Four-wheel positioning detection method and device, electronic equipment and storage medium
By segmenting and adjusting the exposure of the laser line area, calculating the pixel grayscale value, and adaptively adjusting the exposure, the measurement accuracy problem of four-wheel alignment detection under extreme lighting conditions is solved, and high-precision four-wheel alignment detection under different lighting conditions is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-31
- Publication Date
- 2026-03-24
AI Technical Summary
Existing four-wheel alignment testing equipment is prone to underexposure or overexposure of tire images captured by the camera under extreme lighting conditions, resulting in a decrease in measurement accuracy.
By acquiring standard images of the tire without laser lines and images with laser lines, segmenting the laser line area, making preliminary exposure adjustments, calculating the average and maximum grayscale values of pixels, and adaptively adjusting the exposure accuracy, a clear laser line target image is obtained for four-wheel alignment detection.
Under extreme lighting conditions, this method ensures uniform brightness and clear details in the laser line area, reduces the impact of lighting changes on the detection results, and improves the accuracy and stability of four-wheel alignment measurements.
Smart Images
Figure CN121724897A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image processing technology, and in particular to a four-wheel positioning detection method, apparatus, electronic device, and storage medium. Background Technology
[0002] Automotive four-wheel alignment parameters refer to a set of relative positional relationships between a vehicle's wheels and axles, including key parameters such as wheel camber, toe-in, caster angle, and kingpin inclination. The accuracy of four-wheel alignment directly affects vehicle stability, steering performance, and tire wear. Properly set parameters can effectively improve driving comfort, reduce fuel consumption, extend tire life, and ensure driving safety.
[0003] Existing four-wheel alignment detection equipment uses a non-contact measurement method, directly acquiring three-dimensional laser image data of the wheels through a camera to calculate alignment parameters. However, under different ambient lighting conditions (such as excessively dark or bright light, or interference from reflections), the exposure of the images acquired by the camera is often unstable, leading to decreased image contrast or loss of detail, thus affecting the accuracy of subsequent laser line extraction and measurement.
[0004] In summary, to ensure accurate acquisition of tire images under various lighting conditions, an image acquisition method that can adaptively adjust exposure parameters is needed. This would enable the camera to obtain clear and stable tire image data even under extreme lighting conditions, thereby improving the reliability and consistency of four-wheel alignment measurement results.
[0005] Therefore, in extreme lighting conditions, existing four-wheel alignment methods are prone to underexposure or overexposure of tire images captured by cameras, leading to a decrease in the accuracy of four-wheel alignment measurements. Summary of the Invention
[0006] This invention provides a four-wheel alignment detection method, device, electronic equipment, and storage medium, the main purpose of which is to solve the problem of decreased accuracy in four-wheel alignment measurements.
[0007] To achieve the above objectives, the present invention provides a four-wheel alignment detection method, comprising: Acquire a standard image of the target car tire without laser lines and an image of the tire with laser lines, and segment the laser line region of the tire laser line image; Preliminary exposure adjustments are made to the laser line area to obtain an adjusted image of the tire laser line. Calculate the average and maximum gray values of the pixels based on the standard image of the tire without laser lines and the adjusted image of the tire with laser lines, respectively. The exposure accuracy of the tire laser line adjustment image is adjusted based on the average gray value of the pixel and the maximum gray value of the pixel to obtain the tire laser line target image; Based on the target image of the tire laser line, four-wheel alignment detection is performed on the target vehicle.
[0008] The present invention also provides a four-wheel alignment detection device, the device comprising: The laser line region segmentation module is used to acquire a standard image of the tire without laser lines and an image of the tire with laser lines of the target car tire, and to segment the laser line region of the tire laser line image; The initial exposure adjustment module is used to perform initial exposure adjustment on the laser line area to obtain a tire laser line adjustment image; The grayscale value calculation module is used to calculate the corresponding average grayscale value and maximum grayscale value of the pixels based on the standard image of the tire without laser lines and the adjusted image of the tire with laser lines, respectively. An exposure accuracy adjustment module is used to adjust the exposure accuracy of the tire laser line adjustment image based on the average gray value of the pixel and the maximum gray value of the pixel, so as to obtain the tire laser line target image. The four-wheel alignment detection module is used to perform four-wheel alignment detection on the target vehicle based on the target image of the tire laser line.
[0009] The present invention also provides an electronic device, the electronic device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the four-wheel alignment detection method described above.
[0010] The present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the four-wheel alignment detection method described above.
[0011] This invention, through acquiring a standard image of the target vehicle tire without laser lines and an image of the tire with laser lines, precisely segments the laser line region in the laser line image. This effectively obtains clear laser line region information for initial exposure adjustment of the laser line region, achieving adaptive exposure control based on the average background grayscale value. This ensures that the laser line region in the final adjusted tire laser line image has balanced brightness and clear details. By calculating the average pixel grayscale value of the standard tire image without laser lines and the maximum pixel grayscale value of the adjusted tire laser line image, the background brightness and laser reflection intensity of the tire surface can be accurately distinguished, thereby effectively eliminating the influence of external factors such as ambient light and material reflection on the detection results. Through adaptive image exposure adjustment, the brightness contrast between the laser line grayscale region and the background is optimized, effectively obtaining a tire laser line target image with balanced illumination and clear laser lines. Therefore, the four-wheel alignment detection method, device, electronic equipment, and storage medium proposed in this invention can solve the problem that existing four-wheel alignment methods are prone to underexposure or overexposure of tire images acquired by the camera under extreme lighting conditions, leading to a decrease in four-wheel alignment measurement accuracy. Attached Figure Description
[0012] Figure 1 This is a flowchart illustrating a four-wheel alignment detection method according to an embodiment of the present invention. Figure 2 A camera acquires tire laser line images in a four-wheel alignment detection method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the laser line region segmentation process in a four-wheel positioning detection method provided in an embodiment of the present invention; Figure 4 This is an image of the laser line region segmented from the image of the four-wheel positioning detection method provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the initial adjustment of laser line area exposure in a four-wheel positioning detection method provided in an embodiment of the present invention; Figure 6 This is a tire laser line target image after exposure accuracy adjustment for a four-wheel alignment detection method provided in an embodiment of the present invention; Figure 7 This is a functional block diagram of a four-wheel alignment detection device provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of an electronic device that implements the four-wheel positioning detection method according to an embodiment of the present invention.
[0013] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0014] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0015] To address the issue that existing four-wheel alignment methods often suffer from underexposure or overexposure of tire images captured by cameras under extreme lighting conditions, an embodiment of the present invention provides a four-wheel alignment detection method based on three-dimensional laser images.
[0016] Reference Figure 1 The diagram shown is a flowchart illustrating a four-wheel alignment detection method according to an embodiment of this application. In this embodiment, the four-wheel alignment detection method includes: S1. Acquire standard images of the target car tire without laser lines and images of the tire with laser lines, and segment the laser line region of the tire laser line image.
[0017] In this embodiment, the target car tire is the specific car tire object for which image acquisition is required. The standard tire image without laser lines is captured when the laser emitter is not activated; the image only contains the natural surface texture of the tire itself, excluding the red or green laser line used for 3D measurement. This serves as a comparison benchmark for tire laser line images captured at the same location with the laser activated. Figure 2 The image shown illustrates a tire laser line image acquired by a camera in a four-wheel alignment detection method according to an embodiment of the present invention. The tire laser line image is a tire image obtained by scanning the target vehicle tire using laser scanning technology; the laser line is used to capture three-dimensional information of the tire surface.
[0018] like Figure 3 The diagram shown is a flowchart illustrating the laser line region segmentation process in a four-wheel positioning detection method provided by an embodiment of the present invention.
[0019] In detail, the segmentation of the laser line region in the tire laser line image includes: S11, scaling and normalizing the tire laser line image to obtain a normalized tire laser line image; S12, performing laser line target detection on the normalized tire laser line image to obtain the target bounding box coordinates and confidence score for each laser line target; S13, cropping the normalized tire laser line image based on the target bounding box coordinates and confidence score to obtain an initial cropped region; S14, segmenting the tire laser line image based on the initial cropped region to obtain the laser line region.
[0020] In this embodiment, since different shooting distances or lighting conditions can cause differences in the image size and brightness of the captured tire laser line images, the tire laser line images are scaled and normalized to unify the image resolution and grayscale range, eliminating the influence caused by changes in camera installation position, tire size, or light intensity, and obtaining a normalized tire laser line image with standard size and brightness distribution.
[0021] In this embodiment, the YOLOv8 target detection model can be used to analyze the normalized image of the tire laser line. Multi-layer convolution operations are performed on the normalized image to extract feature information including edges, brightness gradients, and stripe patterns. Feature pyramid networks are then used to fuse feature information at different scales to generate multiple candidate detection boxes. The laser line features learned during training (such as bright, thin stripes, smooth edges, and significant brightness contrast) are then used to determine, pixel by pixel, which candidate detection boxes belong to the laser line target. Target detection boxes belonging to the laser line target are then selected from the candidate detection boxes, and the coordinates of the target detection boxes are obtained.
[0022] Furthermore, the YOLOv8 object detection model calculates a confidence value for each bounding box that belongs to a laser line target, representing the probability that the YOLOv8 object detection model considers the target within the bounding box to be a laser line. For example, when the confidence value of a bounding box is 0.93, it means that the model considers that region to be a laser line with a 93% confidence level.
[0023] In this embodiment, target bounding box coordinates greater than a preset confidence threshold are selected based on the confidence level. The specific position of each laser line target in the tire laser line normalized image is determined based on the selected target bounding box coordinates. Based on the specific position, the region containing each laser line is cropped from the tire laser line normalized image to form multiple initial cropping regions that are precisely focused on the position of each laser line.
[0024] like Figure 4 The image shown is a laser line region image segmented from an image of a four-wheel positioning detection method provided in an embodiment of the present invention.
[0025] Furthermore, the initial cropping area is converted into a grayscale cropping area. It is determined whether each pixel in the grayscale cropping area is greater than a preset pixel threshold. If each pixel in the grayscale cropping area is less than or equal to the pixel threshold, the pixels less than or equal to the pixel threshold are set to black. If each pixel in the grayscale cropping area is greater than the pixel threshold, the pixels greater than the pixel threshold are set to white. All white pixels are then combined into a laser line area.
[0026] This application can effectively obtain clear laser line area information by acquiring standard images of tires without laser lines and images with laser lines, and by accurately segmenting the laser line area in the laser line image.
[0027] S2. Perform preliminary exposure adjustments on the laser line area to obtain the tire laser line adjustment image.
[0028] In this embodiment of the application, in order to address the problem of uneven reflection on the tire surface, the grayscale distribution of the laser line area in the tire laser line image is detected, and the exposure of the darker areas is automatically increased while the exposure of the overly bright areas is reduced. This ensures that the laser line remains within the ideal grayscale range in different materials and tread patterns, thereby avoiding line breakage, saturation, or grayscale distortion caused by overexposure or underexposure.
[0029] like Figure 5 The diagram shown is a flowchart illustrating the initial adjustment of laser line area exposure in a four-wheel positioning detection method provided by an embodiment of the present invention.
[0030] In detail, the initial exposure adjustment of the laser line area is performed to obtain the tire laser line adjusted image, including: S21, performing an opening operation on the laser line area to obtain an opening operation image; S22, calculating the total gray value of the pixels in the opening operation image based on the gray value of all pixels in the opening operation image; S23, averaging the total gray value of the pixels in the opening operation image to obtain the average background gray value; S24, adjusting the exposure of the opening operation image based on the average background gray value and a preset gray value threshold range to obtain the tire laser line adjusted image.
[0031] Further, an opening operation is performed on the laser line region to obtain an opening operation image, including: converting the tire laser line image into a grayscale laser line image; generating a structuring element based on the laser line region in the grayscale laser line image; using the structuring element to remove isolated bright spots from the laser line region to obtain a denoised laser line region; and restoring the line integrity of the denoised laser line region to obtain the opening operation image.
[0032] In detail, the tire laser line image is converted from the original RGB color image to a grayscale image to obtain a grayscale laser line image; specifically, a single grayscale value is calculated based on the red (R), green (G), and blue (B) channel brightness values of each pixel in the tire laser line image to remove irrelevant color information and retain only the brightness variation characteristics of the laser line.
[0033] In this embodiment, corresponding structural elements can be automatically generated based on the morphological characteristics (such as line width, direction, and continuity) of the laser line region in a grayscale laser line image. For example, linear or rectangular structural elements can be generated based on the main direction of the laser line. A structural element is a small, predefined shape template used to guide morphological erosion, dilation, and other operations, determining which pixels in the image are retained, expanded, or removed. The shape template is used to perform erosion and dilation operations on the laser line region to remove isolated noise, connect broken line segments, and smooth edges, thereby obtaining a continuous and complete laser line structure.
[0034] The process involves erosion of the laser line area to remove isolated bright spots and small noise points, and to eliminate stray bright pixels caused by reflections, dust, or textures, resulting in a clean, denoised laser line area. A dilation operation is then performed on the denoised image to restore the line width and continuity of the laser lines without introducing new noise, generating an opening image with uniform brightness and smooth edges.
[0035] In this embodiment, the exposure of the opening operation image is adjusted according to the average background gray value and a preset gray value threshold range to obtain a tire laser line adjustment image. This includes: reducing the image exposure of the opening operation image when the average background gray value is greater than the upper limit of the gray value threshold range; using the opening operation image as the tire laser line adjustment image when the average background gray value is less than the upper limit of the gray value threshold range but greater than the lower limit of the gray value threshold range; and increasing the image exposure of the opening operation image when the average background gray value is less than the lower limit of the gray value threshold range.
[0036] Specifically, when the average background grayscale value is higher than the upper limit of the grayscale threshold range, it indicates that the overall image of the opening operation is too bright. The system automatically reduces the exposure parameters to avoid overexposure and generates a tire laser line adjustment image with moderate brightness. When the average background grayscale value is within the grayscale threshold range, it indicates that the exposure of the opening operation image is normal. The system keeps the original image unchanged and directly uses the opening operation image as the tire laser line adjustment image. When the average background grayscale value is lower than the grayscale threshold range threshold, it indicates that the overall image of the opening operation is too dark. The system automatically increases the exposure to enhance brightness and contrast, resulting in a clear and distinguishable tire laser line adjustment image.
[0037] Preliminary exposure adjustments were made to the laser line area, achieving adaptive exposure control based on the average background grayscale value, ensuring that the laser line area in the final tire laser line adjusted image has uniform brightness and clear details.
[0038] S3. Calculate the average and maximum gray values of the corresponding pixels based on the standard image of the tire without laser lines and the adjusted image of the tire with laser lines.
[0039] In this embodiment, the average gray value and maximum gray value of pixels are calculated for the standard image of the tire without laser lines and the adjusted image of the tire with laser lines, respectively, to obtain the comparison relationship between the background brightness and the laser line brightness, which is then used to determine whether the laser line area has reached the ideal exposure state after the initial adjustment.
[0040] In detail, the average and maximum grayscale values of the pixels are calculated based on the standard image of the tire without laser lines and the adjusted image of the tire with laser lines, respectively. This includes: mapping the laser line region of the adjusted image of the tire to the standard image of the tire without laser lines to obtain a target region in the standard image of the tire without laser lines where the laser line region is located at the same position; calculating the center column position of the laser line region and the center column position of the target region based on the laser line region and the target region, respectively; converting the laser line region and the target region into a laser line grayscale region and a target grayscale region, respectively; and using the vertical directions of the center column positions of the laser line region and the target region as... The target scanning direction is defined for both the laser line grayscale region and the target grayscale region. The total number of pixels and the total grayscale value of the grayscale region are counted along the target scanning direction. The average grayscale value of the pixels in both the laser line grayscale region and the target grayscale region are calculated based on these values. The laser line grayscale region and the target grayscale region are scanned line by line along the target scanning direction to obtain the laser line pixel grayscale value and the target pixel grayscale value for each pixel. The maximum grayscale value of the pixels in both the laser line grayscale region and the target grayscale region is then selected based on these values.
[0041] In this embodiment, the tire laser line adjustment image and the tire standard image without laser lines are spatially mapped. By uniformly correcting the size, coordinate system and tire center position of the two images, the laser line area of the tire laser line adjustment image is accurately located on the tire standard image without laser lines, and the corresponding target area in the tire standard image without laser lines is obtained, so that the laser line information corresponds accurately with the original features of the tire surface.
[0042] In this embodiment, before calculating the average gray value and maximum gray value of pixels in the laser line gray area and the target gray area, the gray values of all pixels in the laser line gray area and the target gray area are compared with the preset maximum gray value threshold and minimum gray value threshold. Pixels that are greater than the maximum gray value threshold or less than the minimum gray value threshold are removed to eliminate the influence of extreme values on the calculation results of the average gray value and maximum gray value of pixels.
[0043] Furthermore, the horizontal direction (from left to right) of the image is defined as the column direction, and the vertical direction (from top to bottom) is defined as the row direction. The column position of the center of the laser line region reflects the geometric center of the laser line in the horizontal direction in the tire laser line adjustment image, and the column position of the center of the target region reflects the geometric center of the target region in the horizontal direction in the standard image without laser lines.
[0044] Specifically, geometric analysis is performed on the laser line region in the tire laser line adjustment image and the target region in the standard image without laser lines, respectively. The geometric center coordinates of each laser line region and target region in the horizontal direction are calculated, and the geometric center coordinates of the region in the horizontal direction are used as the center column position.
[0045] In this embodiment, the tire laser line area and the corresponding target area are converted into grayscale images to obtain the laser line grayscale area and the target grayscale area, so as to remove color interference and retain only the brightness information.
[0046] In this embodiment, the target grayscale region corresponding to the standard image of the tire without laser lines is analyzed. The vertical direction of the image (from top to bottom) where the center column of the target region is located is taken as the target scanning direction. The total number of pixels and the total grayscale value of the region are counted along the target scanning direction. Further, the total grayscale value of the region is divided by the total number of pixels in the region to obtain the average grayscale value. The average grayscale value reflects the background brightness characteristics of the tire surface under conditions without laser irradiation. The method for calculating the average grayscale value of the laser line region in the tire laser line adjustment image is the same as the method for calculating the average grayscale value of the target grayscale region in the standard image of the tire without laser lines, and will not be described in detail here.
[0047] In this embodiment, the vertical direction of the image (from top to bottom) where the center column of the laser line region is located is taken as the target scanning direction. The grayscale region of the laser line is scanned line by line along this direction, and the grayscale value changes of each pixel in the laser line grayscale region are recorded in real time. By comparing the grayscale values of all scanned laser line pixels, the pixel with the maximum grayscale value is selected. The pixel position corresponding to the maximum grayscale value represents the strongest reflection point of the laser line in the vertical direction, which can be used to accurately determine the center position of the laser line. The method for calculating the maximum grayscale value of the target grayscale region of the tire laser-line-free standard image is the same as the method for calculating the maximum grayscale value of the laser line region of the tire laser-line-adjusted image, and will not be described in detail here.
[0048] This application can accurately distinguish between the background brightness and laser reflection intensity of the tire surface by calculating the average gray value of the standard image of the tire without laser lines and the maximum gray value of the image of the tire with laser lines, thereby effectively eliminating the influence of external factors such as ambient light and material reflection on the detection results.
[0049] S4. Adjust the exposure accuracy of the tire laser line image based on the average gray value and the maximum gray value of the pixels to obtain the tire laser line target image.
[0050] In this embodiment, by comparing the average gray value of pixels in the laser line area with the maximum gray value of pixels, it is determined whether the laser line is within the ideal brightness range. Based on the determination result, the image exposure is adjusted so that the laser line is clearly visible throughout the entire area without being overexposed.
[0051] In detail, the exposure accuracy of the tire laser line adjustment image is adjusted based on the average gray value and the maximum gray value of the pixels to obtain the tire laser line target image. This includes: subtracting the maximum gray value of the pixels in the laser line gray area and the target gray area to obtain a first gray-level difference; subtracting the average gray value of the pixels in the laser line gray area and the target gray area to obtain a second gray-level difference; if the first gray-level difference is less than a preset first difference threshold or the second gray-level difference is less than a preset second difference threshold, the exposure of the laser line gray area is increased; if the first gray-level difference is greater than the preset first difference threshold or the second gray-level difference is greater than the preset second difference threshold, the exposure of the laser line gray area is decreased; and the tire laser line adjustment image corresponding to the laser line gray area after exposure adjustment is used as the tire laser line target image.
[0052] In this embodiment, the average and maximum gray values of the pixels in the standard image of the tire without laser lines and the image of the tire with laser lines are sampled multiple times and averaged or weighted to obtain more representative average and maximum gray values, thereby reducing the random error of a single measurement.
[0053] The average grayscale value of the pixels at the corresponding positions in the laser line grayscale region of the tire laser line adjustment image is compared with that in the target grayscale region of the standard tire image without laser lines. The difference between the two is calculated to obtain the first grayscale difference value. At the same time, the maximum grayscale value of the pixels in the laser line grayscale region is compared with that in the target grayscale region, and the difference between the two is calculated to obtain the second grayscale difference value. Thus, the difference information between the laser line region and the target region in terms of average grayscale and maximum grayscale is obtained.
[0054] like Figure 6 The image shown is a tire laser line target image after exposure accuracy adjustment in a four-wheel alignment detection method provided by an embodiment of the present invention.
[0055] Furthermore, the calculated first grayscale difference is compared with a preset first difference threshold, and the second grayscale difference is compared with a preset second difference threshold. If the first grayscale difference is less than the first difference threshold or the second grayscale difference is less than the second difference threshold, it indicates that the laser reflection signal is weak or the brightness is uneven, meaning the overall image is too dark, and the exposure needs to be automatically increased to enhance the laser line brightness. If the second grayscale difference is greater than the second difference threshold, the overall surface image is too bright, and the exposure needs to be automatically reduced to prevent overexposure.
[0056] This application optimizes the brightness and background contrast of the laser line grayscale area by adaptively adjusting the image exposure, effectively obtaining a tire laser line target image with balanced illumination and clear laser lines.
[0057] S5. Based on the target image of the tire laser line, perform four-wheel positioning detection on the target vehicle.
[0058] In this embodiment, by adaptively adjusting the exposure to obtain a tire laser line target image with uniform illumination and clear laser lines, the recognizability of tire edge and laser line features in four-wheel alignment detection can be significantly improved, and the measurement error caused by uneven illumination or blurred laser lines can be reduced, thereby improving the stability of the four-wheel alignment detection results and reducing the dependence on ambient light conditions.
[0059] like Figure 7 The diagram shown is a functional block diagram of a four-wheel alignment detection device provided in an embodiment of the present invention.
[0060] The four-wheel alignment detection device 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the four-wheel alignment detection device 100 may include a laser line area segmentation module 101, an initial exposure adjustment module 102, a grayscale value calculation module 103, an exposure accuracy adjustment module 104, and a four-wheel alignment detection module 105. The module described in this invention can also be called a unit, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.
[0061] In this embodiment, the functions of each module / unit are as follows: The laser line region segmentation module 101 is used to acquire a standard image of the tire without laser lines and a tire laser line image of the target car tire, and segment the laser line region of the tire laser line image. The initial exposure adjustment module 102 is used to perform initial exposure adjustment on the laser line area to obtain a tire laser line adjustment image; The grayscale value calculation module 103 is used to calculate the corresponding average grayscale value and maximum grayscale value of the pixels based on the tire laser-free standard image and the tire laser-adjusted image, respectively. The exposure accuracy adjustment module 104 is used to adjust the exposure accuracy of the tire laser line adjustment image according to the average gray value of the pixel and the maximum gray value of the pixel, so as to obtain the tire laser line target image. The four-wheel alignment detection module 105 is used to perform four-wheel alignment detection on the target vehicle based on the target image of the tire laser line.
[0062] In one embodiment, the laser line region segmentation module 101 is specifically used to scale and normalize the tire laser line image to obtain a normalized tire laser line image; perform laser line target detection on the normalized tire laser line image to obtain the target bounding box coordinates and confidence score of each laser line; crop the normalized tire laser line image according to the target bounding box coordinates and the confidence score to obtain an initial cropped region; and segment the tire laser line image according to the initial cropped region to obtain the laser line region.
[0063] In one embodiment, the initial exposure adjustment module 102 is specifically used to perform an opening operation on the laser line region to obtain an opening operation image; calculate the total gray value of the pixels in the opening operation image based on the gray value of all pixels in the opening operation image; average the total gray value of the pixels in the opening operation image to obtain an average background gray value; and adjust the exposure of the opening operation image based on the average background gray value and a preset gray value threshold range to obtain a tire laser line adjustment image.
[0064] In one embodiment, the initial exposure adjustment module 102 is specifically used to convert the tire laser line image into a grayscale laser line image; generate a structural element based on the laser line region in the grayscale laser line image; use the structural element to remove isolated bright spots from the laser line region to obtain a laser line denoising region; and restore the line integrity of the laser line denoising region to obtain an opening operation image.
[0065] In one embodiment, the initial exposure adjustment module 102 is specifically used to: reduce the image exposure of the opening operation image to obtain a tire laser line adjustment image when the average background gray value is greater than the upper limit of the gray value threshold range; not adjust the image exposure of the opening operation image and use the opening operation image as the tire laser line adjustment image when the average background gray value is less than the upper limit of the gray value threshold range but greater than the lower limit of the gray value threshold range; and increase the image exposure of the opening operation image to obtain the tire laser line adjustment image when the average background gray value is less than the lower limit of the gray value threshold range.
[0066] In one embodiment, the grayscale calculation module 103 is used to map the laser line region of the tire laser line adjustment image to the tire laser-free standard image to obtain a target region in the tire laser-free standard image where the laser line region and the target region are at the same position; calculate the center column position of the laser line region and the center column position of the target region based on the laser line region and the target region respectively; convert the laser line region and the target region into a laser line grayscale region and a target grayscale region respectively; and use the vertical directions of the center column positions of the laser line region and the target region as the target scans of the laser line grayscale region and the target grayscale region respectively. The scanning direction is as follows: The total number of pixels and the total grayscale value of the laser line grayscale region and the target grayscale region are counted along the target scanning direction. The average grayscale value of the pixels in the laser line grayscale region and the target grayscale region are calculated based on the total number of pixels and the total grayscale value. The laser line grayscale region and the target grayscale region are scanned line by line along the target scanning direction to obtain the laser line pixel grayscale value and the target pixel grayscale value for each pixel. The maximum grayscale value of the pixels in the laser line grayscale region and the target grayscale region are selected based on the laser line pixel grayscale value and the target pixel grayscale value.
[0067] In one embodiment, the exposure accuracy adjustment module 104 is specifically used to: subtract the maximum gray value of the pixel in the laser line grayscale region and the target grayscale region to obtain a first grayscale difference; subtract the average gray value of the pixel in the laser line grayscale region and the target grayscale region to obtain a second grayscale difference; if the first grayscale difference is less than a preset first difference threshold or the second grayscale difference is less than a preset second difference threshold, then increase the exposure of the laser line grayscale region; if the first grayscale difference is greater than the preset first difference threshold or the second grayscale difference is greater than the preset second difference threshold, then decrease the exposure of the laser line grayscale region; and use the tire laser line adjustment image corresponding to the laser line grayscale region after exposure adjustment as the tire laser line target image.
[0068] In detail, each module in the four-wheel alignment detection device 100 described in this embodiment of the invention uses the same technical means as the four-wheel alignment detection method described in the accompanying drawings, and can produce the same technical effect, which will not be repeated here.
[0069] like Figure 8 The diagram shown is a structural schematic of an electronic device for implementing a four-wheel positioning detection method according to an embodiment of the present invention.
[0070] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program, such as a four-wheel alignment detection program, stored in the memory 11 and capable of running on the processor 10.
[0071] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a four-wheel alignment detection program) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.
[0072] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of a four-wheel alignment detection program, but also to temporarily store data that has been output or will be output.
[0073] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.
[0074] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.
[0075] Figure 8 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 8 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.
[0076] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.
[0077] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.
[0078] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.
[0079] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).
[0080] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the face recognition method based on infrared speckle images described in any of the above embodiments. It should be noted that the computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).
[0081] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.
[0082] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0083] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.
[0084] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0085] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.
[0086] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.
[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims
1. A four-wheel alignment detection method, characterized in that, The method includes: Acquire a standard image of the target car tire without laser lines and an image of the tire with laser lines, and segment the laser line region of the tire laser line image; Preliminary exposure adjustments are made to the laser line area to obtain an adjusted image of the tire laser line. Calculate the average and maximum gray values of the pixels based on the standard image of the tire without laser lines and the adjusted image of the tire with laser lines, respectively. The exposure accuracy of the tire laser line adjustment image is adjusted based on the average gray value of the pixel and the maximum gray value of the pixel to obtain the tire laser line target image; Based on the target image of the tire laser line, four-wheel alignment detection is performed on the target vehicle.
2. The four-wheel alignment detection method as described in claim 1, characterized in that, The laser line region segmenting the tire laser line image includes: The tire laser line image is scaled and normalized to obtain a normalized tire laser line image; Laser line target detection is performed on the normalized image of the tire laser line to obtain the target bounding box coordinates and confidence level of each laser line; The tire laser line normalized image is cropped according to the target box coordinates and the confidence level to obtain the initial cropping region; Based on the initial cropping area, the tire laser line image is segmented to obtain the laser line region.
3. The four-wheel alignment detection method as described in claim 1, characterized in that, The initial exposure adjustment of the laser line area to obtain the tire laser line adjustment image includes: An opening operation is performed on the laser line region to obtain an opening operation image; The total gray value of the pixels in the opening operation image is calculated based on the gray value of all pixels in the opening operation image. The average background gray value is obtained by averaging the total gray values of the pixels in the image obtained from the opening operation. The exposure of the opening operation image is adjusted based on the average background gray value and the preset gray threshold range to obtain the tire laser line adjustment image.
4. The four-wheel alignment detection method as described in claim 3, characterized in that, The step of performing an opening operation on the laser line region to obtain an opening operation image includes: Convert the tire laser line image into a grayscale laser line image; Structural elements are generated based on the laser line regions in the grayscale laser line image; The isolated bright spots in the laser line region are removed using the structural elements to obtain a laser line noise reduction region. The integrity of the lines in the laser line denoising area is restored to obtain the opening operation image.
5. The four-wheel alignment detection method as described in claim 3, characterized in that, The step of adjusting the exposure of the opening operation image based on the average background grayscale value and a preset grayscale threshold range to obtain a tire laser line adjustment image includes: When the average background grayscale value is greater than the upper limit of the grayscale threshold range, the image exposure of the opening operation image is reduced to obtain the tire laser line adjustment image; When the average background grayscale value is less than the upper limit of the grayscale threshold range and greater than the lower limit of the grayscale threshold range, the image exposure of the opening operation image is not adjusted, and the opening operation image is used as the tire laser line adjustment image. When the average background grayscale value is less than the lower limit of the grayscale threshold range, the image exposure of the opening operation image is increased to obtain the tire laser line adjustment image.
6. The four-wheel alignment detection method as described in claim 1, characterized in that, The step of calculating the corresponding average grayscale value and maximum grayscale value of pixels based on the standard image of the tire without laser lines and the adjusted image of the tire with laser lines includes: The laser line region of the tire laser line adjustment image is mapped onto the tire laser line-free standard image to obtain a target region in which the tire laser line-free standard image and the laser line region are in the same position. Calculate the center column position of the laser line region and the center column position of the target region based on the laser line region and the target region, respectively. The laser line region and the target region are converted into a laser line grayscale region and a target grayscale region, respectively. The vertical directions of the center column positions of the laser line region and the center column positions of the target region are respectively taken as the target scanning directions of the laser line grayscale region and the target grayscale region; Along the target scanning direction, the total number of pixels and the total pixel grayscale value of the grayscale region of the laser line grayscale region and the target grayscale region are counted respectively. Calculate the average pixel grayscale value of the laser line grayscale region and the target grayscale region based on the total number of pixels in the grayscale region and the total pixel grayscale value of the region, respectively. The laser line grayscale region and the target grayscale region are scanned line by line according to the target scanning direction to obtain the laser line pixel grayscale value and the target pixel grayscale value of each pixel. The maximum grayscale value of the pixels in the laser line grayscale region and the target grayscale region are selected based on the grayscale value of the laser line pixels and the grayscale value of the target pixels, respectively.
7. The four-wheel alignment detection method as described in claim 1, characterized in that, The step of adjusting the exposure accuracy of the tire laser line adjustment image based on the average gray value of the pixels and the maximum gray value of the pixels to obtain the tire laser line target image includes: The first grayscale difference value is obtained by subtracting the maximum grayscale value of the pixel in the grayscale region of the laser line and the grayscale region of the target grayscale region. The second grayscale difference value is obtained by subtracting the average grayscale value of the pixels in the grayscale region of the laser line and the grayscale region of the target grayscale region. If the first grayscale difference is less than a preset first difference threshold or the second grayscale difference is less than a preset second difference threshold, the exposure of the grayscale region of the laser line is increased; if the first grayscale difference is greater than a preset first difference threshold or the second grayscale difference is greater than a preset second difference threshold, the exposure of the grayscale region of the laser line is decreased. The tire laser line adjustment image corresponding to the grayscale area of the laser line after exposure adjustment is used as the tire laser line target image.
8. A four-wheel alignment detection device, characterized in that, The device includes: The laser line region segmentation module is used to acquire a standard image of the tire without laser lines and an image of the tire with laser lines of the target car tire, and to segment the laser line region of the tire laser line image; The initial exposure adjustment module is used to perform initial exposure adjustment on the laser line area to obtain a tire laser line adjustment image; The grayscale value calculation module is used to calculate the corresponding average grayscale value and maximum grayscale value of the pixels based on the standard image of the tire without laser lines and the adjusted image of the tire with laser lines, respectively. An exposure accuracy adjustment module is used to adjust the exposure accuracy of the tire laser line adjustment image based on the average gray value of the pixel and the maximum gray value of the pixel, so as to obtain the tire laser line target image. The four-wheel alignment detection module is used to perform four-wheel alignment detection on the target vehicle based on the target image of the tire laser line.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the four-wheel alignment detection method as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the four-wheel alignment detection method as described in any one of claims 1 to 7.