Methods for determining curve curvature, vehicles, and readable storage media

Abstract

This application provides a method for determining the curvature of a curve, a vehicle, and a readable storage medium. The method includes controlling the left and right low beam headlights of the vehicle to illuminate independently at different times. A first image is acquired when the left low beam is illuminated independently, and a second image is acquired when the right low beam is illuminated independently. Based on the first and second images, an estimated curvature value for the curve is determined. Based on the estimated curvature value, the vehicle's steering system is controlled to navigate the curve. And / or a warning device on the vehicle is controlled to issue a warning message. Thus, the determined estimated curvature value of the curve is highly accurate.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to a method for determining curve curvature, a vehicle, and a readable storage medium. Background Technology

[0002] The circular curves in underground parking garages are enclosed, low-light environments. When vehicles drive on these curves, there is a risk of scraping or colliding because there are no clean lane edge markings.

[0003] Some vehicles use cameras to capture images to determine the curvature of curves. However, in low-light environments, cameras struggle to capture effective features, and the calculation of curve curvature relies heavily on lane edge fitting, making it unsuitable for scenarios without lane edges, such as underground parking garages, resulting in poor accuracy in determining curve curvature. Summary of the Invention

[0004] This application provides a highly accurate method for determining curve curvature, a vehicle, and a readable storage medium.

[0005] This application provides a method for determining the curvature of a curve, including: Control the left and right low beam headlights of the vehicle to illuminate independently at different times; Acquire a first image when the left low beam headlight is turned on alone and a second image when the right low beam headlight is turned on alone; Based on the first image and the second image, determine the curvature estimate of the bend; Based on the curvature estimate, control the vehicle's steering system to navigate the curve; and / or control the vehicle's warning device to issue a warning message.

[0006] Further, determining the curvature estimate of the curve based on the first image and the second image includes: Extract the center of the light spot formed by the low beam lamp illumination from the first image and the second image respectively; The actual depth from the center of the light spot to the camera is determined based on the pixel coordinates of the center of the light spot. The curvature estimate of the curve is determined based on the depth difference between the centers of the two light spots and the actual depth of the camera.

[0007] Further, determining the actual depth from the center of the light spot to the camera based on the pixel coordinates of the center of the light spot includes: The initial depth from the center of the light spot to the camera is determined based on the pixel coordinates of the center of the light spot. Obtain the steering wheel angle of the vehicle; Based on the steering wheel angle and the vehicle's steering ratio, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected respectively, so as to determine the actual depth from the center of the two light spots to the camera respectively.

[0008] Further, determining the initial depth from the center of the light spot to the camera based on the pixel coordinates of the center of the light spot includes: The initial depth from the center of the light spot to the camera is determined using the following formula. : , in, The height of the camera above the ground. The pitch angle of the camera. The pixel ordinate of the center of the light spot. Let be the ordinate of the principal pixel of the camera. Let y be the focal length of the camera along the y-axis.

[0009] Further, the step of correcting the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera based on the steering wheel angle and the vehicle's steering gear ratio, respectively, to determine the actual depth from the center of the two light spots to the camera, includes: The current steering direction and wheel steering angle of the vehicle are determined based on the steering wheel angle and the steering gear ratio of the vehicle. If the vehicle is turning left, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected according to the wheel steering angle and the first formula group, respectively. If the vehicle is turning right, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected according to the wheel steering angle and the second formula group, respectively.

[0010] Furthermore, the first set of formulas is as follows: , , The second set of formulas is: , , in, The actual depth from the center of the light spot in the first image to the camera. The distance from the center of the light spot in the second image to the actual depth of the camera. The initial depth from the center of the light spot in the first image to the camera is [value]. The initial depth from the center of the light spot in the second image to the camera is [value]. For the wheel steering angle, The distance between the left low beam headlight and the right low beam headlight.

[0011] Further, determining the curvature estimate of the curve based on the depth difference between the centers of the two light spots and the actual depth of the camera includes: The curvature estimate of the curve is determined using the following formula. : , in, Let be the radius of curvature of the curve. The distance between the left low beam headlight and the right low beam headlight. The depth difference between the centers of the two light spots and the actual depth of the camera. , The actual depth from the center of the light spot in the first image to the camera. The distance from the center of the light spot in the second image to the actual depth of the camera is denoted by .

[0012] Furthermore, the method for determining the curvature of a curve also includes: Repeat the following steps multiple times: Control the left and right low beam headlights of the vehicle to illuminate independently at different times; Acquire a first image when the left low beam headlight is turned on alone and a second image when the right low beam headlight is turned on alone; Based on the first image and the second image, determine the curvature estimate of the bend; To obtain multiple curvature estimates; The step of controlling the vehicle's steering system to navigate the curve based on the curvature estimate, and / or controlling the vehicle's warning device to issue a warning message, includes: A sliding window fitting is performed on multiple curvature estimates to obtain the applied curvature value of the curve; Based on the curvature application value, control the vehicle's steering system to navigate the curve; and / or control the vehicle's prompting device to issue a prompt message.

[0013] This application provides a vehicle, including: a processor and a memory communicatively connected to the processor; the memory is used to store computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the curve curvature determination method as described in any of the above embodiments.

[0014] This application provides a readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the curve curvature determination method as described in any of the above embodiments.

[0015] The method for determining the curvature of a curve provided in this application includes acquiring a first image when the left low beam is turned on alone and a second image when the right low beam is turned on alone. Based on the first and second images, an estimated value of the curve's curvature is determined. Thus, in low-light conditions, by using the left and right low beams in a time-sharing manner, the acquired first and second images become clearer, resulting in a more accurate estimated value of the curve's curvature.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] Figure 1 The diagram shown is a flowchart of a method for determining the curvature of a curve according to an embodiment of this application; Figure 2 As shown Figure 1 The flowchart shown is a sub-flowchart of the method for determining the curvature of a curve. Figure 3 As shown Figure 2 The flowchart shown is a sub-flowchart of the method for determining the curvature of a curve. Figure 4 As shown Figure 3 The flowchart shown is a sub-flowchart of the method for determining the curvature of a curve. Figure 5 The diagram shown is a schematic frame diagram of a vehicle according to an embodiment of this application. Detailed Implementation

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0020] To better understand the technical solution of this application, the method for determining curve curvature, the vehicle, and the readable storage medium of this application will be described in detail below with reference to the accompanying drawings. Unless otherwise specified, the features in the following embodiments and implementations can be combined with each other.

[0021] Figure 1 The diagram shows a flowchart of a method for determining the curvature of a curve according to an embodiment of this application. See also... Figure 1 As shown in the figure, this application provides a method for determining the curvature of a curve, which includes steps S1 to S4.

[0022] In step S1, the vehicle's left and right low beam headlights are controlled to illuminate independently, with each headlight illuminating at a different time. This can be achieved by first illuminating one of the headlights individually, and then illuminating the other separately. This avoids overlapping and interference caused by the light spots from the left and right low beam headlights when they are illuminated.

[0023] In one embodiment, after the vehicle enters the circular curve of the underground parking garage, the vehicle's low beam headlights and right low beam headlights are controlled to be turned on separately at different times.

[0024] In one embodiment, after the vehicle enters the underground parking garage, a real-time image of the road surface in front of the vehicle is acquired from a camera. An image recognition algorithm is then used to identify whether the road surface image contains features of a roundabout. If a roundabout is detected, the vehicle's left and right low beam headlights are activated separately in a time-sharing manner.

[0025] In one embodiment, when a user's trigger signal is detected, the vehicle's left and right low beam headlights are controlled to illuminate independently, time-sharingly. The user's trigger signal can be a button press signal.

[0026] In step S2, a first image is acquired when the left low beam is turned on alone, and a second image is acquired when the right low beam is turned on alone. The first image may include at least one frame of image data, and the second image may include at least one frame of image data.

[0027] In one embodiment, a first image captured by the camera when the left low beam is turned on alone and a second image captured by the camera when the right low beam is turned on alone are acquired. The camera can be a monocular camera.

[0028] In step S3, the curvature estimate of the curve is determined based on the first image and the second image.

[0029] Figure 2 As shown Figure 1 The flowchart shown illustrates the method for determining the curvature of a curve. See also... Figure 2 As shown, in one embodiment, step S3 includes steps S31 to S33.

[0030] In step S31, the centers of the light spots formed by the corresponding low beam illumination in the first image and the second image are extracted respectively. Specifically, the center of the light spot formed by the corresponding left low beam illumination in the first image and the center of the light spot formed by the corresponding right low beam illumination in the second image can be extracted.

[0031] In one embodiment, before step S31, the first image and the second image are preprocessed respectively, and the preprocessing includes removing image noise using a Gaussian filtering algorithm.

[0032] In one embodiment, a threshold segmentation algorithm is used to distinguish the light spot from the background, and the center of the distinguished light spot is extracted. This ensures the accuracy of the pixel coordinate extraction of the light spot center, providing accurate pixel coordinate information for depth calculation.

[0033] In step S32, the actual depth from the center of the light spot to the camera is determined based on the pixel coordinates of the center of the light spot. Specifically, the actual depth from the center of each light spot to the camera can be determined based on the pixel coordinates of the center of the light spot in the first image. Alternatively, the actual depth from the center of the light spot to the camera can be determined based on the pixel coordinates of the center of the light spot in the second image.

[0034] Figure 3 As shown Figure 2 The flowchart shown illustrates the method for determining the curvature of a curve. See also... Figure 3 As shown, in one embodiment, step S32 includes steps S321 to S323.

[0035] In step S321, the initial depth from the center of the light spot to the camera is determined based on the pixel coordinates of the center of the light spot. This initial depth can be determined using the pixel coordinates of the center of the light spot and camera parameters. The camera parameters include extrinsic and intrinsic parameters. Extrinsic parameters include the camera's height above the ground and its pitch angle. Intrinsic parameters include the principal pixel coordinates of the camera and its focal length.

[0036] In one embodiment, step S321 includes: determining the initial depth from the center of the light spot to the camera according to the following formula. : , in, The height of the camera above the ground. The camera's tilt angle. The ordinate of the pixel at the center of the light spot. The ordinate of the principal pixel of the camera. The focal length along the y-axis of the camera is [value].

[0037] The initial depth from the center of the light spot in the first image to the camera can be determined using the formulas described above. The distance from the center of the light spot in the second image to the initial depth of the camera. The method for determining the initial depth from the center of the light spot to the camera is simple and highly accurate.

[0038] In step S322, the steering wheel angle of the vehicle is obtained.

[0039] In step S323, based on the vehicle's steering wheel angle and steering ratio, the initial depths from the center of the light spot in the first image to the camera and the initial depths from the center of the light spot in the second image to the camera are corrected respectively, to determine the actual depths from the center of the two light spots to the camera. The vehicle's steering ratio is the proportional relationship between the steering wheel rotation angle and the actual rotation angle of the front wheels.

[0040] When a vehicle turns, its body rotates around the steering center, causing the transmission angles of the left and right low beam headlights to shift relative to the curve's edge. By adjusting the vehicle's steering wheel angle and steering ratio, the initial depth from the center of the two light spots to the camera can be corrected. This compensates for the depth shift caused by the vehicle's body roll, resulting in a more accurate estimate of the curve's curvature.

[0041] Figure 4 As shown Figure 3 The flowchart shown illustrates the method for determining the curvature of a curve. See also... Figure 4 As shown, in one embodiment, step S323 includes steps S3231 to S3233.

[0042] In step S3231, the current steering direction and wheel steering angle of the vehicle are determined based on the steering wheel angle and the vehicle's steering gear ratio.

[0043] In one embodiment, the current wheel steering angle of the vehicle is determined based on the ratio of the vehicle's steering wheel angle to the vehicle's steering gear ratio.

[0044] In this embodiment, the current vehicle steering direction is determined by the positive or negative value of the wheel steering angle. When the vehicle is turning left, the wheel steering angle is positive; when the vehicle is turning right, the wheel steering angle is negative. This ensures that the correction of the initial depth from the center of the two light spots to the camera is more accurate when the vehicle is turning left or right.

[0045] In step S3232, if the vehicle is turning left, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected according to the wheel steering angle and the first formula group, respectively.

[0046] Specifically, if the vehicle is turning left, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected respectively by the first formula group based on the distance between the left and right low beam headlights and the wheel steering angle.

[0047] In one embodiment, the first set of formulas is: , , in, The distance from the center of the light spot in the first image to the actual depth of the camera. The distance from the center of the light spot in the second image to the actual depth of the camera. The initial depth from the center of the light spot in the first image to the camera is [value]. The initial depth from the center of the light spot in the second image to the camera is [value]. For the wheel steering angle, This refers to the distance between the left and right low beam headlights.

[0048] In step S3233, if the vehicle is turning right, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected according to the wheel steering angle and the second formula group, respectively.

[0049] Specifically, if the vehicle is turning right, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected respectively by the second formula group based on the distance between the left and right low beam headlights and the wheel steering angle.

[0050] In one embodiment, the second set of formulas is: , , In this way, the initial depth from the center of the light spot to the camera can be compensated according to different turning directions using different formula sets, thus obtaining a more accurate actual depth from the center of the light spot to the camera.

[0051] In step S33, the curvature estimate of the curve is determined based on the depth difference between the centers of the two light spots and the actual depth of the camera. Specifically, the curvature estimate of the curve is determined based on the depth difference between the centers of the two light spots and the actual depth of the camera, and the distance between the left and right low beam lamps.

[0052] In one embodiment, step S33 includes: determining the curvature estimate of the curve using the following formula. : , in, Let be the radius of curvature of the curve. This refers to the distance between the left and right low beam headlights. The depth difference between the centers of the two light spots and the actual depth of the camera. , The distance from the center of the light spot in the first image to the actual depth of the camera. The distance from the center of the light spot in the second image to the actual depth of the camera.

[0053] In this way, the curve can be approximated as a circular arc. There is a fixed geometric relationship between the depth difference of the two light spots and the radius of the arc. The curvature of the curve can be estimated by inversely calculating the depth difference of the two light spots. Therefore, the curvature of the curve can be estimated without fitting the edge of the lane. This method is suitable for scenarios without lane edges, such as underground parking garages. The method is simple and highly operable.

[0054] In step S4, based on the curvature estimation value, the vehicle's steering system is controlled to navigate the curve; and / or the vehicle's warning device is controlled to issue a warning message. In this way, based on the curvature estimation value, vehicle steering control and collision warnings between the vehicle and the wall can be achieved, thereby improving vehicle safety and enhancing the user experience.

[0055] In one embodiment, the desired steering angle of the vehicle is determined based on a curvature estimate. The vehicle's steering system is then controlled to steer the vehicle through a curve ahead, based on the steering angle.

[0056] In one embodiment, the desired steering angle of the vehicle is determined based on the curvature estimation value. The current steering angle of the vehicle is obtained. If the angular deviation between the current steering angle and the desired steering angle is greater than a set angle threshold, the vehicle's warning device is controlled to issue a warning message. The warning message may include, but is not limited to, at least one of visual, auditory, and tactile cues. When the warning message is visual, the warning device may include, but is not limited to, the instrument panel and the central control screen. When the warning message is auditory, the warning device may include, but is not limited to, an alarm. When the warning message is tactile, the warning device may include, but is not limited to, a seat vibration device and a steering wheel vibration device.

[0057] The method for determining the curvature of a curve provided in this application includes acquiring a first image when the left low beam is turned on alone and a second image when the right low beam is turned on alone. Based on the first and second images, an estimated value of the curve's curvature is determined. Thus, in low-light conditions, by using the left and right low beams in a time-sharing manner, the acquired first and second images become clearer, resulting in a more accurate estimated value of the curve's curvature.

[0058] In one embodiment, the method for determining curve curvature further includes: Steps S1 to S3 are executed multiple times to obtain multiple curvature estimates.

[0059] Step S4 includes: A sliding window fitting is performed on multiple curvature estimates to obtain the applied curvature value of the curve.

[0060] Based on the curvature application value, control the vehicle's steering system to navigate curves; and / or control the vehicle's prompting devices to issue prompting information.

[0061] In one embodiment, the desired steering angle of the vehicle is determined based on the curvature application value. Based on the vehicle's steering angle, the vehicle's steering system is controlled to steer through the curve ahead.

[0062] In one embodiment, the desired steering angle of the vehicle is determined based on the curvature application value. The current steering angle of the vehicle is obtained. If the angular deviation between the current steering angle and the desired steering angle exceeds a set angle threshold, a warning device controlling the vehicle issues a warning message. This results in a more accurate curvature application value for the curve, providing more precise information for vehicle steering control and collision warning.

[0063] Figure 5 The diagram shown is a schematic frame of a vehicle according to one embodiment of this application. See also... Figure 5As shown, this application embodiment also provides a vehicle 100, which includes a processor 101 and a memory 102 communicatively connected to the processor 101. The memory 102 is used to store computer execution instructions. The processor 101 executes the computer execution instructions stored in the memory 102 to implement the curve curvature determination method described in any of the above embodiments.

[0064] This application also provides a readable storage medium storing computer-executable instructions, which, when executed by processor 101, are used to implement the curve curvature determination method as described in any of the above embodiments.

[0065] This application also provides a computer program product, including a computer program / instruction, which, when executed by processor 101, implements the curve curvature determination method as described in any of the above embodiments.

[0066] This application also provides a computer program stored in a readable storage medium, and when the processor 101 executes the computer program, it causes the processor 101 to perform the curve curvature determination method as described in any of the above embodiments.

[0067] This application may take the form of a computer program product implemented on one or more readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented using any method or technology. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of readable storage media include, but are not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0068] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for determining the curvature of a curve, characterized in that, include: Control the vehicle's left and right low beam headlights to illuminate independently at different times; Acquire a first image when the left low beam headlight is turned on alone and a second image when the right low beam headlight is turned on alone; Based on the first image and the second image, determine the curvature estimate of the bend; Determining the curvature estimate of the curve based on the first image and the second image includes: Extract the center of the light spot formed by the low beam lamp illumination from the first image and the second image respectively; The actual depth from the center of the light spot to the camera is determined based on the pixel coordinates of the center of the light spot. The curvature estimate of the bend is determined based on the depth difference between the centers of the two light spots and the actual depth of the camera. Based on the curvature estimate, control the vehicle's steering system to navigate the curve; and / or control the vehicle's warning device to issue a warning message.

2. The method for determining the curvature of a curve according to claim 1, characterized in that, Determining the actual depth from the center of the light spot to the camera based on the pixel coordinates of the center of the light spot includes: The initial depth from the center of the light spot to the camera is determined based on the pixel coordinates of the center of the light spot. Obtain the steering wheel angle of the vehicle; Based on the steering wheel angle and the vehicle's steering ratio, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected respectively, so as to determine the actual depth from the center of the two light spots to the camera respectively.

3. The method for determining the curvature of a curve according to claim 2, characterized in that, Determining the initial depth from the center of the light spot to the camera based on the pixel coordinates of the center of the light spot includes: The initial depth from the center of the light spot to the camera is determined using the following formula. : ， in, The height of the camera above the ground. The pitch angle of the camera. The pixel ordinate of the center of the light spot. Let be the ordinate of the principal pixel of the camera. Let y be the focal length of the camera along the y-axis.

4. The method for determining the curvature of a curve according to claim 2, characterized in that, The step of correcting the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera, respectively, based on the steering wheel angle and the vehicle's steering gear ratio, to determine the actual depth from the center of the two light spots to the camera, includes: The current steering direction and wheel steering angle of the vehicle are determined based on the steering wheel angle and the steering gear ratio of the vehicle. If the vehicle is turning left, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected according to the wheel steering angle and the first formula group, respectively. If the vehicle is turning right, the initial depth from the center of the light spot in the first image to the camera and the initial depth from the center of the light spot in the second image to the camera are corrected according to the wheel steering angle and the second formula group, respectively.

5. The method for determining the curvature of a curve according to claim 4, characterized in that, The first set of formulas is: ， ， The second set of formulas is: ， ， in, The actual depth from the center of the light spot in the first image to the camera. The distance from the center of the light spot in the second image to the actual depth of the camera. The initial depth from the center of the light spot in the first image to the camera is [value]. The initial depth from the center of the light spot in the second image to the camera is [value]. For the wheel steering angle, The distance between the left low beam headlight and the right low beam headlight.

6. The method for determining the curvature of a curve according to claim 1, characterized in that, Determining the curvature estimate of the curve based on the depth difference between the centers of the two light spots and the actual depth of the camera includes: The curvature estimate of the curve is determined using the following formula. : ， in, Let be the radius of curvature of the curve. The distance between the left low beam headlight and the right low beam headlight. The depth difference between the centers of the two light spots and the actual depth of the camera. , The actual depth from the center of the light spot in the first image to the camera. The distance from the center of the light spot in the second image to the actual depth of the camera is denoted by .

7. The method for determining the curvature of a curve according to claim 1, characterized in that, The method for determining the curvature of a curve also includes: Repeat the following steps multiple times: Control the left and right low beam headlights of the vehicle to illuminate independently at different times; Acquire a first image when the left low beam headlight is turned on alone and a second image when the right low beam headlight is turned on alone; Based on the first image and the second image, determine the curvature estimate of the bend; To obtain multiple curvature estimates; The step of controlling the vehicle's steering system to navigate the curve based on the curvature estimate, and / or controlling the vehicle's warning device to issue a warning message, includes: A sliding window fitting is performed on multiple curvature estimates to obtain the applied curvature value of the curve; Based on the curvature application value, control the vehicle's steering system to navigate the curve; and / or control the vehicle's prompting device to issue a prompt message.

8. A vehicle, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory is used to store computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the curve curvature determination method as described in any one of claims 1 to 7.

9. A readable storage medium, characterized in that, The readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the curve curvature determination method as described in any one of claims 1 to 7.

Images