Target screening method and device in curve scene, electronic equipment and storage medium

Abstract

The invention discloses a target screening method and device in a curve scene, electronic equipment and a storage medium, and relates to the field of automatic driving, and the method comprises the steps: obtaining the detection information of a left lane line and a right lane line of a lane where a vehicle is located, and generating a vehicle center trajectory; obtaining target visual detection position information and visual detection corner point information of a vehicle in front of the vehicle; according to the target visual detection position information of the vehicle in front of the vehicle and the central trajectory of the vehicle, calculating the nearest distance between the target visual position of the vehicle and the central trajectory of the vehicle, and judging whether the nearest distance is smaller than a dangerous collision distance threshold; according to the visual detection angular point information and the central trajectory of the vehicle, calculating the nearest distance between the target visual detection angular point of the vehicle and the central trajectory of the vehicle, and judging whether the nearest distance is smaller than a dangerous collision distance threshold value or not; setting a car following target; the step of setting the vehicle following target comprises setting the vehicle in front of the vehicle determined as the dangerous target as the vehicle following target and outputting the vehicle following target to vehicle control execution.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and in particular to target selection methods, devices, electronic devices, storage media, and vehicles in curve scenarios. Background Technology

[0002] The development of intelligent vehicles is in full swing, and driver assistance systems are becoming increasingly popular and gradually becoming standard features in vehicles. ACC (Adaptive Cruise Control), as an important component of driver assistance systems, monitors vehicles ahead to achieve braking and following control, reducing the driver's workload.

[0003] As a crucial step in the ACC system, the target selection function determines which vehicle targets need to be tracked, directly impacting whether the ACC system will mistrack or miss targets. For 1V1R (single camera, single radar) driver assistance systems, the target vehicle's position information combines camera and radar detection data. In curved scenarios, especially curves with significant curvature, lane detection performance often degrades, leading to discrepancies between lane detection results and actual conditions. This results in errors in judging the relative position of the vehicle after integrating camera and radar information and the lane lines, causing the target selection function to fail to correctly identify the vehicle to follow.

[0004] Therefore, a target selection solution is needed for curved driving scenarios to filter and lock the best target to follow, so as to achieve normal following in curved driving scenarios. Summary of the Invention

[0005] The purpose of this invention is to provide a target selection method, a target selection device, an electronic device, a storage medium, and a vehicle in a curved driving scenario, at least solving one technical problem in how to select a following target and how to calculate positional relationships and positional states.

[0006] This invention provides the following solution:

[0007] According to a first aspect of the present invention, a target selection method in a curved driving scenario is provided, the target selection method in a curved driving scenario includes:

[0008] Step S1: Obtain the detection information of the left and right lane lines of the lane where the vehicle is located, and generate the center trajectory line of the vehicle.

[0009] Step S2: Obtain the visual detection position information and visual detection corner point information of the vehicle target in front of the vehicle;

[0010] Step S3: Based on the visual detection position information of the vehicle target in front of the vehicle and the center trajectory line of the vehicle, calculate the closest distance between the visual position of the vehicle target and the center trajectory line of the vehicle, and determine whether it is less than the preset dangerous collision distance threshold.

[0011] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0012] Step S4: Based on the visual detection corner point information and the vehicle center trajectory line, calculate the closest distance between the vehicle target visual detection corner point and the vehicle center trajectory line, and determine whether it is less than the preset dangerous collision distance threshold.

[0013] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0014] Step S5: Set the target vehicle to follow;

[0015] Setting a following target involves designating the vehicle in front of the vehicle that is determined to be a dangerous target as the following target and outputting this designation to the vehicle control system.

[0016] Furthermore, step S1 includes:

[0017] Obtain visual detection information of the left and right lane lines of the lane where the vehicle is located. The left lane line is denoted as Lane_Left and the right lane line is denoted as Lane_Right. Generate the center trajectory line Curve of the vehicle based on Lane_Left and Lane_Right. Curve = 0.5 × (Lane_Left + Lane_Right).

[0018] Furthermore, step S2 includes:

[0019] Obtain the lateral position information Posi_Y and longitudinal position detection information Posi_X of the vehicle target in front of the vehicle, as well as the lateral position information CornerPosi_Y and longitudinal position detection information CornerPosi_X of the vehicle corner.

[0020] Furthermore, step S3 includes:

[0021] The shortest distance Dis_DetCurve from the target position (Posi_X, Posi_Y) of the vehicle ahead to the center trajectory line Curve of the vehicle is calculated using the Newton-Raphson iteration method. It is then determined whether Dis_DetCurve is less than the dangerous collision distance Dis_Thr. If it is less, the vehicle target is considered a dangerous target.

[0022] Furthermore, step S4 includes:

[0023] If the curve is a right turn, the right corner of the vehicle target is used; if the curve is a left turn, the left corner of the vehicle target is used. The shortest distance Dis_CornerCurve from the vehicle target corner position (CornerPosi_X, CornerPosi_Y) to the vehicle's center trajectory line Curve is calculated using Newton's iteration method. It is then determined whether Dis_CornerCurve is less than the dangerous collision distance Dis_Thr. If it is less, the vehicle target is considered a dangerous target.

[0024] Furthermore, step S5 includes:

[0025] Select the dangerous target that is closest to the vehicle's longitudinal distance as the target to follow.

[0026] According to a second aspect of the present invention, a target screening device for a curved road scenario is provided, the target screening device for a curved road scenario comprising:

[0027] The center trajectory acquisition module is used to acquire the left and right lane lines of the lane where the vehicle is located, and to detect and generate the center trajectory line of the vehicle.

[0028] The vehicle inspection point information acquisition module is used to acquire the visual detection position information and visual detection corner point information of the vehicle target in front of the vehicle;

[0029] The first dangerous target determination module is used to calculate the closest distance between the visual position of the vehicle target and the center trajectory line of the vehicle based on the visual detection position information of the vehicle target in front of the vehicle and the center trajectory line of the vehicle, and to determine whether it is less than the preset dangerous collision distance threshold.

[0030] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0031] The second dangerous target determination module is used to calculate the closest distance between the visual detection corner point of the vehicle target and the center trajectory line of the vehicle based on the visual detection corner point information and the vehicle center trajectory line, and to determine whether it is less than the preset dangerous collision distance threshold.

[0032] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0033] The vehicle following target setting module is used to set the vehicle following target;

[0034] Setting a following target involves designating the vehicle in front of the vehicle that is determined to be a dangerous target as the following target and outputting this designation to the vehicle control system.

[0035] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0036] The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the target selection method in the curve scenario.

[0037] According to a fourth aspect of the present invention, a computer-readable storage medium is provided storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the target selection method in the curve scenario.

[0038] According to a fifth aspect of the present invention, a vehicle is provided, comprising:

[0039] An electronic device for implementing the steps of the target selection method in the curve scenario;

[0040] The processor runs a program that, when running, executes the steps of the target selection method in the curve scenario from data output by the electronic device.

[0041] A storage medium for storing a program that, when running, executes the steps of the target selection method in the curve scenario based on data output from an electronic device.

[0042] The above solution achieves the following beneficial technical effects:

[0043] This application fully considers visual position information. Vehicle corner information and lane line detection information are from the same source, that is, they are both camera detection results. Even in the case of curves, the camera detection performance is reduced, but the correctness of the visual detection position of the vehicle target, the relative position of the corner detection position and the lane line detection can still be maintained. Based on this information, a target selection method in curves is proposed, which improves the accuracy and stability of target selection in the ACC function in curves. Attached Figure Description

[0044] Figure 1 This is a flowchart of a target selection method in a curved road scenario provided by one or more embodiments of the present invention.

[0045] Figure 2 This is a structural diagram of a target screening device in a curved road scenario provided by one or more embodiments of the present invention.

[0046] Figure 3 This is a schematic diagram of a multi-object screening method for a curved road scene provided in a specific embodiment of the present invention.

[0047] Figure 4 This is a schematic diagram of a curve scenario provided by a specific embodiment of the present invention.

[0048] Figure 5This is a block diagram of an electronic device for a target selection method in a curved road scenario provided by one or more embodiments of the present invention. Detailed Implementation

[0049] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Figure 1 This is a flowchart of a target selection method in a curved road scenario provided by one or more embodiments of the present invention.

[0051] like Figure 1 The target selection methods shown in the curve scenario include:

[0052] Step S1: Obtain the detection information of the left and right lane lines of the lane where the vehicle is located, and generate the center trajectory line of the vehicle.

[0053] Step S2: Obtain the visual detection position information and visual detection corner point information of the vehicle target in front of the vehicle;

[0054] Step S3: Based on the visual detection position information of the vehicle target in front of the vehicle and the center trajectory line of the vehicle, calculate the closest distance between the visual position of the vehicle target and the center trajectory line of the vehicle, and determine whether it is less than the preset dangerous collision distance threshold.

[0055] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0056] Step S4: Based on the visual detection corner point information and the vehicle center trajectory line, calculate the closest distance between the vehicle target visual detection corner point and the vehicle center trajectory line, and determine whether it is less than the preset dangerous collision distance threshold.

[0057] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0058] Step S5: Set the target vehicle to follow;

[0059] Setting a following target involves designating the vehicle in front of the vehicle that is determined to be a dangerous target as the following target and outputting this designation to the vehicle control system.

[0060] Specifically, in curve scenarios, especially sharp curves with small radii of curvature, lane detection performance tends to degrade. If the target vehicle ahead uses position information fused with radar detection results, errors can easily occur when calculating its relative position to the lane lines and its relative position to the vehicle's center trajectory. That is, the vehicle ahead may actually be within the vehicle's lane, but the target selection function may fail to correctly identify this positional relationship. The core strategy of this application is to consider visual position information. Vehicle corner information and lane detection information are from the same source, i.e., both are camera detection results. Even in curve scenarios, where camera detection performance decreases, the visual detection position of the vehicle target and the accuracy of the relative positional relationship between the corner detection position and the lane line detection can still be maintained. Based on this information, the accuracy and stability of target selection in the ACC function in curve scenarios can be improved.

[0061] In this embodiment, step S1 includes:

[0062] Obtain visual detection information of the left and right lane lines of the lane where the vehicle is located. The left lane line is denoted as Lane_Left and the right lane line is denoted as Lane_Right. Generate the center trajectory line Curve of the vehicle based on Lane_Left and Lane_Right. Curve = 0.5 × (Lane_Left + Lane_Right).

[0063] Specifically, in one particular embodiment, such as Figure 3 In the multi-object filtering method for curved scenes shown, step S1 involves obtaining the detection information of the left and right lane lines of the lane where the vehicle is located, and generating the center trajectory line of the vehicle based on the lane line detection information; the lane line detection information is represented by the following formula:

[0064] ,in This indicates the shortest lateral distance from the lane line to the vehicle. This indicates the angle between the lane line and the direction the camera is facing. Indicates the curvature of the lane line. This represents the rate of change of lane curvature. Therefore, the left lane can be represented as: The right lane line can be represented as: Based on the left lane line and the right lane line, the vehicle's center trajectory line (Curve) is generated, which is represented as:

[0065] .

[0066] In this embodiment, step S2 includes:

[0067] Obtain the lateral position information Posi_Y and longitudinal position detection information Posi_X of the vehicle target in front of the vehicle, as well as the lateral position information CornerPosi_Y and longitudinal position detection information CornerPosi_X of the vehicle corner.

[0068] In this embodiment, step S3 includes:

[0069] The shortest distance Dis_DetCurve from the target position (Posi_X, Posi_Y) of the vehicle ahead to the center trajectory line Curve of the vehicle is calculated using the Newton-Raphson iteration method. It is then determined whether Dis_DetCurve is less than the dangerous collision distance Dis_Thr. If it is less, the vehicle target is considered a dangerous target.

[0070] Specifically, in one particular embodiment, such as Figure 3 In the multi-target filtering method for the curved scene shown, step S2 involves obtaining the lateral and longitudinal detection position information of the vehicle target in front of the vehicle from the camera, namely Posi_Y and Posi_X, respectively. The lateral and longitudinal position detection information of the vehicle corner points are CornerPosi_Y and CornerPosi_X, respectively.

[0071] Step S3: Calculate the shortest distance Dis_DetCurve from the target position (Posi_X, Posi_Y) of the vehicle ahead to the center trajectory line Curve of the vehicle using the Newton-Raphson iteration method. If Dis_DetCurve is less than the dangerous collision distance Dis_Thr, then the vehicle is determined to be a dangerous target.

[0072] In another specific embodiment, the method for calculating the shortest distance from (Posi_X, Posi_Y) to the Curve based on Newton's iteration method is as follows: Figure 4 In the curved scenario shown, point P is the visual detection position of the vehicle target (Posi_X, Posi_Y), and point Q (PosiCurve_X, PosiCurve_Y) is on the vehicle's center trajectory line. The target's position at point Q is calculated in real time to minimize the length of PQ. The distance Dis between PQ can be calculated using the formula:

[0073] Calculations are performed, and since the square root is a monotonically increasing function, we need to consider... The minimum value is the same as the minimum value of Dis. There is a vehicle center trajectory line.

[0074] , recorded as Then we have: ,calculate The first derivatives are: , That is, the first derivative of the trajectory line of the vehicle's center. Let This allows us to find the Q-point location that minimizes Dis. To use Newton's iteration method, we define an auxiliary function... Then only the solution is needed. The iterative formula for Newton's method is as follows:

[0075] ;

[0076] in, yes The derivative of . In this example, let . = Then there is

[0077] , for The second derivative. Initial position of iteration. The longitudinal position PosiCurve_X of point Q can be solved by a finite number of iterations. The position of point Q can be solved by PosiCurve_Y=Cur(PosiCurve_X). The length Dis of PQ can be solved by combining the position of point P.

[0078] In this embodiment, step S4 includes:

[0079] If the curve is a right turn, the right corner of the vehicle target is used; if the curve is a left turn, the left corner of the vehicle target is used. The shortest distance Dis_CornerCurve from the vehicle target corner position (CornerPosi_X, CornerPosi_Y) to the vehicle's center trajectory line Curve is calculated using Newton's iteration method. It is then determined whether Dis_CornerCurve is less than the dangerous collision distance Dis_Thr. If it is less, the vehicle target is considered a dangerous target.

[0080] Specifically, in the above specific embodiment, it is determined whether the curve is a left turn or a right turn. If it is a left turn, the left corner point of the vehicle target is used; if it is a right turn, the right corner point of the vehicle target is used. After determining the corner point, the shortest distance Dis_CornerCurve from the corner point position (CornerPosi_X, CornerPosi_Y) to the vehicle's center trajectory line Curve is calculated using the Newton-Raphson iteration method. If Dis_CornerCurve is less than the dangerous collision distance Dis_Thr, the vehicle is determined to be a dangerous target. The calculation process of the shortest distance from (CornerPosi_X, CornerPosi_Y) to the Curve based on the Newton-Raphson iteration method is consistent with the method in step S3.

[0081] In this embodiment, step S5 includes:

[0082] Select the dangerous target that is closest to the vehicle's longitudinal distance as the target to follow.

[0083] Specifically, the vehicle selects the hazardous target that is closest to its own longitudinal distance from all hazardous targets and outputs it as the following target.

[0084] Using vehicle target visual position detection information and corner point position detection information that are from the same source as lane line detection information, the relative positional relationship between the vehicle target and the vehicle's center trajectory line is calculated, and the vehicle target is further determined to determine whether it is within the vehicle's lane. This method can improve the accuracy and stability of ACC following target recognition when the camera detection performance degrades in curve scenarios.

[0085] According to a second aspect of the present invention, a target screening device for a curve scenario is provided. The target screening device for a curve scenario includes: a center trajectory acquisition module, a vehicle inspection point information acquisition module, a first dangerous target determination module, a second dangerous target determination module, and a following target setting module.

[0086] The center trajectory acquisition module is used to acquire the detection information of the left and right lane lines of the lane where the vehicle is located, and generate the center trajectory line of the vehicle.

[0087] The vehicle inspection point information acquisition module is used to acquire the visual detection position information and visual detection corner point information of the vehicle target in front of the vehicle;

[0088] The first dangerous target determination module is used to calculate the closest distance between the visual position of the vehicle target and the center trajectory line of the vehicle based on the visual detection position information of the vehicle target in front of the vehicle and the center trajectory line of the vehicle, and to determine whether it is less than the preset dangerous collision distance threshold.

[0089] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0090] The second dangerous target determination module is used to calculate the closest distance between the visual detection corner point of the vehicle target and the center trajectory line of the vehicle based on the visual detection corner point information and the vehicle center trajectory line, and to determine whether it is less than the preset dangerous collision distance threshold.

[0091] If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target.

[0092] The vehicle following target setting module is used to set the vehicle following target;

[0093] Setting a following target involves designating the vehicle in front of the vehicle that is determined to be a dangerous target as the following target and outputting this designation to the vehicle control system.

[0094] It is worth noting that although this system / device only discloses the center trajectory acquisition module, the vehicle inspection point information acquisition module, the first dangerous target determination module, the second dangerous target determination module, and the following target setting module, it does not mean that this device is limited to the above-mentioned basic functional modules. On the contrary, what this invention intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. That is to say, this system / device is open rather than closed. It should not be assumed that the scope of protection of the claims of this invention is limited to the above-disclosed basic functional modules just because this embodiment only discloses a few basic functional modules.

[0095] Figure 5 This is a block diagram of an electronic device for a target selection method in a curved road scenario provided by one or more embodiments of the present invention.

[0096] like Figure 5 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0097] The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the target selection method in a curve scenario.

[0098] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a target selection method in a curve scenario.

[0099] This application also provides a vehicle, including:

[0100] Electronic equipment used to implement the steps of a target selection method in a curved road scenario;

[0101] The processor runs a program, and when the program runs, it executes the steps of the target selection method in the curve scenario based on the data output by the electronic device.

[0102] Storage medium used to store programs that, when running, execute the target selection method in a curve scenario based on data output from an electronic device.

[0103] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0104] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0105] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0106] Electronic devices can also obtain reset commands corresponding to the storage media. The reset commands corresponding to the storage media are provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and no restrictions are imposed here.

[0107] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0108] For ease of description, the above devices are described separately by function as various units and modules. Of course, in implementing this application, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0109] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0110] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0111] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A target selection method in a curved road scenario, characterized in that, The target selection method in the curved scenario includes: Step S1: Obtain the detection information of the left and right lane lines of the lane where the vehicle is located, and generate the center trajectory line of the vehicle. Step S2: Obtain the visual detection position information and visual detection corner point information of the vehicle target in front of the vehicle; Step S3: Based on the visual detection position information of the vehicle target in front of the vehicle and the center trajectory line of the vehicle, calculate the closest distance between the visual position of the vehicle target and the center trajectory line of the vehicle, and determine whether it is less than the preset dangerous collision distance threshold. If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target. Step S4: Based on the visual detection corner point information and the vehicle center trajectory line, calculate the closest distance between the vehicle target visual detection corner point and the vehicle center trajectory line, and determine whether it is less than the preset dangerous collision distance threshold. If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target. Step S5: Set the target vehicle to follow; Setting a following target involves designating the vehicle in front of the vehicle that is determined to be a dangerous target as the following target and outputting this designation to the vehicle control system.

2. The target selection method in a curved scene according to claim 1, characterized in that, Step S1 includes: Obtain visual detection information of the left and right lane lines of the lane where the vehicle is located. The left lane line is denoted as Lane_Left and the right lane line is denoted as Lane_Right. Generate the center trajectory line Curve of the vehicle based on Lane_Left and Lane_Right. Curve = 0.5 × (Lane_Left + Lane_Right).

3. The target selection method in a curved scene according to claim 2, characterized in that, Step S2 includes: Obtain the lateral position information Posi_Y and longitudinal position detection information Posi_X of the vehicle target in front of the vehicle, as well as the lateral position information CornerPosi_Y and longitudinal position detection information CornerPosi_X of the vehicle corner.

4. The target selection method in a curved scene according to claim 3, characterized in that, Step S3 includes: The shortest distance Dis_DetCurve from the target position (Posi_X, Posi_Y) of the vehicle ahead to the center trajectory line Curve of the vehicle is calculated using the Newton-Raphson iteration method. It is then determined whether Dis_DetCurve is less than the dangerous collision distance Dis_Thr. If it is less, the vehicle target is considered a dangerous target.

5. The target selection method in a curved scene according to claim 3, characterized in that, Step S4 includes: If the curve is a right turn, the right corner of the vehicle target is used; if the curve is a left turn, the left corner of the vehicle target is used. The shortest distance Dis_CornerCurve from the vehicle target corner position (CornerPosi_X, CornerPosi_Y) to the vehicle's center trajectory line Curve is calculated using Newton's iteration method. It is then determined whether Dis_CornerCurve is less than the dangerous collision distance Dis_Thr. If it is less, the vehicle target is considered a dangerous target.

6. The target selection method in a curved scene according to claim 3, characterized in that, Step S5 includes: Select the dangerous target that is closest to the vehicle's longitudinal distance as the target to follow.

7. A target selection device for curved road scenarios, characterized in that, The target selection device in the curved scenario includes: The center trajectory acquisition module is used to acquire the detection information of the left and right lane lines of the lane where the vehicle is located, and generate the center trajectory line of the vehicle. The vehicle inspection point information acquisition module is used to acquire the visual detection position information and visual detection corner point information of the vehicle target in front of the vehicle; The first dangerous target determination module is used to calculate the closest distance between the visual position of the vehicle target and the center trajectory line of the vehicle based on the visual detection position information of the vehicle target in front of the vehicle and the center trajectory line of the vehicle, and to determine whether it is less than the preset dangerous collision distance threshold. If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target. The second dangerous target determination module is used to calculate the closest distance between the visual detection corner point of the vehicle target and the center trajectory line of the vehicle based on the visual detection corner point information and the vehicle center trajectory line, and to determine whether it is less than the preset dangerous collision distance threshold. If the value is less than 0, then the vehicle in front of the vehicle is considered a dangerous target. The vehicle following target setting module is used to set the vehicle following target; Setting a following target involves designating the vehicle in front of the vehicle that is determined to be a dangerous target as the following target and outputting this designation to the vehicle control system.

8. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of the target selection method in a curve scenario as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The device stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the target selection method in a curve scenario as described in any one of claims 1 to 6.

10. A vehicle, characterized in that, include: An electronic device for implementing the steps of the target selection method in a curve scenario as described in any one of claims 1 to 6; A processor that runs a program that, when the program is running, performs the steps of the target selection method in a curve scenario as described in any one of claims 1 to 6 from data output by an electronic device. A storage medium for storing a program that, when running, performs the steps of the target selection method in a curve scenario as described in any one of claims 1 to 6 on data output from an electronic device.

Images