speed, angle and other data of the target vehicle relative to the vehicle's coordinate system can be obtained.
[0056] According to the coordinates of the target vehicle relative to the vehicle coordinate system, the rear bumper center of the target vehicle is generally the center point of the target vehicle. and vehicle commander The coordinates of the four corner points of the target vehicle at the origin of the vehicle coordinate system can be obtained: ( , / 2 )、( , - / 2 )、(0, / 2 ) and (0, - / 2 ); The order of the corner points is left front, right front, right rear, left rear. The rotated coordinates can be obtained based on the angle theta of the target relative to the vehicle: ; ; in, is the horizontal axis coordinate after rotation, is the vertical axis coordinate after rotation, is the horizontal axis coordinate before rotation, is the longitudinal coordinate before rotation; the coordinates of the four corner points after rotation plus the obtained rear insurance center coordinates of the target can be obtained to obtain the coordinates of the four corner points of the target relative to the vehicle.
[0057] In some embodiments, the first overlap rate between the target object and the ego vehicle is expressed as a function of the ego vehicle coordinates obtained at the ordinate of the target object according to the predicted driving trajectory, the coordinates of the corner points closest to the target object and the ego vehicle, and the structural parameters of the target object, wherein the ego vehicle coordinates are determined based on the position of the target object, and the position of the target object includes the ordinate of the target object relative to the ego vehicle coordinate system.
[0058] Specifically, the first overlap rate between the target object and the ego vehicle is a complex function, which depends on multiple variables, including the ego vehicle coordinates, the coordinates of the corner point closest to the ego vehicle and the target object, and the structural parameters of the target object; the ego vehicle coordinates are determined according to the ordinate coordinates of the target object relative to the ego vehicle coordinate system. After obtaining the ego vehicle coordinates, the coordinates of the corner point closest to the target object and the structural parameters of the target object, the first overlap rate can be calculated according to the function expression.
[0059] In some embodiments, the vehicle coordinates include the vehicle horizontal coordinate and the vehicle vertical coordinate, wherein the vehicle vertical coordinate is taken as the target object vertical coordinate, and the vehicle horizontal coordinate is determined based on the vehicle vertical coordinate and the predicted driving trajectory.
[0060] Specifically, in the ego vehicle coordinate system, the ego vehicle coordinates include the ego vehicle horizontal coordinate and the ego vehicle vertical coordinate. The ego vehicle vertical coordinate can be expressed as the target object vertical coordinate. The ego vehicle horizontal coordinate is obtained by the ego vehicle vertical coordinate and the predicted driving trajectory. The trajectory equation of the predicted driving trajectory can be expressed as: Y=C0+C1X+C2X 2 +C3X 3 ; Among them, C0, C1, C2 and C3 are constants, Y can be the vertical coordinate of the target object, and X, the horizontal coordinate of the vehicle, can be obtained based on the above equation.
[0061] In some embodiments, the first overlap ratio between the target object and the vehicle is expressed as follows: ; or, ; in, is the first overlap ratio between the target object and the vehicle, is the horizontal coordinate of the vehicle, is the horizontal coordinate of the corner point closest to the target object and the vehicle, is the width of the vehicle.
[0062] Specifically, the first overlap rate between the vehicle and the target object can be obtained based on the predicted driving trajectory of the vehicle, the width of the vehicle, and the calculated coordinates of the four corner points of the target object. First, the coordinates of the vehicle obtained by the vehicle according to the predicted driving trajectory at the longitudinal position of the target object are calculated. , and then obtain the positional relationship between the vehicle and the target object based on the coordinates of the corner point closest to the vehicle, and then calculate the positional relationship between the vehicle and the target object based on the width of the vehicle. The first overlap rate is calculated; different directions are defined differently in the ego-vehicle coordinate system, where left and upward are defined as positive and right and downward are defined as negative. The calculation formulas for the target on the left and right sides of the ego-vehicle are different, so the positive and negative directions need to be considered during the calculation; The target vehicle is on the left side of the vehicle: ; The target vehicle is on the right side of the vehicle: .
[0063] Reference below Figure 2 The first step of calculating the overlap rate between the target vehicle and the self-vehicle is illustrated by way of example, as follows: Step S3, obtaining the position of the target vehicle relative to the own vehicle according to the sensor.
[0064] Step S4, calculating the coordinates of the four corner points of the target vehicle according to the length, width and angle of the target vehicle.
[0065] Step S5, calculating a first overlap ratio between the target vehicle and the own vehicle according to the coordinates of the four points and their positional relationship with the own vehicle.
[0066] In some embodiments, the selected overlap rate condition includes that each first overlap rate obtained according to the detection data of each frame of the target reaches a selected overlap rate threshold and the count value of the plurality of first overlap rates reaches a first set count threshold.
[0067] Specifically, when determining the longitudinal following target, detection data of multiple frames of targets are acquired in real time, and multiple first overlap rates are obtained based on the detection data of multiple consecutive frames of targets. When the first overlap rate of the current frame reaches the selected overlap rate threshold, it is determined that the first overlap rate of the current frame meets the selected overlap rate condition. Different selected overlap rate thresholds can be set according to different vehicle states and specification requirements. For example, the selected overlap rate threshold can be set to 20%. When the first overlap rate of the current frame exceeds 20%, it is determined that the first overlap rate of the current frame meets the selected overlap rate condition, and the first overlap rate counter is incremented by one. For example, the first set counting threshold can be set to 10 times. When the first set counting threshold reaches 10, it means that the target object and the vehicle meet the selected overlap rate condition within a period of time. At this time, the target object is determined to be a longitudinal following target.
[0068] In some embodiments, when the first overlap ratio reaches the selected overlap ratio threshold, the count value of the first overlap ratio increases by one; if the first overlap ratio obtained by any frame of target detection data does not reach the selected overlap ratio threshold, the count value of the first overlap ratio is reset to zero.
[0069] Specifically, the first overlap rate of the current frame can be obtained by calculation, and it is determined whether the overlap rate of the current frame meets the selected overlap rate threshold. If it meets the selected overlap rate threshold, the count value of the first overlap rate increases by one. If the first overlap rate obtained by any frame does not reach the selected overlap rate threshold, the counter is reset to zero and the detection of the next time period begins. If the count value of the first overlap rate is greater than a certain set threshold, it can be determined that the target meets the selection condition and can be selected as the longitudinal following target.
[0070] For example, the selected overlap rate threshold can be set to 20%, and the first set counting threshold can be set to 10 times; since the determination of the longitudinal following target is carried out within a certain period of time, the detection data of multiple frames of the target is acquired in real time, and multiple first overlap rates are obtained based on the detection data of multiple consecutive frames of the target. When the first overlap rate of the current frame exceeds 20%, it is determined that the first overlap rate of the current frame meets the selected overlap rate condition, and the first overlap rate counter is increased by one. If the first overlap rate of the current frame does not exceed 20%, the counter is reset to zero and the counting is restarted. When the first set counting threshold reaches 10, it means that the target object and the vehicle meet the selected overlap rate condition within a period of time, and the target object is determined to be the longitudinal following target.
[0071] In some embodiments, when there are multiple targets determined according to the selected overlap rate condition, the target with the smallest relative longitudinal distance to the vehicle among the multiple targets is the longitudinal following target.
[0072] Specifically, when determining the target object according to the selected overlap rate condition, there may be multiple target objects in front. When multiple target objects and the ego vehicle meet the selected overlap rate condition, only the target object with the smallest relative longitudinal distance to the ego vehicle is selected as the longitudinal following target to avoid confusion in the selection of the longitudinal following target.
[0073] Reference below Figure 3 The following is an example of the steps for selecting a longitudinal following target: Step S6, setting a threshold for the overlap rate.
[0074] Step S7, determine whether the target vehicle meets the overlap rate selected threshold, if so, execute step S8, otherwise, execute step S9.
[0075] Step S8, the number of consecutively selected frames is increased by one.
[0076] Step S9, the number of consecutively selected frames is reset to zero.
[0077] Step S10, whether the number of continuously selected frames reaches a certain set threshold, if so, execute step S12, otherwise, execute step S11.
[0078] Step S11, save the selected frame number and continue to judge the next frame.
[0079] Step S12, select as the longitudinal following target.
[0080] In some embodiments, the method also includes: after determining the longitudinal following target, obtaining a second overlap rate between the longitudinal following target and the vehicle based on the detection data of the longitudinal following target; when multiple second overlap rates obtained based on the detection data of the longitudinal following target in multiple consecutive frames meet the condition for discarding the overlap rates, discarding the longitudinal following target.
[0081] Specifically, the second overlap rate can be understood as the overlap rate when the ego vehicle abandons the longitudinal following target. After the ego vehicle determines the longitudinal following target, the detection data of the longitudinal following target is obtained in real time, and the second overlap rate between the longitudinal following target and the ego vehicle is obtained according to the detection data. The abandonment overlap rate condition is set, and the second overlap rate is compared with the abandonment overlap rate. When the multiple second overlap rates obtained meet the abandonment overlap rate condition, it means that the longitudinal following target does not meet the ego vehicle following condition. At this time, the longitudinal following target is abandoned.
[0082] In some embodiments, the discarding overlap rate condition includes that each second overlap rate obtained according to the detection data of the longitudinal following target in each frame is less than a discarding overlap rate threshold and the count value of the plurality of second overlap rates reaches a second set count threshold.
[0083] Specifically, when the overlap rate between the ego vehicle and the following vehicle target is small, the ego vehicle needs to reselect the following vehicle target. Therefore, the discard overlap rate threshold is less than the selected overlap rate threshold. For example, the overlap rate threshold can be set to 20%, and the discard overlap rate threshold can be set to 10%. When the second overlap rate of the current frame is less than 10%, it is determined that the second overlap rate of the current frame meets the discard overlap rate condition, and the second overlap rate counter is increased by one. For example, the second set counting threshold can be set to 10 times. When the second set counting threshold reaches 10, the ego vehicle cancels following the vehicle and reselects the longitudinal following target.
[0084] In some embodiments, when the second overlap rate reaches the discard overlap rate threshold, the count value of the second overlap rate increases by one; if the second overlap rate obtained by any frame of detection data of the longitudinal drive target does not reach the discard overlap rate threshold, the count value of the second overlap rate is cleared.
[0085] Specifically, the second overlap rate of the current frame can be obtained by calculating the current frame, and it is determined whether the overlap rate of the current frame meets the discard overlap rate threshold. If the discard overlap rate threshold is met, the count value of the second overlap rate increases by one. If the second overlap rate obtained by any frame does not reach the discard overlap rate threshold, the counter is reset to zero and the detection of the next time period is started.
[0086] For example, when a target has been selected as a following target, it is also necessary to use the multi-frame overlap rate to discard the target to ensure stability. Different overlap rate discarding thresholds can be set according to different vehicle states and specification requirements. The current frame overlap rate can be obtained by calculation, and it is determined whether the current frame overlap rate meets the overlap rate discarding threshold. If the threshold is met, the target's discard overlap rate threshold counter is increased by one. If not, the counter is reset to zero. When the counter that meets the discard overlap rate threshold is greater than a set threshold, it can be determined that the target meets the discarding condition and can be discarded.
[0087] The discarding overlap rate threshold can be set to 10%, and the second set counting threshold can be set to 10 times; after the ego vehicle determines the longitudinal following target, it obtains detection data of multiple frames of the target in real time, and obtains multiple second overlap rates based on the detection data of multiple consecutive frames of the target. When the second overlap rate of the current frame is less than 10%, it is determined that the second overlap rate of the current frame meets the discarding overlap rate condition, and the second overlap rate counter is increased by one. If the second overlap rate of the current frame is not less than 10%, the counter is reset to zero and restarts counting. When the second set counting threshold reaches 10, the discarding overlap rate condition is met, the ego vehicle cancels following the vehicle, and reselects the longitudinal following target.
[0088] Reference below Figure 4 The steps of discarding the longitudinal following target are illustrated by example, and the specific contents are as follows: Step S13, setting a threshold for discarding overlap rate.
[0089] Step S14, determine whether the target vehicle meets the overlap rate discarding threshold, if so, execute step S15, otherwise, execute step S16.
[0090] Step S15, the number of consecutively discarded frames is increased by one.
[0091] Step S16, the number of consecutive discards is cleared.
[0092] Step S17, whether the number of consecutive discarded frames reaches a certain set threshold, if so, execute step S19, otherwise, execute step S18.
[0093] Step S18, save the number of discarded frames and continue to judge the next frame.
[0094] Step S19, discarding the longitudinal following vehicle target.
[0095] For example, the existing scheme only judges whether to use the lateral offset between the target center point and the ego vehicle to determine whether to use it as a following target, which is not accurate. The positional relationship between the target vehicle and the ego vehicle is judged as a point-to-point relationship, and the length, width and angle of the target vehicle are not considered. The length, width and angle of the target should be taken into account, that is, the positional relationship between the ego vehicle and the target vehicle is judged as a rigid body motion relationship between two-dimensional planes, and the overlap rate between the ego vehicle and the target vehicle should be calculated instead of the arbitration boundary line. The existing scheme for selecting and discarding targets only considers the positional relationship between the target and the ego vehicle at the current moment. The target selection performed only in a single frame is inaccurate and unstable, and does not take too much consideration into account in the time dimension. If the front vehicle happens to be near the critical threshold of the arbitration boundary line, the selected target will have problems such as discontinuity and instability, resulting in a poor following experience. In the actual selection process, the selection or discarding of the target cannot be determined only by a single frame, but needs to be determined by the motion trend of multiple consecutive frames.
[0096] In the present invention, different data are first obtained through different sensors, and the data of multiple sensors are fused to obtain the position of the target vehicle relative to the self-vehicle coordinate system, and then the length, width and other attributes of the target vehicle are obtained through the visual sensor, and then the angle of the target relative to the self-vehicle is calculated through the speed of the target vehicle, or the angle is obtained through the visual sensor when the target vehicle is stationary; according to the obtained length, width, angle of the target relative to the self-vehicle and the position of the target, the coordinates of the four corner points of the target are calculated, and the overlap rate of the target vehicle with the self-vehicle is calculated through the coordinates of the four corner points and the width of the self-vehicle. Then, different overlap rate thresholds are set according to different self-vehicle states, and then it is determined whether the target vehicle meets the overlap rate threshold. If the overlap rate threshold is met, the cumulative number of frames that meet the threshold is increased, and if it is not met, the cumulative number of frames that meet the threshold is reset to zero. If the number of frames that continuously meet the threshold reaches a certain set threshold, the target can be identified as a stable target, and the target is output as a longitudinal following target. Similarly, the selected target can be continuously tested and discarded.
[0097] A second aspect of the present invention provides an electronic device, such as Figure 5 As shown, the electronic device 100 includes: at least one processor 101 and a memory 102 .
[0098] Among them, at least one processor 101 is communicatively connected with the memory 102, and the memory 102 stores a computer program that can be executed by the at least one processor 101. When the at least one processor 101 executes the computer program, the method for determining the longitudinal following target is implemented.
[0099] According to the electronic device of the embodiment of the present invention, the corresponding program for determining the longitudinal following target can be stored in the memory. When implementing the charging control method, the processor runs the program in the memory, obtains multiple first overlapping rates based on the detection data of the target object in multiple consecutive frames, and determines that the target object is the longitudinal following target when the multiple first overlapping rates meet the selected overlapping rate conditions, thereby avoiding problems such as discontinuity and instability when determining the longitudinal following target, improving the following experience, and improving the accuracy of selecting the longitudinal following target.
[0100] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the method for determining a longitudinal following target of the above-mentioned embodiment.
[0101] A fourth aspect of the present invention provides a vehicle, such as Figure 6 As shown, the vehicle 200 includes: an electronic device 100; Or, if Figure 7 As shown, vehicle 200 includes a sensor device 210 and a controller 220 .
[0102] The sensor device 210 is used to detect detection data of the target object; the controller 220 is connected to the sensor device 210 and is used to execute the method for determining the longitudinal following target of the above embodiment.
[0103] According to the vehicle of the embodiment of the present invention, when implementing the method for determining a longitudinal following target, the controller controls the sensor device to obtain detection data of the target object in multiple consecutive frames, and obtains multiple first overlapping rates through the detection data of the target object in multiple consecutive frames. When the multiple first overlapping rates meet the selected overlapping rate conditions, the target object is determined to be a longitudinal following target, thereby avoiding problems such as discontinuity and instability when determining the longitudinal following target, improving the following experience, and improving the accuracy of selecting the longitudinal following target.
[0104] In some embodiments, Figure 7 As shown, the sensor device 210 includes: a visual sensor 211 and a millimeter wave radar 212 .
[0105] Among them, the visual sensor 211 is connected to the controller 220, and is used to obtain the structural parameters of the target object and / or the target object angle relative to the vehicle coordinate system; the millimeter wave radar 212 is connected to the controller 220, and is used to detect the target object position relative to the vehicle coordinate system.
[0106] In the description of this specification, any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code including one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.
[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
[0108] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0109] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0110] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0111] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.
[0112] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, substrates, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example.
[0113] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.
Claims
1. A method for determining a longitudinal following target, characterized in that: include: Obtaining a first overlap ratio between the target object and the vehicle according to detection data of the target object; When a plurality of the first overlapping rates obtained according to the detection data of the target object in a plurality of consecutive frames satisfy a selected overlapping rate condition, the target object is determined to be a longitudinal following target.
2. The method according to claim 1, characterized in that The detection data of the target object includes the target object position, the target object angle and the structural parameters of the target object relative to the vehicle coordinate system.
3. The method according to claim 2, characterized in that The first overlap ratio between the target object and the vehicle is obtained according to the coordinates of the corner points of the target object relative to the vehicle, the position of the target object and the structural parameters of the target; The coordinates of the corner points of the target object relative to the vehicle are determined according to the position of the target object, the angle of the target object and the structural parameters of the target object.
4. The method according to claim 3, characterized in that The corner coordinates of the target object relative to the vehicle are determined according to the corner rotation coordinates of the target object and the position of the target object; The rotation coordinates of the corner points of the target object are obtained according to the coordinates of the corner points of the target object at the origin of the vehicle coordinate system and the angle of the target object.
5. The method according to claim 4, characterized in that The coordinates of the corner points of the target object at the origin of the vehicle coordinate system are determined according to the structural parameters of the target object.
6. The method according to claim 5, characterized in that The structural parameters of the target object include a length value of the target object and a width value of the target object.
7. The method according to claim 6, characterized in that The coordinates of the corner points of the target object at the origin of the vehicle coordinate system include the following: ( , / 2 )、( , - / 2 )、(0, / 2 ) and (0, - / 2 ); in, is the length of the target object, is the width of the target object.
8. The method according to any one of claims 3 to 7, characterized in that: The first overlap rate between the target object and the self-vehicle is expressed as a function of the self-vehicle coordinates obtained by the self-vehicle at the target object's ordinate according to the predicted driving trajectory, the coordinates of the corner point closest to the target object and the structural parameters of the target object, wherein the self-vehicle coordinates are determined based on the target object's position, and the target object's position includes the target object's ordinate coordinate relative to the self-vehicle coordinate system.
9. The method according to claim 8, characterized in that The vehicle coordinates include a horizontal coordinate and a vertical coordinate, wherein the vertical coordinate is taken as the vertical coordinate of the target object, and the horizontal coordinate is determined according to the vertical coordinate and the predicted driving trajectory.
10. The method according to claim 8, characterized in that The first overlap ratio between the target object and the vehicle is expressed as follows: ； or, ; in, is the first overlap ratio between the target object and the vehicle, is the horizontal coordinate of the vehicle, is the horizontal coordinate of the corner point closest to the target object and the vehicle, is the width of the vehicle.
11. The method according to any one of claims 1 to 6, characterized in that: The selected overlap rate condition includes that each of the first overlap rates obtained according to the detection data of the target object in each frame reaches a selected overlap rate threshold and the count value of multiple first overlap rates reaches a first set count threshold.
12. The method according to claim 11, characterized in that When the first overlap rate reaches the selected overlap rate threshold, the count value of the first overlap rate increases by one; if the first overlap rate obtained by any frame of detection data of the target object does not reach the selected overlap rate threshold, the count value of the first overlap rate is reset to zero.
13. The method according to claim 1, characterized in that The method further includes: when there are multiple targets determined according to the selected overlap rate condition, the target with the smallest relative longitudinal distance to the vehicle among the multiple targets is used as the longitudinal following target.
14. The method according to any one of claims 1 to 6 and 13, characterized in that The method further comprises: After determining the longitudinal following target, obtaining a second overlap rate between the longitudinal following target and the ego vehicle according to the detection data of the longitudinal following target; When a plurality of the second overlapping rates obtained based on the detection data of the longitudinal following target in a plurality of consecutive frames meet a discarding overlapping rate condition, the longitudinal following target is discarded.
15. The method according to claim 14, characterized in that The discarding overlap rate condition includes that each of the second overlap rates obtained according to the detection data of the longitudinal following target in each frame is less than a discarding overlap rate threshold and the count values of multiple second overlap rates reach a second set count threshold.
16. The method according to claim 15, characterized in that When the second overlap rate reaches the discard overlap rate threshold, the count value of the second overlap rate increases by one; if the second overlap rate obtained from the detection data of the longitudinal drive target in any frame does not reach the discard overlap rate threshold, the count value of the second overlap rate is cleared.
17. An electronic device, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and when the at least one processor executes the computer program, the method for determining a longitudinal following target according to any one of claims 1 to 16 is implemented.
18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for determining a longitudinal following target according to any one of claims 1 to 16 is implemented.
19. A vehicle, characterized in that: The vehicle comprises the electronic device of claim 17; Alternatively, the vehicle comprises: A sensor device, the sensor device is used to detect detection data of a target object; A controller, which is connected to the sensor device and is used to execute the method for determining a longitudinal following target as described in any one of claims 1-16.
20. The vehicle according to claim 19, characterized in that The sensor device comprises: A visual sensor connected to the controller, and used to obtain the structural parameters of the target object and / or the target object angle relative to the vehicle coordinate system; The millimeter wave radar is connected to the controller and is used to detect the target position of the target relative to the vehicle coordinate system.