Lane lighting control method and system for self-closed-loop intelligent vehicle lighting system

Abstract

The present invention provides a lane lighting control method and system for a self-closed-loop intelligent vehicle lighting system, belonging to the field of intelligent vehicle lighting control technology. The method includes: preparing relevant calibration tools and completing the construction of a calibration site; arranging targets on the wall of the calibration site to complete the calibration of camera extrinsic parameters; preparing calibration images required for the vehicle lights, and controlling the vehicle lights to project the required calibration pattern onto the wall via a driver board; controlling the camera to capture the pattern projected by the vehicle lights, performing calibration calculations, and saving the calibration results; obtaining lane line detection results in the vehicle coordinate system through the vehicle forward visual perception system; converting the lane line detection results in the vehicle coordinate system into lane lines in the vehicle light image coordinate system through the transformation relationship between the vehicle coordinate system and the vehicle light image coordinate system; and controlling the matrix LED headlights to project a fixed range of light forward based on the lane lines in the vehicle light image coordinate system to achieve lane lighting. High-resolution calibration of matrix LED headlights is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent vehicle lamp control, and in particular to a lane lighting control method and system for a self-closed-loop intelligent vehicle lamp system. Background Art

[0002] As an essential component of vehicle safety, headlights improve road visibility and enhance the driver's field of vision. However, with the continuous development of artificial intelligence technology, people are no longer satisfied with the role of headlights for traditional lighting, and are now expecting more intelligent and personalized lighting methods.

[0003] The self-closed-loop intelligent headlight system captures environmental information during driving through the camera embedded in the headlight module, and drives the LED lights to illuminate the lane of the vehicle after calculation and processing by the AI ​​algorithm, so that all intelligent functions are realized in a closed loop within the headlight system. However, during the operation of this system, in order to obtain good lighting effects and driving experience, light beam control is crucial. Therefore, it is necessary to accurately map the objects perceived by the perception system to the smallest control unit (lamp beads or light partitions) of the lighting system in order to form precise control of the lighting system. However, the existing headlight system calibration method usually requires headlight calibration on a sufficient site, and the calibration process is usually based on obstacle calibration, without calibrating the lane lighting. As a result, the illumination range of the headlights is not projected based on the actual area of ​​the lane during vehicle driving, affecting the lighting effect and driving experience.

[0004] Therefore, there is an urgent need to provide a lane lighting calibration method for matrix LED headlights that can quickly achieve high resolution under conditions of limited site area. Summary of the Invention

[0005] The purpose of the present invention is to overcome at least one technical problem existing in the prior art. On the one hand, a lane lighting control method for a self-closed-loop intelligent headlight system is provided, and the method includes: S1: building a calibration scene based on a vehicle equipped with a matrix LED headlight and an assisted driving perception system; S2: arranging a target image at a preset position in the built calibration scene, and collecting the target image information by a camera placed in the assisted driving perception system; S3: using Zhang's calibration method to calculate the external parameters of the camera based on the target image information; S4: based on the preset calibration image, controlling the matrix LED headlight through a driving board to project a projection image corresponding to the calibration image in a predetermined direction; S5: extracting four pixel points in the calibration image so that their grayscale values ​​are preset grayscale values; S6: controlling the camera to shoot the projection image projected in a predetermined direction; S7: obtaining four pixels in the calibration image The method comprises the following steps: step S8: constructing a conversion relationship between the coordinates of at least one pixel point in the projected image in the vehicle coordinate system and the coordinates of at least one pixel point in the calibration image in the pixel coordinate system by fitting an affine transformation matrix; step S9: calculating an affine transformation matrix by respectively bringing the four pairs of pixel point coordinates obtained in step S7 into the conversion relationship of step S8; step S10: obtaining a lane line detection result in the vehicle coordinate system through the assisted driving perception system; step S11: converting the lane line detection result in the vehicle coordinate system into a lane line equation in the pixel coordinate system through the conversion relationship; and step S12: controlling the matrix LED headlights to project light that matches the lane range forward based on the lane line equation in the pixel coordinate system.

[0006] Furthermore, step S2 includes: S201: using a checkerboard image as the target image, each cell in the checkerboard image is equal in size; S202: placing the target image on a spatial plane directly in front of the vehicle; S203: adjusting the checkerboard position so that each point in the checkerboard image is at the same longitudinal distance from the optical center of the camera in the assisted driving perception system.

[0007] Furthermore, step S3 includes: S301: recording the length, width, height of the camera from the ground, and distance from the spatial plane to the camera of each cell on the chessboard; S302: calculating the external parameters of the camera using Zhang's calibration method based on the length, width, height of the camera from the ground, and distance from the spatial plane to the camera of each cell on the chessboard, and the coordinates of the cell corner points in the chessboard image in the pixel coordinate system contained in the target image information collected by the camera.

[0008] Furthermore, the method also includes: when the site space is sufficient, step S4 includes controlling the matrix LED headlights to project a projection image corresponding to the calibration image onto the ground in front of the vehicle; when the site space is insufficient, step S4 includes controlling the matrix LED headlights to project a projection image corresponding to the calibration image onto the spatial plane in front of the vehicle.

[0009] Furthermore, the method also includes: when the space on the site is insufficient, the step S7 also includes: S701: controlling a pixel point in the calibration image to be projected onto the first spatial plane and the second spatial plane in sequence through the matrix LED headlight projection; S702: obtaining the coordinates (x1, y1, z1) of the projected pixel point m1 corresponding to a pixel point in the calibration image on the first spatial plane in the vehicle coordinate system through the external parameters of the camera; S703: obtaining the coordinates (x2, y2, z2) of the projected pixel point m2 corresponding to a pixel point in the calibration image on the second spatial plane in the vehicle coordinate system through the external parameters of the camera; S704: constructing a three-dimensional spatial coordinate relationship through the coordinates (x1, y1, z1) of the pixel point m1 in the vehicle coordinate system and the coordinates (x2, y2, z2) of the pixel point m2 in the vehicle coordinate system as follows: S705: Based on the three-dimensional space coordinate relationship, a theoretical ground projection point m3 of a certain LED lamp bead on the matrix LED headlight is obtained as the coordinate of at least one pixel point in the projected image in the vehicle coordinate system.

[0010] Furthermore, any three of the four pixel points extracted in step S5 are not on the same straight line.

[0011] Furthermore, the conversion relationship in step S8 is:

[0012]

[0013] Where P is the coordinate of the pixel point on the projected image of the matrix LED headlight in the vehicle coordinate system, P' is the coordinate of the pixel point on the calibration image of the matrix LED headlight in the pixel coordinate system, and T is the affine transformation matrix.

[0014] Furthermore, the step S10 includes: obtaining a lane line detection result in a vehicle coordinate system through the assisted driving perception system, wherein the detection result includes position information of the left and right lane lines of the lane in the vehicle coordinate system.

[0015] Furthermore, the step S11 includes: S1101: sampling four points at equal intervals on the lane line detection result to obtain the coordinates of the four points in the vehicle coordinate system; S1102: converting the four sampled points into coordinates in the pixel coordinate system based on the affine transformation matrix; S1103: fitting the cubic curve equations of the two lane lines in the pixel coordinate system of the headlight calibration image, where the left lane line equation is y=C0+C1x+C2x 2 +C3x 3 , the equation of the right lane is y=C4+C5x+C6x 2 +C7x 3 ; S1104: The area between the left lane line equation and the right lane line equation is the lane range.

[0016] In the second aspect, the present invention provides a lane lighting control system for a self-closed-loop intelligent vehicle lighting system, which is implemented by the above-mentioned lane lighting control method for a self-closed-loop intelligent vehicle lighting system. The system includes: a target image information acquisition module, which is suitable for arranging a target image at a preset position in a constructed calibration scene, and acquiring the target image information by a camera placed in the assisted driving perception system; a camera external parameter calculation module, which is suitable for calculating the external parameters of the camera based on the target image information by using Zhang's calibration method; a projection module, which is suitable for controlling the matrix LED vehicle light through a driving board based on a preset calibration image to project a projection image corresponding to the calibration image in a predetermined direction; extracting four pixel points in the calibration image so that their grayscale values ​​are preset grayscale values; a coordinate acquisition module, which is suitable for controlling the camera to shoot the projection image projected in a predetermined direction; obtaining the pixel coordinates of four pixel points in the calibration image. The vehicle coordinate system is configured to obtain the coordinates of the pixel points in the projected image corresponding to the four pixel points in the calibration image in the vehicle coordinate system through the external parameters of the camera; a coordinate conversion module is configured to construct a conversion relationship between the coordinates of at least one pixel point in the projected image in the vehicle coordinate system and the coordinates of at least one pixel point in the calibration image in the pixel coordinate system by fitting an affine transformation matrix; an affine transformation matrix is ​​calculated by respectively substituting the four pairs of pixel point coordinates into the conversion relationship; a lane detection result acquisition module is configured to obtain the lane line detection result in the vehicle coordinate system through the assisted driving perception system; a lane line equation acquisition module is configured to convert the lane line detection result in the vehicle coordinate system into the lane line equation in the pixel coordinate system through the conversion relationship; a headlight control module is configured to control the matrix LED headlight to project light that matches the lane range forward based on the lane line equation in the pixel coordinate system.

[0017] In a third aspect, an embodiment of the present invention further provides an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the computer program is executed by the processor, the lane lighting control method for a self-closed-loop intelligent vehicle lighting system is implemented.

[0018] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the above-mentioned lane lighting control method for a self-closed-loop intelligent vehicle lighting system.

[0019] The beneficial effects of the present invention are:

[0020] The embodiments of the present application provide a lane lighting control method and system for a self-closed-loop intelligent vehicle lighting system, which has the following advantages over the existing technology: it can achieve high-resolution calibration of matrix LED headlights. Compared with the traditional manual measurement calibration method, this calibration method integrates the ranging algorithm of machine vision, making the calibration process more convenient. In addition, even in an environment with limited site length, calibration can be completed by spatial modeling of the light beam. Specifically, combined with machine vision technology, the calibration algorithm can automatically complete the calibration of the matrix LED headlights without the need for manual measurement, and it can work even in sites with limited area. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention will be further described below with reference to the accompanying drawings and examples.

[0022] Figure 1 This is a flow chart of a lane lighting control method for a self-closed-loop intelligent vehicle lighting system provided in Example 1 of the present invention.

[0023] Figure 2 This is a flow chart of the method involved in step S2 provided in Example 1 of the present invention.

[0024] Figure 3 This is a flow chart of the method involved in step S3 provided in Example 1 of the present invention.

[0025] Figure 4 This is a flow chart of the method involved in step S7 provided in Example 1 of the present invention.

[0026] Figure 5 This is a schematic diagram of vehicle lighting system calibration when there is insufficient space on the site, as provided in Example 1 of the present invention.

[0027] Figure 6 This is another schematic diagram of vehicle lighting system calibration when the site space is insufficient, provided by Example 1 of the present invention.

[0028] Figure 7 This is a flow chart of the method involved in step S11 provided in Example 1 of the present invention.

[0029] Figure 8 This is a structural diagram of a lane lighting control system for a self-closed-loop intelligent vehicle lighting system provided by Example 2 of the present invention.

[0030] Figure 9 This is a partial block diagram of an electronic device provided by Example 3 of the present invention. DETAILED DESCRIPTION

[0031] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the various operations as sequential processes, many of the operations therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0032] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0033] The present invention will now be described in detail with reference to the accompanying drawings. This figure is a simplified schematic diagram, which only illustrates the basic structure of the present invention in a schematic manner, and therefore only shows the components related to the present invention.

[0034] Example 1

[0035] For ease of understanding, the following is an overall description of the inventive concept before describing the embodiments of the present invention in detail:

[0036] The present application provides a lane lighting control method and system for a self-closed-loop intelligent vehicle lighting system, aiming to solve the problem that the existing vehicle lighting system calibration method usually requires vehicle lighting calibration on a sufficient site, and the calibration process is usually based on obstacle calibration without calibrating the lane lighting. As a result, the illumination range of the vehicle lights is not projected based on the actual area of ​​the lane during vehicle driving, affecting the lighting effect and driving experience. The first step is to prepare the relevant calibration tools and complete the construction of the calibration site. The second step is to place targets on the walls of the calibration site to calibrate the camera's extrinsic parameters. The third step is to prepare the required calibration images for the headlights and control the headlights to project the required calibration pattern onto the wall using the driver board. The fourth step is to control the camera to capture the projected pattern, perform calibration calculations, and save the calibration results. The fifth step is to use the vehicle's forward vision perception system to obtain lane line detection results in the vehicle coordinate system. The sixth step is to transform the lane line detection results in the vehicle coordinate system into lane lines in the headlight image coordinate system using the vehicle coordinate system-headlight image coordinate system transformation relationship. The seventh step is to control the matrix LED headlights to project a fixed range of light forward based on the calculation results in the sixth step to achieve lane illumination. This method enables high-resolution calibration of matrix LED headlights. Compared to traditional manual measurement calibration methods, this calibration method integrates machine vision ranging algorithms, making the calibration process more convenient. In addition, even in an environment with limited site length, calibration can be completed through spatial modeling of the light beam. Specifically combined with machine vision technology, the calibration algorithm can automatically complete the calibration of the matrix LED headlights without the need for human participation in measurement, and it can work even in sites with limited area.

[0037] The specific implementation is as follows:

[0038] like Figure 1 FIG. 1 is a flow chart of a lane lighting control method for a self-closed-loop intelligent vehicle lighting system provided by this embodiment.

[0039] As an example, the method includes:

[0040] S1: Build a calibration scenario based on a vehicle equipped with matrix LED lights and an assisted driving perception system.

[0041] S2: Arrange a target image at a preset position in the constructed calibration scene, and collect the target image information through a camera placed in the assisted driving perception system.

[0042] S3: Calculate the extrinsic parameters of the camera using Zhang's calibration method based on the target image information.

[0043] S4: Based on a preset calibration image, the matrix LED headlight is controlled by a driving board to project a projection image corresponding to the calibration image in a predetermined direction.

[0044] S5: Extract four pixels from the calibration image to make their grayscale values ​​equal to preset grayscale values.

[0045] S6: Control the camera to capture the projection image projected in a predetermined direction.

[0046] S7: Obtain coordinates of four pixel points in the calibration image in a pixel coordinate system, and obtain coordinates of pixel points in the projection image corresponding to the four pixel points in the calibration image in a vehicle coordinate system through the extrinsic parameters of the camera.

[0047] S8: Constructing a conversion relationship between the coordinates of at least one pixel point in the projected image in the vehicle coordinate system and the coordinates of at least one pixel point in the calibration image in the pixel coordinate system by fitting an affine transformation matrix.

[0048] S9: The affine transformation matrix is ​​calculated by respectively substituting the four pairs of pixel coordinates obtained in step S7 into the transformation relationship of step S8.

[0049] S10: Obtaining lane line detection results in the vehicle coordinate system through the assisted driving perception system.

[0050] S11: Convert the lane line detection result in the vehicle coordinate system into a lane line equation in the pixel coordinate system through the conversion relationship.

[0051] S12: Based on the lane line equation in the pixel coordinate system, the matrix LED headlight is controlled to project light that matches the lane range forward.

[0052] In some feasible implementations, the calibration scene building process in step S1 is specifically to prepare a vehicle equipped with matrix LED headlights and an Advanced Driver Assistance System (ADAS), drive the vehicle to a level ground and dimly lit environment, place a spatial plane perpendicular to the ground, such as a wall, in front of the vehicle, and place the horizontal direction of the vehicle's front bumper parallel to the wall.

[0053] In some possible implementations, combined Figure 2As shown, step S2 includes: S201: using a checkerboard image as the target image, where each cell in the checkerboard image is of equal size; S202: placing the target image on a spatial plane directly in front of the vehicle; and S203: adjusting the checkerboard position so that each point in the checkerboard image is at an equal longitudinal distance from the optical center of the camera in the assisted driving perception system. Specifically, a checkerboard image is printed and affixed to the wall directly in front of the vehicle, requiring that each cell on the checkerboard is of equal size and that there is no gap between the checkerboard and the wall, to ensure that each point on the checkerboard is at an equal longitudinal distance from the optical center of the camera in the assisted driving perception system.

[0054] In some feasible embodiments, combined with Figure 3 As shown, step S3 includes: S301: recording the length, width, camera height from the ground, and distance from the spatial plane to the camera of each cell on the checkerboard; S302: using Zhang's calibration method to calculate the camera's extrinsic parameters based on the length, width, camera height from the ground, and distance from the spatial plane to the camera of each cell on the checkerboard, as well as the coordinates of the cell corner points in the pixel coordinate system in the checkerboard image contained in the target image information collected by the camera. Specifically, the length, width, camera height from the ground, and distance from the wall to the camera of each cell on the checkerboard are recorded, the corner points of each cell on the checkerboard are extracted using OPenCV, and based on the positions of the cell corner points in the pixel coordinate system in the result of the camera shooting the checkerboard, the camera's extrinsic parameters, including the rotation matrix and the translation vector, are calculated using Zhang's calibration method.

[0055] In some feasible embodiments, steps S4 and S5 further include preparing a calibration image required for the headlights, and controlling the headlights to project the calibration pattern onto the wall via the driver board. Specifically, the pixel resolution of the calibration image is consistent with the resolution of the matrix LED headlights, which is 320*80, to ensure that each lamp bead in the headlights corresponds to each pixel in the image. The calibration image is a single-channel image, and the grayscale value of the pixels in the image corresponds to the brightness of a specific lamp bead in the matrix LED headlights. The grayscale value of at least four pixels in the image is set to 255, and any three of the four pixels are not on the same straight line.

[0056] In some feasible embodiments, when the field space is sufficient, step S4 includes controlling the matrix LED headlights to project a projection image corresponding to the calibration image onto the ground in front of the vehicle; when the field space is insufficient, step S4 includes controlling the matrix LED headlights to project a projection image corresponding to the calibration image onto the spatial plane in front of the vehicle. In other words, when the field length projected by the camera is sufficient, the calibration image can be projected onto the road surface in front of the vehicle for subsequent calibration; when the field length projected by the camera is insufficient, the calibration image can be projected onto the wall in front of the vehicle for subsequent calibration.

[0057] In some feasible implementations, steps S6-S9 are the calibration process between the vehicle coordinate system and the pixel coordinate system. Specifically, if the field is long enough, four points can be illuminated on the ground in front of the vehicle. At this time, the affine transformation matrix T is fitted based on the pattern projected by the matrix LED headlights, as shown in the following formula:

[0058]

[0059] In the formula, P is the coordinate of a pixel point on the pattern projected by the matrix LED headlight in the vehicle coordinate system. Its specific coordinate position is (x, y), which is automatically calculated using the camera's external parameter information and the principle of monocular vision ranging. P' is the coordinate of a pixel point on the matrix LED headlight calibration map in the pixel coordinate system. Its specific coordinate position is (x', y'), corresponding to the four pixels with the grayscale value set to 255 extracted above. By substituting the four pairs of pixels into the above formula (1), the eight equations obtained can be solved to obtain the eight parameters m1-m8 in the affine transformation matrix T. This matrix T can restore any target in the vehicle's front camera's field of view to the pixel position on the above calibration map. Among them, the four pairs of pixels are the four pixels with the grayscale value set to 255 on the calibration image and the corresponding four pixels on the projected image. It should be noted that the above-mentioned vehicle coordinate system refers to the center of the vehicle's rear axle as the origin, the direction of the vehicle's front as the positive direction of the x-axis, and the horizontal left as the positive direction of the y-axis. The pixel coordinate system takes the upper left corner of the calibration image as the origin, the horizontal right as the positive direction of the x-axis, and the horizontal downward as the positive direction of the y-axis.

[0060] In some feasible embodiments, combined with Figure 4-6As shown, when the space in the venue is insufficient, the step S7 further includes: S701: controlling a pixel point in the calibration image to be projected onto the first spatial plane and the second spatial plane in sequence through the matrix LED headlight projection; S702: obtaining the coordinates (x1, y1, z1) of the projected pixel point m1 corresponding to a pixel point in the calibration image on the first spatial plane in the vehicle coordinate system through the extrinsic parameters of the camera; S703: obtaining the coordinates (x2, y2, z2) of the projected pixel point m2 corresponding to a pixel point in the calibration image on the second spatial plane in the vehicle coordinate system through the extrinsic parameters of the camera; S704: constructing a three-dimensional spatial coordinate relationship through the coordinates (x1, y1, z1) of the pixel point m1 in the vehicle coordinate system and the coordinates (x2, y2, z2) of the pixel point m2 in the vehicle coordinate system as follows:

[0061]

[0062] S705: Based on the three-dimensional space coordinate relationship, a theoretical ground projection point m3 of a certain LED lamp bead on the matrix LED headlight is obtained as the coordinate of at least one pixel point in the projected image in the vehicle coordinate system.

[0063] Specifically, combined Figure 5 As shown in Figure 2, the pattern projected by matrix LED headlights can be illuminated on a wall. With the vehicle stationary, a point in the calibration diagram is projected by the headlights, and two points, m1(x1, y1, z1) and m2(x2, y2, z2), can be determined on the front and rear walls, respectively. The origin, x, and y directions of this coordinate system are consistent with the vehicle coordinate system, with the z direction perpendicular to the ground and pointing upward. These two points define a straight line in three-dimensional space, as shown in Formula (2). Letting z = 0 yields the intersection of this line and the ground, which is the theoretical ground projection point m3(x3, y3, 0) of a particular LED bead on the headlight.

[0064] In some feasible implementations, considering the problem of opaque walls, the theoretical assumption of the two walls mentioned above is difficult to achieve. In actual use, the first wall can be changed to a motor-controlled lifting system. When calculating the coordinates of point m1, the first wall is lowered, and when calculating the coordinates of point m2, the first wall is raised. More simply, Figure 6 As shown, only the second wall is retained, and the calculation of points m1 and m2 is achieved by moving the vehicle. Specifically, when the distance from the vehicle to the wall is x2, the coordinates of the projected point are calculated (equivalent to m2). The vehicle then moves forward until the distance from the wall is x1, at which point the coordinates of the projected point are calculated (equivalent to m1). This method effectively ensures accurate calibration between the vehicle coordinate system and the pixel coordinate system even in a limited space.

[0065] In some feasible implementations, step S10 includes: obtaining a lane line detection result in a vehicle coordinate system through the assisted driving perception system, the detection result including position information of the left and right lane lines of the lane in the vehicle coordinate system. Specifically, obtaining a lane line detection result in a vehicle coordinate system through the assisted driving visual perception system. Specifically, outputting the lane line detection result in the vehicle forward visual perception through pipeline communication (SPI communication or Socket communication is also acceptable, taking into account the frame rate, signal length, wiring length, and stability requirements), including the position information of the left and right lane lines of the own vehicle lane in the vehicle coordinate system.

[0066] In some possible implementations, combined Figure 7 As shown, step S11 includes: S1101: sampling four points at equal intervals on the lane line detection result to obtain the coordinates of the four points in the vehicle coordinate system; S1102: converting the four sampled points into coordinates in the pixel coordinate system based on the affine transformation matrix; S1103: fitting the cubic curve equations of the two lane lines in the pixel coordinate system of the headlight calibration image, and the equation of the left lane line is y=C0+C1x+C2x 2 +C3x 3 , the equation of the right lane is y=C4+C5x+C6x 2 +C7x 3 S1104: The area between the left lane line equation and the right lane line equation is the lane range. Specifically, use formula (1) to transform these four points to the pixel coordinate system of the headlight calibration map (that is, to P'), and then fit two cubic curve equations on the pixel coordinate system of the headlight calibration map, including: the left lane line is y = C0 + C1x + C2x 2 +C3x 3 , the right lane line is y=C4+C5x+C6x 2 +C7x 3 The area between these two curves corresponds to the lane area of ​​the vehicle ahead. In the vehicle coordinate system, the interval A on the left lane line takes four points (x1, y1), (x2, y2), (x3, y3), (x4, y4), and multiplies them by the inverse matrix of matrix T. We can get 4 points (x'1, y'1), (x'2, y'2), (x'3, y'3), (x'4, y'4) in the car light image coordinate system, and then substitute these 4 points into the lane line equation to get:

[0067] y'1=C0+C1x'1+C2x'1 2 +C3x'1 3 ;

[0068] y'2=C0+C1x'2+C2x'2 2 +C3x'2 3 ;

[0069] y'3=C0+C1x'3+C2x'3 2 +C3x'3 3 ;

[0070] y'4=C0+C1x'4+C2x'4 2 +C3x'4 3 ;

[0071] Using matrix elimination, we can obtain the coefficients C0, C1, C2, and C3, and thus the equation for the left lane. Similarly, we can obtain the coefficients C4, C5, C6, and C7 in the equation for the right lane, and thus the equation for the right lane.

[0072] In some feasible embodiments, step S12 includes: based on the calculation results of step S11, controlling the matrix LED headlights to project light forward within a fixed range to achieve lane lighting. Specifically, step S11 has already calculated the equations for mapping the left and right lane lines onto the headlight calibration map in the pixel coordinate system. These two cubic curves can be drawn on the projection map. The grayscale values ​​of all pixels in the area between these two curves are then set to 255. This image is then loaded into the headlight driver board, which then controls the headlights to project light, achieving precise lane lighting projection.

[0073] In some feasible implementations, the above embodiments include an assisted driving perception system, matrix LED headlights, and a calibration algorithm. Specifically, the assisted driving perception system is an intelligent perception system based on a forward-looking camera, which is used to monitor and analyze the road conditions in front of the vehicle in real time. The forward-looking camera captures images and video data on the road. The forward-looking visual perception system can use computer vision and deep learning technologies to identify and analyze information such as vehicles, pedestrians, traffic signs, and road markings on the road. The matrix LED headlight refers to a lighting module installed at the front of the vehicle, which is independent of the low beam and high beam. It uses a high-definition matrix LED light source, which can perform precise light beam control and adjustment as needed to provide a clearer, more uniform and efficient lighting effect.

[0074] The above embodiment achieves high-resolution calibration of matrix LED headlights. Compared to traditional manual measurement calibration methods, this calibration method integrates machine vision ranging algorithms, making the calibration process more convenient. Furthermore, even in environments with limited site length, calibration can be completed by spatially modeling the light beam. Incorporating machine vision technology, calibration algorithms can automatically complete the calibration of matrix LED headlights, eliminating the need for manual measurement and enabling operation even in confined areas.

[0075] Example 2

[0076] See also Figure 8 , this embodiment provides a structural diagram of a lane lighting control system for a self-closed-loop intelligent vehicle lighting system.

[0077] As an example, the system is implemented using the lane lighting control method for a self-closed-loop intelligent vehicle lighting system described in Example 1. The system includes:

[0078] The target image information acquisition module 810 is adapted to arrange target images at preset positions in the constructed calibration scene, and to acquire the target image information through a camera placed in the assisted driving perception system.

[0079] The camera extrinsic parameter calculation module 820 is adapted to calculate the camera extrinsic parameters using the Zhang calibration method based on the target image information.

[0080] The projection module 830 is adapted to control the matrix LED headlights to project a projection image corresponding to the calibration image in a predetermined direction through a driving board based on a preset calibration image; and extract four pixel points from the calibration image so that their grayscale values ​​are preset grayscale values.

[0081] The coordinate acquisition module 840 is adapted to control the camera to capture a projection image projected in a predetermined direction; obtain the coordinates of four pixel points in the calibration image in a pixel coordinate system, and obtain the coordinates of the pixel points in the projection image corresponding to the four pixel points in the calibration image in a vehicle coordinate system through the extrinsic parameters of the camera.

[0082] The coordinate transformation module 850 is adapted to construct a transformation relationship between the coordinates of at least one pixel point in the projected image in the vehicle coordinate system and the coordinates of at least one pixel point in the calibration image in the pixel coordinate system by fitting an affine transformation matrix; and the affine transformation matrix is ​​calculated by respectively substituting the four pairs of pixel point coordinates into the transformation relationship.

[0083] The lane detection result acquisition module 860 is adapted to acquire lane line detection results in the vehicle coordinate system through the assisted driving perception system.

[0084] The lane line equation acquisition module 870 is adapted to convert the lane line detection result in the vehicle coordinate system into the lane line equation in the pixel coordinate system through the conversion relationship.

[0085] The headlight control module 880 is adapted to control the matrix LED headlight to project light that matches the lane range forward based on the lane line equation in the pixel coordinate system.

[0086] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the first embodiment.

[0087] It is worth noting that all modules involved in this embodiment are logical units. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovations of this invention, this embodiment does not include units that are not closely related to solving the technical problems proposed by this invention. However, this does not mean that other units do not exist in this embodiment.

[0088] Example 3

[0089] See also Figure 9 An embodiment of the present invention further provides an electronic device, comprising: a memory and a processor; the memory stores at least one program instruction; the processor implements the lane lighting control method for a self-closed-loop intelligent vehicle lighting system provided in Example 1 by loading and executing the at least one program instruction.

[0090] The memory 702 and processor 701 are connected using a bus. The bus can include any number of interconnected buses and bridges, connecting various circuits of one or more processors 701 and memory 702. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and, therefore, are not described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor 701 is transmitted over a wireless medium via an antenna. Furthermore, the antenna receives data and transmits it to the processor 701.

[0091] The processor 701 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. The memory 702 can be used to store data used by the processor 701 when performing operations.

[0092] Example 4

[0093] An embodiment of the present invention further provides a storage medium storing a lane lighting control method for a self-closed-loop intelligent vehicle lighting system. When executed, the lane lighting control program for the self-closed-loop intelligent vehicle lighting system implements the steps of the lane lighting control method for the self-closed-loop intelligent vehicle lighting system described above. Because this storage medium incorporates all the technical solutions of all the aforementioned embodiments, it possesses at least all the beneficial effects of the technical solutions of the aforementioned embodiments, and therefore will not be further elaborated upon here.

[0094] The above is only an embodiment of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the field are aware of all common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the field can improve and implement this scheme in combination with their own abilities under the inspiration given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several variations and improvements can be made, which should also be regarded as the scope of protection of the present invention. These will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A lane lighting control method for a self-closed-loop intelligent vehicle lighting system, characterized in that: The method comprises: S1: Build a calibration scenario based on a vehicle equipped with matrix LED lights and an assisted driving perception system; S2: Arranging a target image at a preset position in the constructed calibration scene, and collecting the target image information by a camera placed in the assisted driving perception system, including: S201: Using a checkerboard image as the target image, where each cell in the checkerboard image has the same size; S202: placing the target image on a spatial plane directly in front of the vehicle; S203: Adjusting the positions of the checkerboard so that the longitudinal distances between each point in the checkerboard image and the optical center of the camera in the assisted driving perception system are equal; S3: Calculate the camera's external parameters based on the target image information using Zhang's calibration method, including: S301: Recording the length and width of each cell on the chessboard, the height of the camera from the ground, and the distance from the space plane to the camera; S302: Calculating the camera's extrinsic parameters using Zhang's calibration method based on the length and width of each cell on the checkerboard, the height of the camera from the ground, the distance from the spatial plane to the camera, and the coordinates of the cell corners in the checkerboard image in a pixel coordinate system contained in the target image information captured by the camera; S4: Based on a preset calibration image, controlling the matrix LED headlight through a driving board to project a projection image corresponding to the calibration image in a predetermined direction, including: When the space in the venue is sufficient, step S4 includes controlling the matrix LED headlights to project a projection image corresponding to the calibration image onto the ground in front of the vehicle; When the space in the venue is insufficient, step S4 includes controlling the matrix LED headlights to project a projection image corresponding to the calibration image onto a spatial plane in front of the vehicle; S5: extracting four pixels from the calibration image so that their grayscale values ​​are preset grayscale values; S6: controlling the camera to capture a projection image projected in a predetermined direction; S7: Obtaining coordinates of four pixel points in the calibration image in a pixel coordinate system, and obtaining coordinates of pixel points in the projection image corresponding to the four pixel points in the calibration image in a vehicle coordinate system through the extrinsic parameters of the camera; S8: constructing a transformation relationship between the coordinates of at least one pixel point in the projection image in the vehicle coordinate system and the coordinates of at least one pixel point in the calibration image in the pixel coordinate system by fitting an affine transformation matrix; S9: Obtain an affine transformation matrix by respectively substituting the four pairs of pixel coordinates obtained in step S7 into the transformation relationship of step S8; S10: Acquire lane line detection results in the vehicle coordinate system through the assisted driving perception system; S11: Converting the lane line detection result in the vehicle coordinate system into a lane line equation in the pixel coordinate system through the conversion relationship; S12: Based on the lane line equation in the pixel coordinate system, the matrix LED headlight is controlled to project light that matches the lane range forward.

2. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 1, characterized in that: The method further includes: when the venue space is insufficient, the step S7 further includes: S701: Control a pixel point in the calibration image to be projected onto a first spatial plane and a second spatial plane in sequence through the matrix LED headlight projection; S702: Obtain the coordinates of the projected pixel point m1 corresponding to a pixel point in the calibration image on the first spatial plane in the vehicle coordinate system using the extrinsic parameters of the camera ( ); S703: Obtain the coordinates of the projected pixel point m2 corresponding to a pixel point in the calibration image on the second spatial plane in the vehicle coordinate system using the extrinsic parameters of the camera ( ); S704: The coordinates of the pixel m1 in the vehicle coordinate system ( ) and the coordinates of pixel m2 in the vehicle coordinate system ( ) Construct the three-dimensional space coordinate relationship as follows: ； S705: Based on the three-dimensional space coordinate relationship, a theoretical ground projection point m3 of a certain LED lamp bead on the matrix LED headlight is obtained as the coordinate of at least one pixel point in the projected image in the vehicle coordinate system.

3. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 1, characterized in that: Any three of the four pixel points extracted in step S5 are not on the same straight line.

4. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 1, characterized in that: The conversion relationship in step S8 is: ； Where P is the coordinate of the pixel point on the projected image projected by the matrix LED headlight in the vehicle coordinate system, is the coordinate of the pixel point on the matrix LED headlight calibration image in the pixel coordinate system, T is the affine transformation matrix, are the 8 parameters in the affine transformation matrix T, the coordinate point (x, y) represents the coordinate of the pixel point in the projected image in the vehicle coordinate system, the coordinate point ( ) represents the coordinates of the pixel points in the calibration image in the pixel coordinate system.

5. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 1, characterized in that: The step S10 includes: obtaining a lane line detection result in a vehicle coordinate system through the assisted driving perception system, wherein the detection result includes position information of the left and right lane lines of the lane in the vehicle coordinate system.

6. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 1, characterized in that: The step S11 includes: S1101: Sampling four points at equal intervals on the lane line detection result to obtain coordinates of the four points in the vehicle coordinate system; S1102: transforming the four sampled points into coordinates in a pixel coordinate system based on the affine transformation matrix; S1103: Fit the cubic curve equations of the two lane lines in the pixel coordinate system of the headlight calibration image. The equation of the left lane line is , the equation of the right lane is ; S1104: The area between the left lane line equation and the right lane line equation is the lane range; Where, is the cubic curve equation coefficient of the left lane line, is the cubic curve equation coefficient of the right lane line, is the coordinate value in the pixel coordinate system.

7. A lane lighting control system for a self-closed loop intelligent vehicle lighting system, characterized in that: The system is implemented using the lane lighting control method for a self-closed-loop intelligent vehicle lighting system according to any one of claims 1 to 6, and the system includes: A target image information acquisition module is adapted to arrange target images at preset positions in the constructed calibration scene, and to acquire the target image information through a camera placed in the assisted driving perception system; A camera extrinsic parameter calculation module is adapted to calculate the camera extrinsic parameters using Zhang's calibration method based on the target image information; A projection module is adapted to control the matrix LED headlights to project a projection image corresponding to the calibration image in a predetermined direction through a driver board based on a preset calibration image; and extract four pixels from the calibration image so that their grayscale values ​​are preset grayscale values; a coordinate acquisition module adapted to control the camera to capture a projection image projected in a predetermined direction; acquire coordinates of four pixels in the calibration image in a pixel coordinate system, and acquire coordinates of pixels in the projection image corresponding to the four pixels in the calibration image in a vehicle coordinate system using extrinsic parameters of the camera; a coordinate transformation module adapted to construct a transformation relationship between the coordinates of at least one pixel point in the projected image in the vehicle coordinate system and the coordinates of at least one pixel point in the calibration image in the pixel coordinate system by fitting an affine transformation matrix; and to calculate the affine transformation matrix by respectively substituting the four pairs of pixel point coordinates into the transformation relationship; A lane detection result acquisition module is adapted to acquire lane line detection results in a vehicle coordinate system through the assisted driving perception system; A lane line equation acquisition module is adapted to convert the lane line detection result in the vehicle coordinate system into a lane line equation in the pixel coordinate system through the conversion relationship; The headlight control module is adapted to control the matrix LED headlight to project light that matches the lane range forward based on the lane line equation in the pixel coordinate system.

Images