Double-lamp fusion calibration system and method for intelligent self-closed-loop vehicle lamp

Abstract

The invention discloses a double-lamp fusion calibration system and method for an intelligent self-closed-loop automobile lamp, and belongs to the technical field of automobile illumination. The double-lamp fusion calibration system of the intelligent self-closed-loop vehicle lamp comprises a left high-definition projection headlamp, a right high-definition projection headlamp, a calibration board, a high-resolution camera, an image processing module, a control module and a feedback adjustment module. Marking points are arranged on the calibration plate; the high-resolution camera is used for shooting mark point images on the calibration board irradiated by the left and right high-definition projection headlamps; the image processing module is used for drawing projection image boundaries of the left and right high-definition projection headlamps; the control module is used for calculating a deviation value between the projected images; and the feedback adjustment module is used for monitoring the alignment calibration effect of the projected image in real time and controlling the left and right high-definition projection headlamps to perform illumination parameter adjustment. According to the double-lamp fusion calibration system and method for the intelligent self-closed-loop vehicle lamp, high-precision alignment of projection images of a left high-definition projection headlamp and a right high-definition projection headlamp is achieved, and the illumination effect and the driving safety are improved.

Description

Technical Field

[0001] The present invention relates to a dual - lamp fusion calibration system and method for intelligent self - closed - loop vehicle lamps, belonging to the technical field of automotive lighting. Background Art

[0002] Currently, with the rapid development of automotive lighting technology, high - definition projection headlamps play an increasingly important role in the field of automotive lighting due to their excellent lighting effects and intelligent adjustment capabilities.

[0003] In the existing technology, due to various errors in the vehicle manufacturing and assembly processes, the projection images of the left and right high - definition projection headlamps often show misalignment problems, which not only affect the lighting effect but also pose a potential threat to driving safety. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a dual - lamp fusion calibration system and method for intelligent self - closed - loop vehicle lamps, which realizes high - precision alignment of the projection images of the left and right high - definition projection headlamps, improves the lighting effect and driving safety, and saves the hardware cost of dual - lamp projection image calibration.

[0005] To solve the above - mentioned technical problem, the technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a dual - lamp fusion calibration system for intelligent self - closed - loop vehicle lamps, which includes a left high - definition projection headlamp, a right high - definition projection headlamp, a calibration board, a high - resolution camera, an image - processing module, a control module, and a feedback adjustment module;

[0007] Marker points are set on the calibration board;

[0008] The high - resolution camera is used to capture the images of the marker points on the calibration board after being irradiated by the left and right high - definition projection headlamps, and to monitor the light intensity projected onto the calibration board in real time;

[0009] The image - processing module is used to process the marker point images to obtain the boundaries of the projection images of the left and right high - definition projection headlamps;

[0010] The control module is used to calculate the deviation value between the projection images of the left and right high - definition projection headlamps according to the boundaries of the projection images of the left and right high - definition projection headlamps;

[0011] The feedback adjustment module is used to monitor the alignment calibration effect of the projection images of the left and right high - definition projection headlamps in real time, and to control the left and right high - definition projection headlamps to optimize and adjust the lighting parameters according to the alignment calibration effect until the predetermined alignment standard is reached.

[0012] On the other hand, the present invention also provides a calibration method for a dual-lamp fusion calibration system of an intelligent self-closed-loop vehicle lamp, which includes the following steps:

[0013] Step S1: Set up a calibration board in front of the vehicle. Multiple marking points are set on the calibration board. Start the left high-definition projection headlamp and the right high-definition projection headlamp and irradiate the calibration board simultaneously.

[0014] Step S2: Use a high-resolution camera to capture the image of the marking points on the calibration board after being irradiated by the left high-definition projection headlamp and the right high-definition projection headlamp from a preset shooting position and angle. At the same time, monitor the light intensity projected onto the calibration board in real time, perform dynamic light intensity adjustment according to the light intensity on the calibration board, and perform real-time image quality monitoring on the image of the marking points captured by the high-resolution camera.

[0015] Step S3: Identify and process the image of the marking points captured by the high-resolution camera through an image processing module, and draw the boundaries of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp.

[0016] Step S4: Calculate the deviation value between the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp according to the boundaries of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp.

[0017] Step S5: Adjust the lighting parameters of the left high-definition projection headlamp and the right high-definition projection headlamp according to the deviation value between the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp.

[0018] Step S6: Start the left high-definition projection headlamp and the right high-definition projection headlamp again, verify the alignment calibration effect of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp, monitor the alignment calibration effect in real time through a feedback adjustment module, and control the left high-definition projection headlamp and the right high-definition projection headlamp to perform continuous iteration of lighting parameters until the predetermined alignment standard is reached.

[0019] Further, in step S2, the light intensity projected onto the calibration board is monitored in real time, and dynamic light intensity adjustment is performed according to the light intensity on the calibration board. Specifically, it includes the following steps:

[0020] The light intensity projected onto the calibration board is monitored in real time through a sensor built in the high-resolution camera. The left high-definition projection headlamp and the right high-definition projection headlamp adjust the brightness of the LED pixels according to the light intensity on the calibration board sent by the high-resolution camera.

[0021] Further, in step S2, real-time image quality monitoring is performed on the image of the marking points captured by the high-resolution camera. Specifically, it includes the following steps:

[0022] The image processing module receives the image of the marker points on the calibration board captured by the high-resolution camera, and performs real-time analysis on each frame of the marker point image to detect whether the image is clear and whether the marker points are completely visible. If the image quality does not meet the standard, an alarm will be issued immediately, and the shooting parameters of the high-resolution camera will be adjusted for reshooting.

[0023] Further, in the step S2, the calculation method of the preset shooting position includes the following steps:

[0024] According to the position, size and marker point distribution data of the calibration board, as well as the parameters of the vehicle lights of each model, the optimal shooting position, that is, the preset shooting position, is automatically calculated.

[0025] Further, in the step S3, the image processing module identifies and processes the marker point image captured by the high-resolution camera, and draws the boundaries of the projection images of the left high-definition projection headlight and the right high-definition projection headlight. Specifically, it includes the following steps:

[0026] First, the position information of each marker point in the marker point image is extracted through image recognition and image processing techniques, and then the boundaries of the projection images of the left high-definition projection headlight and the right high-definition projection headlight are drawn respectively according to the position information of the marker points.

[0027] Further, the image processing technology includes an adaptive threshold segmentation technology, which specifically includes the following steps:

[0028] For each pixel in the marker point image, according to the brightness distribution of the local neighborhood where the pixel is located, the brightness threshold of each pixel is calculated, and the pixels are classified as foreground or background according to the brightness threshold. The pixels classified as foreground correspond to the marker points in the marker point image.

[0029] Further, the adaptive threshold segmentation technology adopts the local mean method, and the calculation formula of the local mean method is as follows:

[0030]

[0031] Where, T(x,y) is the brightness threshold at the pixel (x,y);

[0032] S is the local neighborhood centered on the pixel (x,y);

[0033] N is the number of pixels in the S neighborhood;

[0034] (i,j) is the pixel coordinates in the S neighborhood;

[0035] I(i,j) is the brightness value of the pixel (i,j) in the S neighborhood;

[0036] C is a constant.

[0037] Further, in the step S4, the deviation values between the projection images of the left high-definition projection headlight and the right high-definition projection headlight include a horizontal deviation value, a vertical deviation value, and a rotation deviation value. The calculation formula for the horizontal deviation value is as follows:

[0038]

[0039] The calculation formula for the vertical deviation value is as follows:

[0040]

[0041] The calculation formula for the rotation deviation value is as follows:

[0042]

[0043] Where x Li and y Li are respectively the abscissa and ordinate of the i-th marked point in the projection image of the left high-definition projection headlight;

[0044] x Ri and y Ri are respectively the abscissa and ordinate of the i-th marked point in the projection image of the right high-definition projection headlight;

[0045] n is the total number of marked points;

[0046] Δx is the horizontal deviation value;

[0047] Δy is the vertical deviation value;

[0048] θ is the rotation deviation value.

[0049] Further, in the step S5, the adjustment of the lighting parameters of the left high-definition projection headlight and the right high-definition projection headlight includes the adjustment of the brightness, position, and irradiation angle of the LED pixels. The calculation formula for the brightness adjustment of the LED pixels is as follows:

[0050] L adjusted =L initia l×k brightness ;

[0051] The calculation formula for the position adjustment of the LED pixels is as follows:

[0052] (x adjusted ,y adjusted )=(x initial ,y initial )+(Δx compensation ,Δy compensation );

[0053] The calculation formula for the irradiation angle adjustment of the LED pixels is as follows:

[0054] θ adjusted = θ initial + Δθ compensation ;

[0055] where L adjusted is the brightness of the adjusted LED pixel;

[0056] (x adjusted , y adjusted ) is the position of the adjusted LED pixel;

[0057] θ adjusted is the irradiation angle of the adjusted LED pixel;

[0058] L initial is the initial brightness of the LED pixel;

[0059] (x initial , y initial ) is the initial position of the LED pixel;

[0060] θ initial is the initial irradiation angle of the LED pixel;

[0061] k brightness is the brightness adjustment coefficient;

[0062] (Δx compensation , Δy compensation ) is the LED pixel position compensation amount calculated according to the deviation value;

[0063] Δθ compensation is the LED pixel irradiation angle compensation amount calculated according to the deviation value.

[0064] Adopting the above technical solution, the present invention has the following beneficial effects:

[0065] The present invention realizes an end-to-end full-process self-closed-loop dual-lamp fusion calibration from visual perception to image processing and then to headlamp control. By setting up a calibration board to provide position reference points for the projection images of the left and right high-definition projection headlamps, it is beneficial to perform accurate calibration of the projection images. The high-resolution camera collects the marked point images on the calibration board after being irradiated by the left and right high-definition projection headlamps from the preset optimal shooting position, which can ensure that the marked point images are clearly visible. At the same time, dynamic light intensity adjustment and real-time image quality monitoring are carried out, solving the problem of unstable image quality of traditional calibration methods in different lighting environments, ensuring that the quality of the marked point images collected by the high-resolution camera always meets the calibration requirements, and guaranteeing the accuracy of subsequent image processing. In the image processing process, an adaptive threshold segmentation technology is introduced to solve problems such as uneven illumination and complex background encountered in the calibration process, improving the accuracy and robustness of image segmentation. The control module calculates the deviation value between the projection images of the left and right high-definition projection headlamps, which can accurately quantify the inconsistency between the projection images of the left and right high-definition projection headlamps, ensuring the accuracy of subsequent lighting parameter adjustment. Precise algorithms are used to adjust the lighting parameters, achieving high-precision alignment of the projection images of the left and right high-definition projection headlamps in terms of position, direction, and angle, improving the lighting effect and driving safety, and saving the hardware cost of dual-lamp projection image calibration. The feedback adjustment module is set up to realize the closed-loop optimization of the calibration system, which can continuously iterate the lighting parameters, improving the practicability and applicability of the calibration system. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is the principle block diagram of the dual-lamp fusion calibration system of the intelligent self-closed-loop headlamp of the present invention;

[0067] Figure 2 is the flow chart of the calibration method of the dual-lamp fusion calibration system of the intelligent self-closed-loop headlamp of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] In order to make the content of the present invention easier to be clearly understood, the present invention will be further described in detail below according to specific embodiments in combination with the drawings.

[0069] Embodiment 1

[0070] As Figure 1 shown, this embodiment provides a dual-lamp fusion calibration system for an intelligent self-closed-loop headlamp, which includes a left high-definition projection headlamp, a right high-definition projection headlamp, a calibration board, a high-resolution camera, an image processing module, a control module, and a feedback adjustment module;

[0071] The left high-definition projection headlamp and the right high-definition projection headlamp are lighting devices with intelligent adjustment capabilities, and different lighting effects can be adjusted by controlling the brightness of Mini LED pixels in different areas inside;

[0072] The calibration board is a flat board made of materials with high stability and low deformation, such as high-quality aluminum alloy or hard plastic, to ensure that it remains flat and undeformed during long-term use. The surface of the calibration board is specially treated, having good reflectivity and wear resistance, facilitating high-resolution cameras to capture clear images. Multiple marking points are set on the calibration board to provide accurate position reference points for the projection images of the left and right high-definition projection headlights. These marking points are distributed in a regular grid form, and the row and column spacings of the grid are precisely calculated to ensure that the positions and spacings of each marking point are known, so as to accurately calibrate the projection images of the left and right high-definition projection headlights. The marking points usually adopt high-contrast circular or square patterns so that image recognition algorithms can quickly and accurately identify their positions;

[0073] The high-resolution camera is used to capture the images of the marking points on the calibration board after being irradiated by the left high-definition projection headlight and the right high-definition projection headlight, and to monitor the light intensity projected onto the calibration board in real time to ensure that the captured images of the marking points are clearly visible;

[0074] The image processing module is used to process the images of the marking points to obtain the boundaries of the projection images of the left high-definition projection headlight and the right high-definition projection headlight;

[0075] The control module is used to calculate the deviation value between the projection images of the left high-definition projection headlight and the right high-definition projection headlight according to the boundaries of the projection images of the left high-definition projection headlight and the right high-definition projection headlight;

[0076] The feedback adjustment module is used to monitor the alignment calibration effect of the projection images of the left high-definition projection headlight and the right high-definition projection headlight in real time, and to control the left high-definition projection headlight and the right high-definition projection headlight to optimize the adjustment of the lighting parameters according to the alignment calibration effect until the predetermined alignment standard is reached, ensuring the high-precision alignment of the projection images of the left and right high-definition projection headlights.

[0077] Embodiment 2

[0078] As Figure 2 shown, this embodiment provides a calibration method for a dual-lamp fusion calibration system of an intelligent self-closed-loop vehicle lamp as in Embodiment 1, which includes the following steps:

[0079] Step S1: Set a calibration board in front of the vehicle. Multiple marking points are set on the calibration board. Start the left high-definition projection headlight and the right high-definition projection headlight and irradiate the calibration board simultaneously, making the calibration board perpendicular to the irradiation directions of the left and right high-definition projection headlights to ensure that the projection images of the left and right high-definition projection headlights can completely cover the marking points on the calibration board;

[0080] Specifically, use a bracket or fixture to fix the calibration board in an appropriate position to ensure its stability.

[0081] Step S2: Use a high-resolution camera to capture the images of the marked points on the calibration board after being illuminated by the left high-definition projection headlamp and the right high-definition projection headlamp from the preset shooting position and angle, ensuring that the captured images of the marked points are clearly visible. The calculation method of the preset shooting position includes the following steps: Automatically calculate the optimal shooting position, that is, the preset shooting position, according to the position, size, and marked point distribution data of the calibration board, as well as the parameters of the vehicle headlamps of each model. The user only needs to operate according to the feedback information of the system to easily complete the high-quality image acquisition work, improving the efficiency and accuracy of image acquisition;

[0082] Meanwhile, real-time monitor the light intensity projected onto the calibration board and perform dynamic light intensity adjustment according to the light intensity on the calibration board, which specifically includes the following steps: Real-time monitor the light intensity projected onto the calibration board through the sensor built in the high-resolution camera. The left high-definition projection headlamp and the right high-definition projection headlamp automatically adjust the brightness of the LED pixels according to the light intensity on the calibration board sent by the high-resolution camera, ensuring that the images of the marked points on the calibration board are clear and not overexposed under different ambient light conditions, effectively solving the problem of unstable image quality under different lighting environments in traditional calibration methods;

[0083] Meanwhile, perform real-time image quality monitoring on the images of the marked points captured by the high-resolution camera, which specifically includes the following steps: The image processing module receives the images of the marked points on the calibration board captured by the high-resolution camera and performs real-time analysis on each frame of the images of the marked points to detect whether the images are clear and whether the marked points are completely visible. If the image quality does not meet the standard, an alarm will be immediately issued, and the shooting parameters of the high-resolution camera will be adjusted to perform re-shooting to ensure that the image quality of the marked points captured by the high-resolution camera always meets the calibration requirements.

[0084] Step S3: Import the images of the marked points captured by the high-resolution camera into a computer, and use the image processing module to identify and process the images of the marked points captured by the high-resolution camera, and draw the boundaries of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp, which specifically includes the following steps: First, extract the position information of each marked point in the image of the marked points through image recognition and image processing techniques, and then draw the boundaries of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp respectively according to the position information of the marked points;

[0085] Specifically, during the calibration of the projected image, due to possible differences in the illumination intensity of the left and right high-definition projection headlights and factors such as the reflection characteristics of the calibration plate surface, the brightness of the marked points in the collected marked point images may be uneven. Therefore, an adaptive threshold segmentation technique is introduced in the image processing technology to address issues such as uneven illumination and complex backgrounds encountered during the calibration process. The specific steps are as follows: For each pixel in the marked point image, based on the brightness distribution of the local neighborhood where the pixel is located, the brightness threshold of each pixel is dynamically calculated. According to the brightness threshold, the pixel is classified as foreground or background. The pixels classified as foreground correspond to the marked points in the marked point image. Compared with the global threshold segmentation technique, this method can better adapt to changes in the illumination conditions in the projected image, improving the accuracy and robustness of image segmentation;

[0086] Specifically, the implementation of the adaptive threshold segmentation technique can adopt the local mean method. The calculation formula of the local mean method is as follows:

[0087]

[0088] Where T(x, y) is the brightness threshold at pixel (x, y);

[0089] S is the local neighborhood centered on pixel (x, y);

[0090] N is the number of pixels in the S neighborhood;

[0091] (i, j) are the pixel coordinates in the S neighborhood;

[0092] I(i, j) is the brightness value of pixel (i, j) in the S neighborhood;

[0093] C is a constant used to adjust the brightness threshold to adapt to different image characteristics.

[0094] Step S4: According to the boundaries of the projected images of the left and right high-definition projection headlights, calculate the deviation value between the projected images of the left and right high-definition projection headlights. By calculating the deviation value, the inconsistency between the projected images of the left and right high-definition projection headlights can be accurately quantified, ensuring the accuracy of subsequent lighting parameter adjustment;

[0095] Specifically, the deviation value between the projected images of the left and right high-definition projection headlights includes a horizontal deviation value, a vertical deviation value, and a rotation deviation value. The horizontal deviation value and the vertical deviation value directly reflect the misalignment degree of the projected images of the left and right high-definition projection headlights in the horizontal and vertical directions, and the rotation deviation value reflects the inconsistency in the rotation angle of the projected images of the left and right high-definition projection headlights. The calculation formula of the horizontal deviation value is as follows:

[0096]

[0097] The calculation formula for the vertical deviation value is as follows:

[0098]

[0099] The calculation formula for the rotation deviation value is as follows:

[0100]

[0101] Wherein, x Li and y Li are respectively the abscissa and ordinate of the i-th marked point in the projection image of the left high-definition projection headlight;

[0102] x Ri and y Ri are respectively the abscissa and ordinate of the i-th marked point in the projection image of the right high-definition projection headlight;

[0103] n is the total number of marked points;

[0104] Δx is the horizontal deviation value;

[0105] Δy is the vertical deviation value;

[0106] θ is the rotation deviation value.

[0107] Step S5, according to the deviation value between the projection images of the left high-definition projection headlight and the right high-definition projection headlight, adjust the lighting parameters of the left high-definition projection headlight and the right high-definition projection headlight;

[0108] Specifically, the adjustment of the lighting parameters of the left high-definition projection headlight and the right high-definition projection headlight includes the adjustment of the brightness, position and irradiation angle of the LED pixels. By precisely adjusting these parameters, the projection images of the left and right high-definition projection headlights are aligned in terms of position, direction and angle. The calculation formula for the brightness adjustment of the LED pixels is as follows:

[0109] L adjusted = L initial × k brightness ;

[0110] The calculation formula for the position adjustment of the LED pixels is as follows:

[0111] (x adjusted , y adjusted ) = (x initial , y initial ) + (Δx compensation , Δy compensation );

[0112] The calculation formula for the irradiation angle adjustment of the LED pixels is as follows:

[0113] θ adjusted = θinitial +Δθ compensation ;

[0114] Wherein, L adjusted is the brightness of the adjusted LED pixel;

[0115] (x adjusted , y adjusted ) is the position of the adjusted LED pixel;

[0116] θ adjusted is the irradiation angle of the adjusted LED pixel;

[0117] L initial is the initial brightness of the LED pixel;

[0118] (x initial , y initial ) is the initial position of the LED pixel;

[0119] θ initial is the initial irradiation angle of the LED pixel;

[0120] k brightness is the brightness adjustment coefficient;

[0121] (Δx compensation , Δy compensation ) is the LED pixel position compensation amount calculated according to the deviation value;

[0122] Δθ compensation is the LED pixel irradiation angle compensation amount calculated according to the deviation value.

[0123] Step S6, start the left high-definition projection headlight and the right high-definition projection headlight again, verify the alignment calibration effect of the projection images of the left high-definition projection headlight and the right high-definition projection headlight. You can use a high-resolution camera to take the image of the marking points on the calibration board again, and compare the projection images before and after the lighting parameter adjustment through the image processing module to confirm the alignment effect;

[0124] During the verification process, a closed-loop optimization mechanism is adopted to further improve the calibration accuracy. Specifically, the alignment calibration effect is monitored in real time through the feedback adjustment module, and the left high-definition projection headlight and the right high-definition projection headlight are controlled to continuously iterate the lighting parameters according to the alignment calibration effect until the predetermined alignment standard is reached, improving the practicability and applicability of the calibration system.

[0125] The working principle of the present invention is as follows:

[0126] A calibration board is set in front of the vehicle, and multiple marking points are set on the calibration board. The left high-definition projection headlamp and the right high-definition projection headlamp are started and irradiate the calibration board simultaneously. A high-resolution camera is used to capture the images of the marking points on the calibration board after being irradiated by the left high-definition projection headlamp and the right high-definition projection headlamp. The image processing module identifies and processes the images of the marking points captured by the high-resolution camera, draws the boundaries of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp. According to the boundaries of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp, the deviation value between the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp is calculated. According to the deviation value between the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp, the lighting parameters of the left high-definition projection headlamp and the right high-definition projection headlamp are adjusted. The left high-definition projection headlamp and the right high-definition projection headlamp are started again to verify the alignment calibration effect of the projection images of the left high-definition projection headlamp and the right high-definition projection headlamp. The feedback adjustment module monitors the alignment calibration effect in real time and controls the left high-definition projection headlamp and the right high-definition projection headlamp to continuously iterate the lighting parameters until the predetermined alignment standard is reached.

[0127] The present invention realizes the end-to-end full-process self-closed-loop dual-lamp fusion calibration from visual perception to image processing and then to headlamp control. By setting the calibration board to provide position reference points for the projection images of the left and right high-definition projection headlamps, it is beneficial to accurately calibrate the projection images. By using a high-resolution camera to collect the images of the marking points on the calibration board after being irradiated by the left and right high-definition projection headlamps from the preset optimal shooting position, it can ensure that the images of the marking points are clearly visible, and at the same time, dynamic light intensity adjustment and real-time image quality monitoring are carried out, solving the problem of unstable image quality of traditional calibration methods in different lighting environments, ensuring that the image quality of the marking points collected by the high-resolution camera always meets the calibration requirements, and guaranteeing the accuracy of subsequent image processing. In the image processing process, the adaptive threshold segmentation technology is introduced to solve the problems such as uneven illumination and complex background encountered in the calibration process, improving the accuracy and robustness of image segmentation. Using the control module to calculate the deviation value between the projection images of the left and right high-definition projection headlamps can accurately quantify the inconsistency between the projection images of the left and right high-definition projection headlamps, ensuring the accuracy of subsequent lighting parameter adjustment. Adopting an accurate algorithm to adjust the lighting parameters realizes the high-precision alignment of the projection images of the left and right high-definition projection headlamps in terms of position, direction and angle, improving the lighting effect and driving safety, and saving the hardware cost of dual-lamp projection image calibration. Setting the feedback adjustment module realizes the closed-loop optimization of the calibration system, can continuously iterate the lighting parameters, and improves the practicability and applicability of the calibration system.

[0128] The specific embodiments described above further elaborate on the technical problems solved, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A dual - lamp fusion calibration system for an intelligent self - closed - loop vehicle lamp, characterized in that, It includes a left high-definition projection headlight, a right high-definition projection headlight, a calibration board, a high-resolution camera, an image processing module, a control module, and a feedback adjustment module; Marker points are set on the calibration board; The high-resolution camera is used to capture the image of the marker points on the calibration board after being irradiated by the left high-definition projection headlight and the right high-definition projection headlight, and to monitor the light intensity projected onto the calibration board in real time; The image processing module is used to process the marker point image to obtain the projection image boundaries of the left high-definition projection headlight and the right high-definition projection headlight; The control module is used to calculate the deviation value between the projection images of the left high-definition projection headlight and the right high-definition projection headlight according to the projection image boundaries of the left high-definition projection headlight and the right high-definition projection headlight; The feedback adjustment module is used to monitor the alignment calibration effect of the projection images of the left high-definition projection headlight and the right high-definition projection headlight in real time, and to control the left high-definition projection headlight and the right high-definition projection headlight to optimize and adjust the lighting parameters according to the alignment calibration effect until the predetermined alignment standard is reached.

2. A calibration method for a dual - lamp fusion calibration system of the intelligent self - closed - loop vehicle lamp as described in claim 1, characterized in that, It includes the following steps: Step S1: Set a calibration board in front of the vehicle, with multiple marker points set on the calibration board, start the left high-definition projection headlight and the right high-definition projection headlight and irradiate the calibration board simultaneously; Step S2: Use the high-resolution camera to capture the image of the marker points on the calibration board after being irradiated by the left high-definition projection headlight and the right high-definition projection headlight from the preset shooting position and angle, and at the same time monitor the light intensity projected onto the calibration board in real time, perform dynamic light intensity adjustment according to the light intensity on the calibration board, and perform real-time image quality monitoring on the marker point image captured by the high-resolution camera; Step S3: Identify and process the marker point image captured by the high-resolution camera through the image processing module, and draw the boundaries of the projection images of the left high-definition projection headlight and the right high-definition projection headlight; Step S4: Calculate the deviation value between the projection images of the left high-definition projection headlight and the right high-definition projection headlight according to the projection image boundaries of the left high-definition projection headlight and the right high-definition projection headlight; Step S5: Adjust the lighting parameters of the left high-definition projection headlight and the right high-definition projection headlight according to the deviation value between the projection images of the left high-definition projection headlight and the right high-definition projection headlight; Step S6: Start the left high-definition projection headlight and the right high-definition projection headlight again, verify the alignment calibration effect of the projection images of the left high-definition projection headlight and the right high-definition projection headlight, monitor the alignment calibration effect in real time through the feedback adjustment module, and control the left high-definition projection headlight and the right high-definition projection headlight to perform continuous iteration of the lighting parameters until the predetermined alignment standard is reached.

3. The calibration method of the dual-lamp fusion calibration system for the intelligent self-closed-loop vehicle lamp according to claim 2, characterized in that, In step S2, when monitoring the light intensity projected onto the calibration board in real time and performing dynamic light intensity adjustment according to the light intensity on the calibration board, it specifically includes the following steps: The light intensity projected onto the calibration board is monitored in real time through the sensor built in the high-resolution camera, and the left high-definition projection headlight and the right high-definition projection headlight adjust the brightness of the LED pixels according to the light intensity on the calibration board sent by the high-resolution camera.

4. The calibration method of the dual-lamp fusion calibration system for the intelligent self-closed-loop vehicle lamp according to claim 2, characterized in that, In step S2, real-time image quality monitoring is performed on the marked point images captured by the high-resolution camera, which specifically includes the following steps: The image processing module receives the marked point images on the calibration board captured by the high-resolution camera, and performs real-time analysis on each frame of the marked point images to detect whether the images are clear and whether the marked points are completely visible. If the image quality does not meet the standard, an alarm is immediately issued, and the shooting parameters of the high-resolution camera are adjusted for reshooting.

5. The calibration method of the dual-lamp fusion calibration system for the intelligent self-closed-loop vehicle lamp according to claim 2, characterized in that In step S2, the calculation method of the preset shooting position includes the following steps: According to the position, size and marked point distribution data of the calibration board, as well as the parameters of the vehicle headlights of each model, the optimal shooting position, that is, the preset shooting position, is automatically calculated.

6. The calibration method of the dual-light fusion calibration system for the intelligent self-closed-loop vehicle lamp according to claim 2, characterized in that, In step S3, the image processing module identifies and processes the marked point images captured by the high-resolution camera, and draws the boundaries of the projection images of the left high-definition projection headlight and the right high-definition projection headlight, which specifically includes the following steps: First, the position information of each marked point in the marked point image is extracted through image recognition and image processing technologies, and then the boundaries of the projection images of the left high-definition projection headlight and the right high-definition projection headlight are respectively drawn according to the position information of the marked points.

7. The calibration method of the dual-lamp fusion calibration system of the intelligent self-closed-loop vehicle lamp according to claim 6, characterized in that, The image processing technology includes an adaptive threshold segmentation technology, which specifically includes the following steps: For each pixel in the marked point image, according to the brightness distribution of the local neighborhood where the pixel is located, the brightness threshold of each pixel is calculated, and the pixels are classified as foreground or background according to the brightness threshold. The pixels classified as foreground correspond to the marked points in the marked point image.

8. The calibration method of the dual-lamp fusion calibration system for an intelligent self-closed-loop vehicle lamp according to claim 7, characterized in that The adaptive threshold segmentation technology adopts the local mean method, and the calculation formula of the local mean method is as follows: Where T(x, y) is the brightness threshold at pixel (x, y); S is the local neighborhood centered on pixel (x, y); N is the number of pixels in the S neighborhood; (i, j) are the pixel coordinates in the S neighborhood; I(i, j) is the brightness value of pixel (i, j) in the S neighborhood; C is a constant.

9. The calibration method of the dual-lamp fusion calibration system for the intelligent self-closed-loop vehicle lamp according to claim 2, characterized in that, In step S4, the deviation values between the projection images of the left high-definition projection headlight and the right high-definition projection headlight include horizontal deviation value, vertical deviation value and rotation deviation value. The calculation formula of the horizontal deviation value is as follows: The calculation formula of the vertical deviation value is as follows: The calculation formula of the rotation deviation value is as follows: where x Li and y Li are the abscissa and ordinate of the i-th marked point in the projection image of the left high-definition projection headlamp, respectively; x Ri and y Ri are respectively the abscissa and ordinate of the i-th marked point in the projection image of the right high-definition projection headlamp; n is the total number of marked points; Δx is the horizontal deviation value; Δy is the vertical deviation value; θ is the rotation deviation value.

10. The calibration method of the dual-lamp fusion calibration system for the intelligent self-closed-loop vehicle lamp according to claim 2, wherein In step S5, the adjustment of the lighting parameters of the left high-definition projection headlight and the right high-definition projection headlight includes the adjustment of the brightness, position and irradiation angle of the LED pixels. The calculation formula for the brightness adjustment of the LED pixels is as follows: L adjusted = L initial × k brightness ; The calculation formula for the position adjustment of the LED pixels is as follows: (x adjusted , y adjusted ) = (x initial , y initial ) + (Δx compensation , Δy compensation ); The calculation formula for the irradiation angle adjustment of the LED pixels is as follows: θ adjusted = θ initial + Δθ compensation ; Among them, L adjusted is the brightness of the adjusted LED pixel; (x adjusted , y adjusted ) is the position of the adjusted LED pixel; θ adjusted is the irradiation angle of the adjusted LED pixel; L initial is the initial LED pixel brightness; (x initial , y initial ) is the initial LED pixel position; θ initial is the initial LED pixel illumination angle; k brightness is the brightness adjustment coefficient; (Δx compensation , Δy compensation ) is the LED pixel position compensation amount calculated based on the deviation value; Δθ compensation is the compensation amount of the LED pixel irradiation angle calculated according to the deviation value.

Images