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

Abstract

The invention provides a lane illumination control method and system for a self-closed-loop intelligent vehicle lamp system, and belongs to the technical field of vehicle lamp intelligent control. The method comprises the following steps: preparing a related calibration tool, and completing the construction of a calibration site; arranging targets on the wall surface of the calibration site, and completing calibration of external parameters of the camera; preparing a calibration picture required by the vehicle lamp, and controlling the vehicle lamp to project a pattern required by calibration to the wall surface through the driving plate; controlling the camera to shoot a pattern projected by the vehicle lamp, performing calibration calculation and storing a calibration result; acquiring a lane line detection result under a vehicle coordinate system through a vehicle foresight visual perception system; converting a lane line detection result under the vehicle coordinate system into a lane line under the vehicle lamp image coordinate system through a conversion relation between the vehicle coordinate system and the vehicle lamp image coordinate system; and controlling the matrix type LED headlamps to project light in a fixed range forwards based on the lane lines under the vehicle lamp image coordinate system, so as to realize lane illumination. And the calibration of the high-resolution matrix type LED headlamp is realized.

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 important part of vehicle safety, vehicle headlights can 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, but also have expectations for 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 light 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 the system, in order to obtain good lighting effects and driving experience, the control of the light beam 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 calibration method of the headlight system usually requires the headlight calibration to be carried out on a sufficient site, and the calibration process is usually based on the calibration of obstacles, and the lane lighting is not calibrated. This means that 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 comprises: 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 through a camera placed in the assisted driving perception system; S3: calculating the external parameters of the camera based on the target image information by using Zhang's calibration method; 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 coordinates of the point in the pixel coordinate system, and the coordinates of the pixel points in the projection image corresponding to the four pixel points in the calibration image in the vehicle coordinate system are obtained through the external parameters of the camera; S8: the conversion 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 is constructed by fitting the affine transformation matrix; S9: the affine transformation matrix is ​​calculated by respectively bringing the four pairs of pixel point coordinates obtained in the step S7 into the conversion relationship of step S8; S10: the lane line detection result in the vehicle coordinate system is obtained through the assisted driving perception system; S11: the lane line detection result in the vehicle coordinate system is converted into the 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.

[0006] Furthermore, the step S2 includes: S201: using a checkerboard image as the target image, wherein 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; S203: adjusting the position of the checkerboard 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.

[0007] Further, the step S3 includes: S301: recording the length, width, height of the camera from the ground and the distance from the spatial plane to the camera of each cell on the chessboard; S302: using Zhang's calibration method to calculate the external parameters of the camera based on the length, width, height of the camera from the ground and the 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 venue space is insufficient, the step S7 also includes: S701: controlling a pixel point in the calibration image to be projected to the first spatial plane and the second spatial plane in sequence through the matrix LED light 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 projection image in the vehicle coordinate system.

[0010] Furthermore, any three pixel points among 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 projection image projected by 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 a left lane line and a right lane line of a lane in the vehicle coordinate system.

[0015] Further, 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 sampled four points to the 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 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 a second aspect, the present invention provides a lane lighting control system for a self-closed-loop intelligent vehicle lighting system, wherein the system is implemented using the above-mentioned lane lighting control method for a self-closed-loop intelligent vehicle lighting system, and the system includes: a module for collecting target image information, which is suitable for arranging a target image at a preset position in a constructed calibration scene, and collecting the target image information by a camera placed in the assisted driving perception system; a module for calculating camera external parameters, which is suitable for calculating the external parameters of the camera based on the target image information using Zhang's calibration method; a projection module, which is suitable for controlling the matrix LED vehicle light to project a projection image corresponding to the calibration image in a predetermined direction through a driving board based on a preset calibration image; 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 capture a projection image projected in a predetermined direction; and obtaining the pixel coordinates of four pixel points in the calibration image. The coordinates of the projection image in the vehicle coordinate system are obtained by the external parameters of the camera, and the coordinates of the pixels in the projection image corresponding to the four pixels in the calibration image in the vehicle coordinate system are obtained by means of the external parameters of the camera; a coordinate conversion module is used to construct a conversion relationship between the coordinates of at least one pixel in the projection image in the vehicle coordinate system and the coordinates of at least one pixel in the calibration image in the pixel coordinate system by fitting an affine transformation matrix; an affine transformation matrix is ​​calculated by bringing the four pairs of pixel coordinates into the conversion relationship respectively; a lane detection result acquisition module is used to acquire the lane line detection result in the vehicle coordinate system through the auxiliary driving perception system; a lane line equation acquisition module is used 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 used 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 in 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 embodiment of the present application provides a lane lighting control method and system for a self-closed-loop intelligent vehicle lighting system, which has the following advantages over the prior art: high-resolution calibration of matrix LED headlights can be achieved. Compared with the traditional manual measurement calibration method, this calibration method integrates the ranging algorithm of machine vision, and the calibration process is more convenient. In addition, even in an environment where the length of the site is limited, the calibration can be completed by spatial modeling of the light beam. Specifically, combined with machine vision technology, the calibration algorithm can be used to automatically complete the calibration of the matrix LED headlights, without the need for manual measurement, and can work even in a site with a limited area. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[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 It is a flow chart of the method involved in step S2 provided in Example 1 of the present invention.

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

[0025] Figure 4 It 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 the site space is insufficient, 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 in Example 1 of the present invention.

[0028] Figure 7 It is a flow chart of the method involved in step S11 provided in embodiment 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 in Example 2 of the present invention.

[0030] Fig. 9 This is a partial block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0031] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations as sequential processes, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the 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", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" 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 inventive concept is generally described below 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 lane lighting. As a result, the illumination range of the vehicle lighting 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 relevant calibration tools and complete the construction of the calibration site; the second step is to arrange targets on the wall of the calibration site to complete the calibration of the camera's external parameters; the third step is to prepare the calibration images required for the headlights, and control the headlights to project the calibration patterns onto the wall through the driver board; the fourth step is to control the camera to shoot the patterns projected by the headlights, perform calibration calculations and save the calibration results; the fifth step is to obtain the lane line detection results in the vehicle coordinate system through the vehicle's forward vision perception system; the sixth step is to convert the lane line detection results in the vehicle coordinate system into lane lines in the headlight image coordinate system through the transformation relationship between the vehicle coordinate system and the headlight image coordinate system; the seventh step is to control the matrix LED headlights to project a fixed range of light forward based on the calculation results of the sixth step to achieve lane lighting. High-resolution calibration of matrix LED headlights can be achieved. Compared with the traditional manual measurement calibration method, this calibration method integrates the machine vision ranging algorithm, and the calibration process is more convenient. In addition, even in an environment where the length of the site is limited, calibration can be completed through spatial modeling of the light beam. Specifically combined with machine vision technology, the calibration of the matrix LED headlights can be automatically completed through the calibration algorithm, without the need for human participation in the measurement, and it can work even in sites with limited area.

[0037] The specific implementation is as follows:

[0038] like Figure 1 As shown, it 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 external 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: extracting four pixels from the calibration image so that their grayscale values ​​are preset grayscale values.

[0045] S6: Control the camera to capture a 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 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.

[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 in step S8.

[0049] S10: Acquire 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, directly in front of the vehicle, and place the horizontal direction of the vehicle's front bumper parallel to the wall.

[0053] In some feasible embodiments, combined with Figure 2As shown, step S2 includes: S201: using a checkerboard image as the target image, and each cell in the checkerboard image is of equal size; S202: placing the target image on the spatial plane directly in front of the vehicle; S203: adjusting the position of the checkerboard 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 prepared, and the checkerboard image is pasted on 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, so as 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, height of the camera from the ground, and the distance from the spatial plane to the camera of each cell on the chessboard; S302: using Zhang's calibration method to calculate the external parameters of the camera based on the length, width, height of the camera from the ground, and the distance from the spatial plane to the camera of each cell on the chessboard, as well as the coordinates of the corner points of the cells in the chessboard picture in the pixel coordinate system contained in the target image information collected by the camera. Specifically, the length, width, height of the camera from the ground, and the distance from the wall to the camera of each cell on the chessboard are recorded, and the corner points of each cell on the chessboard are extracted through OPenCV. Based on the position of the corner points of the cells in the pixel coordinate system in the result of the camera shooting the chessboard, the external parameters of the camera, including the rotation matrix and the translation vector, are calculated using Zhang Zhengyou's calibration method.

[0055] In some feasible implementations, steps S4 and S5 further include: preparing a calibration image required for the headlight, and controlling the headlight to project the calibration pattern onto the wall through the driver board. Specifically, the pixel resolution of the calibration image is consistent with the resolution of the matrix LED headlight, which is 320*80, so as to ensure that each lamp bead in the headlight can correspond to each pixel in the image. The calibration image is a single-channel image, and the grayscale value of the pixel in the image corresponds to the brightness of a certain lamp bead on the matrix LED headlight. The grayscale value of at least 4 pixels on the image is set to 255, and any 3 of the 4 pixels are not on the same straight line.

[0056] In some feasible implementations, when the site space is sufficient, step S4 includes controlling the matrix LED headlight 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 headlight to project a projection image corresponding to the calibration image onto the spatial plane in front of the vehicle. That is, when the length of the site 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 length of the site 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 in combination with the pattern projected by the matrix LED headlights, as shown in the following formula:

[0058]

[0059] Where P is the coordinate of a certain pixel point on the pattern projected by the matrix LED headlight in the vehicle coordinate system, and its specific coordinate position is (x, y), which is automatically calculated through the camera's external parameter information and the principle of monocular vision ranging. P' is the coordinate of a certain pixel point on the matrix LED headlight calibration map in the pixel coordinate system, and its specific coordinate position is (x', y'), corresponding to the 4 pixels with the grayscale value set to 255 extracted above. By substituting 4 pairs of pixels into the above formula (1), 8 equations are obtained to solve the 8 parameters m1-m8 in the affine transformation matrix T, which 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 4 pairs of pixels are 4 pixels with grayscale values ​​set to 255 on the calibration image and the corresponding 4 pixels on the projection 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 front of the vehicle is facing the positive direction of the x-axis, and the horizontal left is 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 is the positive direction of the x-axis, and the horizontal downward is the positive direction of the y-axis.

[0060] In some feasible embodiments, combined with Figure 4-6As shown, when the venue space is insufficient, the step S7 also includes: S701: controlling a pixel point in the calibration image to be projected to the first spatial plane and the second spatial plane in sequence through the matrix LED light 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 space 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 projection image in the vehicle coordinate system.

[0063] Specifically, combined Figure 5 As shown in the figure, the pattern projected by the matrix LED headlight can be irradiated onto the wall. When the vehicle is stationary, a certain point in the calibration diagram is projected by the headlight, 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 aforementioned vehicle coordinate system, and the z direction is perpendicular to the ground and upward is the positive direction. These two points determine a straight line in three-dimensional space as shown in formula (2). Let z = 0, and the intersection of the straight line and the ground is obtained, which is the theoretical ground projection point m3(x3, y3, 0) of a certain LED lamp 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 and lowering wall. 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 realized by moving the vehicle. Specifically, when the distance between the vehicle and the wall is x2, the coordinates of the projection point are calculated (equivalent to m2), and then the vehicle moves forward until the distance from the wall is x1, and the coordinates of the projection point are calculated (equivalent to m1). In this way, accurate calibration between the vehicle coordinate system and the pixel coordinate system can be effectively achieved in a limited space.

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

[0066] In some feasible embodiments, combined with Figure 7 As shown, 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 sampled four points to the 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, transform 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 where the vehicle in front is located. Define the vehicle coordinate system, take four points (x1, y1), (x2, y2), (x3, y3), (x4, y4) on the left lane line, and multiply them by the inverse matrix of matrix T on the left. 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 the matrix elimination method, we can get the coefficients C0, C1, C2, and C3, and thus get the equation for the left lane line. Similarly, we can get the coefficients C4, C5, C6, and C7 in the equation for the right lane line, and thus get the equation for the right lane line.

[0072] In some feasible implementations, the step S12 includes: based on the calculation result of step S11, controlling the matrix LED headlight to project a fixed range of light forward to achieve lane lighting. Specifically, in step S11, the equations for mapping the left and right lane lines to the headlight calibration map in the pixel coordinate system have been calculated, and the two cubic curves can be drawn in the projection map, and then the grayscale values ​​of all pixels in the area between the two curves are set to 255, and the image is read into the driver board of the headlight, and the headlight is controlled by the driver board to project it to achieve the precise projection effect of lane lighting.

[0073] In some feasible implementations, the above embodiments include an assisted driving perception system, a matrix LED headlight, 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 vehicles, pedestrians, traffic signs, road markings and other information on the road. The matrix LED headlight refers to a lamp 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 realizes the calibration of matrix LED headlights with high resolution. Compared with the traditional manual measurement calibration method, this calibration method integrates the ranging algorithm of machine vision, and the calibration process is more convenient. In addition, even in an environment where the length of the site is limited, the calibration can be completed by spatial modeling of the light beam. Combined with machine vision technology, the calibration of matrix LED headlights can be automatically completed through the calibration algorithm, without the need for manual measurement, and can work even in a site with limited area.

[0075] Example 2

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

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

[0078] The target image information acquisition module 810 is adapted to arrange a target image at a preset position in a 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 by using Zhang's 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 in the calibration image so that their grayscale values ​​are preset grayscale values.

[0081] The coordinate acquisition module 840 is suitable for controlling the camera to capture a projection image projected in a predetermined direction; obtaining the coordinates of four pixel points in the calibration image in a pixel coordinate system, and obtaining 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 external parameters of the camera.

[0082] The coordinate transformation module 850 is suitable for constructing the 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 the 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 the lane line detection result 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 in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.

[0087] It is worth mentioning that all modules involved in this embodiment are logical units. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

[0088] Example 3

[0089] See also Fig. 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 lamp system provided in Example 1 by loading and executing the at least one program instruction.

[0090] The memory 702 and the processor 701 are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 701 and the memory 702 together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor 701 is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data 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] The embodiment of the present invention further provides a storage medium, on which a lane lighting control method for a self-closed loop intelligent vehicle lamp system is stored, and when the lane lighting control program for the self-closed loop intelligent vehicle lamp system is executed, the steps of the lane lighting control method for the self-closed loop intelligent vehicle lamp system as described above are implemented. Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be repeated here one by one.

[0094] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can know all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant 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 deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, which 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: Calibration scenario based on a vehicle equipped with matrix LED lights and assisted driving perception system; S2: arranging a target image at a preset position in the constructed calibration scene, and collecting the target image information through a camera placed in the assisted driving perception system; S3: Calculate the external parameters of the camera using Zhang's calibration method based on the target image information; 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; S5: extracting four pixels from the calibration image so that their grayscale values ​​are preset grayscale values; S6: Control 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 a lane line detection result in a vehicle coordinate system through the auxiliary 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 step S2 comprises: S201: using a checkerboard image as the target image, wherein each cell in the checkerboard image has an equal size; S202: placing the target image on a spatial plane directly in front of the vehicle; S203: Adjust the position of the chessboard so that each point in the chessboard image has an equal longitudinal distance from the optical center of a camera in the assisted driving perception system.

3. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 2, characterized in that: The step S3 comprises: 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: Calculate the external parameters of the camera using Zhang's calibration method based on the length and width of each cell on the chessboard, the height of the camera from the ground and the distance from the spatial plane to the camera, 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.

4. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 1, characterized in that: The method further comprises: When the venue space is sufficient, step S4 includes controlling the matrix LED headlight to project a projection image corresponding to the calibration image onto the ground in front of the vehicle; When the venue space 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.

5. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 4, 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 a matrix LED lamp projection; S702: Obtaining the coordinates (x1, y1, z1) of a projected pixel point m1 on a first spatial plane corresponding to a pixel point in a calibration image in a 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: Construct a three-dimensional space coordinate relationship using 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: 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 projection image 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: Any three of the four pixel points extracted in step S5 are not on the same straight line.

7. 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 projection image projected by 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.

8. 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 a left lane line and a right lane line of a lane in the vehicle coordinate system.

9. The lane lighting calibration method for a self-closed-loop intelligent vehicle lighting system according to claim 1, characterized in that: The step S11 comprises: S1101: sampling four points at equal intervals on the lane line detection result to obtain coordinates of the four points in a vehicle coordinate system; S1102: transforming the four sampled points into coordinates in a 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. 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.

10. A lane lighting control system for a self-closed loop intelligent vehicle lighting system, characterized in that: The system is implemented by the lane lighting control method for a self-closed-loop intelligent vehicle lighting system according to any one of claims 1 to 9, and the system comprises: A target image information acquisition module is adapted to arrange a target image at a preset position in a 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, adapted to control the matrix LED headlight to project a projection image corresponding to the calibration image in a predetermined direction through a driving board based on a preset calibration image; extract four pixel points in 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 the coordinates of four pixel points in the calibration image in a pixel coordinate system, and acquire the 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; A coordinate transformation module is adapted to construct 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; and the affine transformation matrix is ​​calculated by respectively bringing the four pairs of pixel point coordinates into the transformation relationship; A lane detection result acquisition module is used 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