Brake disc defect online detection method and system based on machine vision

Abstract

The invention provides a brake disc defect online detection method and system based on machine vision. The method comprises the steps that a first image on a finished product conveying device is collected through a first image collecting device; according to the conveying direction and the conveying speed of the finished product conveying device, the first image is restored, and a second image is obtained; performing positioning extraction operation on the second image to obtain a region image corresponding to the brake disc; and the regional image is preprocessed and defect extraction is carried out, and first alarm information is output after defects are extracted. According to the brake disc defect online detection method and system based on machine vision, dynamic online detection is achieved, and the detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an online detection method and system for brake disc defects based on machine vision. Background Art

[0002] With the rapid advancement of science and technology and the continuous development of industrial production, quality control plays a vital role in the manufacturing industry. However, in large-scale production processes, defects and failures are inevitable, which have a negative impact on product quality and production efficiency. Traditional manual inspection cannot meet the requirements of high-efficiency and high-precision quality control, so machine vision defect detection technology came into being.

[0003] When deep learning methods are applied in practice, it is also necessary to consider the problem of brake disc movement on the production line, that is, how to achieve dynamic online detection. Summary of the invention

[0004] One of the purposes of the present invention is to provide a method and system for online detection of brake disc defects based on machine vision, so as to realize dynamic online detection and improve detection efficiency.

[0005] An embodiment of the present invention provides a method for online detection of brake disc defects based on machine vision, comprising:

[0006] Capturing a first image on the finished product conveying device by a first image acquisition device;

[0007] According to the conveying direction and conveying speed of the finished product conveying device, the first image is restored to obtain a second image;

[0008] Performing a positioning extraction operation on the second image to obtain an area image corresponding to the brake disc;

[0009] The regional image is preprocessed and defects are extracted, and the first alarm information is output after the defects are extracted.

[0010] Preferably, the step of restoring the first image includes:

[0011] According to the pixel sampling interval, conveying direction and conveying speed of the first image, a preset deviation parameter determination table is searched to retrieve the deviation parameter;

[0012] A restored and reconstructed image is constructed according to the starting pixel point and the pixel sampling order in the first image, and the pixels after the starting pixel point are resampled from the first image according to the deviation parameter to obtain the second image.

[0013] Preferably, the steps of performing a positioning extraction operation on the second image are as follows:

[0014] Binarizing the first image and then extracting edges to obtain an edge-extracted image;

[0015] The minimum circumscribed circle fitting method is used to fit the edge extraction image, set the mask, extract the working surface, and obtain the regional image.

[0016] Preferably, preprocessing the regional image includes: median filtering image denoising and using Laplacian operator to perform image enhancement.

[0017] Preferably, the defect extraction steps are as follows:

[0018] The OTSU algorithm is used to segment and extract defects, the improved Canny operator is used for scratch detection, the probabilistic Hough transform method is combined to connect scratches, and parallel processing is introduced to shorten the detection time of the improved Canny algorithm.

[0019] The present invention also provides a brake disc defect online detection system based on machine vision, comprising: an acquisition unit, a restoration unit, a positioning extraction unit and a defect detection unit;

[0020] Among them, the acquisition unit acquires a first image on the finished product conveying device through a first image acquisition device; the restoration unit restores the first image according to the conveying direction and conveying speed of the finished product conveying device to acquire a second image; the positioning and extraction unit performs positioning and extraction operations on the second image to obtain a regional image corresponding to the brake disc; the defect detection unit preprocesses the regional image and extracts defects, and outputs a first alarm message after the defects are extracted.

[0021] Preferably, the restoration unit performs restoration processing on the first image including:

[0022] According to the pixel sampling interval, conveying direction and conveying speed of the first image, a preset deviation parameter determination table is searched to retrieve the deviation parameter;

[0023] A restored and reconstructed image is constructed according to the starting pixel point and the pixel sampling order in the first image, and the pixels after the starting pixel point are resampled from the first image according to the deviation parameter to obtain the second image.

[0024] Preferably, the steps of the positioning extraction unit performing the positioning extraction operation on the second image are as follows:

[0025] Binarizing the first image and then extracting edges to obtain an edge-extracted image;

[0026] The minimum circumscribed circle fitting method is used to fit the edge extraction image, set the mask, extract the working surface, and obtain the regional image.

[0027] Preferably, the defect detection unit preprocesses the regional image including: median filtering image denoising and using Laplace operator for image enhancement.

[0028] Preferably, the defect extraction steps of the defect detection unit are as follows:

[0029] The OTSU algorithm is used to segment and extract defects, the improved Canny operator is used for scratch detection, the probabilistic Hough transform method is combined to connect scratches, and parallel processing is introduced to shorten the detection time of the improved Canny algorithm.

[0030] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0031] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0033] Figure 1 Schematic diagram of a brake disc defect online detection method based on machine vision in an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram of the working surface positioning in an embodiment of the present invention;

[0035] Figure 3 This is a schematic diagram of the Canny operator when extracting the working surface in an embodiment of the present invention;

[0036] Figure 4 Schematic diagram of linear interpolation of pixel gradient direction in an embodiment of the present invention;

[0037] Figure 5 It is a convolution template diagram in an embodiment of the present invention;

[0038] Figure 6 This is a flowchart of the Canny operator program for defect extraction and identification in an embodiment of the present invention;

[0039] Figure 7 Schematic diagram of a brake disc defect online detection system based on machine vision in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0041] The embodiment of the present invention provides a method for online detection of brake disc defects based on machine vision, such as Figure 1 As shown, including:

[0042] Step 1: Capture a first image on the finished product conveying device by a first image acquisition device;

[0043] Step 2: restore the first image according to the conveying direction and conveying speed of the finished product conveying device to obtain a second image;

[0044] Step 3: Perform a positioning extraction operation on the second image to obtain an area image corresponding to the brake disc;

[0045] Step 4: preprocess the regional image and extract defects, and output the first alarm information after the defects are extracted.

[0046] Among them, the first image acquisition device includes a gantry arranged above the conveyor belt of the finished product conveying device, a spherical integral light source arranged on the gantry, a camera arranged in the spherical integral light source, a control unit and a communication unit; the control unit is electrically connected to the spherical integral light source, the camera and the communication unit respectively; the control unit controls the opening and closing of the spherical integral light source, the control unit obtains the first image it collects through the camera, and sends the first image to the industrial big data platform through the communication unit. Since the present application is aimed at shooting and detecting the brake disc transmitted by the conveyor belt; during shooting, the brake disc on the conveyor belt is moving and distortion will occur; therefore, the distortion needs to be restored, therefore, the industrial big data platform restores the first image The processing steps include:

[0047] According to the pixel sampling interval, conveying direction and conveying speed of the first image, a preset deviation parameter determination table is queried to retrieve the deviation parameter; the pixel acquisition interval, conveying speed, conveying direction and deviation parameter in the deviation parameter determination table are correspondingly associated; the pixel sampling interval is the minimum value of the imaging time difference between two adjacent pixels in the first image, and the conveying speed is the distance moved by the object on the conveyor belt per unit time;

[0048] A restored and reconstructed image is constructed according to the starting pixel point and the pixel sampling order in the first image, and the pixels after the starting pixel point are resampled from the first image according to the deviation parameter to obtain the second image.

[0049] A deviation parameter determination table is used to determine the deviation parameters of pixels when the pixel sampling interval, the conveying direction and the conveying speed of the finished product conveying device are known. The deviation parameters include a lateral deviation value and a longitudinal deviation value. During resampling and reconstruction, the coordinates of the pixel points after the starting pixel point in the restored and reconstructed image are respectively added with the lateral deviation value and the longitudinal deviation value to obtain the extracted coordinates, and the pixel values ​​of the extracted coordinates in the first image are used as the values ​​of the pixel points in the restored and reconstructed image. In addition, it is also possible to determine whether there is an abnormality based on the deviation parameters. When the lateral deviation value in the deviation parameters is less than or equal to a preset first threshold value or the longitudinal deviation value is less than or equal to a preset second threshold value, it is determined that the camera setting is abnormal, and an alarm can be issued by a first alarm device set next to the first image acquisition device to remind the staff to make adjustments.

[0050] The steps of performing a positioning extraction operation on the second image are as follows:

[0051] Binarizing the first image and then extracting edges to obtain an edge-extracted image;

[0052] The minimum circumscribed circle fitting method is used to fit the edge extraction image, set the mask, extract the working surface, and obtain the regional image.

[0053] The brake disc is a regular circular shape. Through the illumination of a circular spherical integral light source, it is found that there is a significant difference in the grayscale value between the brake disc area and the non-brake disc area. Based on this, the edge detection and binarization algorithms can be used to locate the brake disc. However, when the edge detection algorithm is used to locate and extract the brake disc, the real-time recognition is not enough, and the pixels of different brake disc edge images are different. The threshold needs to be re-debugged, and a step of least squares fitting circle operation needs to be added, which invisibly increases the workload, so this method cannot meet actual needs. When the binarization algorithm is used to locate and extract the brake disc, it is found that this method can quickly and accurately extract the brake disc area based on the grayscale difference, so the binarization algorithm is used to locate and extract the brake disc.

[0054] The weighted average method is used to grayscale the brake disc. The formula is as follows:

[0055] Gray(i,j)=0.299R(i,j)+0.578G(i,j)+0.114B(i,j)

[0056] Among them, R(i,j), G(i,j), B(i,j) are the pixel values ​​of the red, green, and blue color channels respectively, and Gray(i,j) is the grayscale value.

[0057] Then use the threshold operator to binarize the image, traverse the brake disc contour, and use the maximum contour to intercept the brake disc area.

[0058] This application is mainly aimed at the scratch defects on the working surface of the brake disc. Accurately extracting the working surface can reduce the complexity of subsequent detection and improve the detection speed. The implementation process of working surface positioning is as follows Figure 2 shown.

[0059] The circle fitting algorithm based on the Canny operator is used to extract the working surface. The Canny operator is also called the optimal edge detection algorithm. It uses a double threshold method to determine the potential boundary, that is, setting an upper threshold and a lower threshold. The principle diagram of the Canny operator is as follows Figure 3 As shown,

[0060] Among them, enoising: The Gaussian kernel used in Gaussian filtering is a Gaussian function with two dimensions, x and y, and the standard deviation σ in the two dimensions is generally the same, in the form of:

[0061]

[0062] Gradient: Calculate the gradient magnitude and direction according to the Sobel operator to find the gradient of the image. The Sobel operator is two 3×3 matrices, S x and S y The former is used to calculate the pixel gradient matrix G in the x direction of the image x , which is used to calculate the pixel gradient matrix G in the y direction of the image y The specific form is:

[0063]

[0064] Where I is the grayscale image matrix, and the * here represents the cross-correlation operation. Then:

[0065]

[0066] The gradient strength matrix G can be calculated xy .

[0067] Non-maximum suppression: Compare the gradient strength of the current pixel with the gradient strength of the adjacent pixels along the positive and negative gradient directions. If it is the maximum (i.e., the extreme value), the pixel is retained as an edge point. If it is not the maximum, it is suppressed and not regarded as an edge point. For more accurate calculation, this paper uses linear interpolation between two adjacent pixels across the gradient direction to obtain the pixel gradient to be compared, such as Figure 4 As shown: The pixel adjacency can be divided into 4 regions, each of which contains two parts, the upper and lower parts. If the gradient strength in the x direction of the central pixel is g x (i,j), the gradient strength in the y direction is g y (i,j), the gradient strength is gxy (i,j), then according to g x (i,j) and g y The positive and negative and size of (i, j) can determine the area to which its gradient direction belongs, and then the two gradient intensities g involved in the comparison of the positive and negative gradient directions are obtained according to the linear interpolation of its pixel gradient direction and the pixel gradient of the adjacent points. up (i,j) and g down (i,j). The formula is as follows:

[0068] g up (i,j)=(1-t)·g xy (i,j+1)+t·g xy (i-1,j+1)

[0069] g down (i,j)=(1-t)·g xy (i,j-1)+t·g xy (i+1,j-1)

[0070] The calculation methods for the other three regions are similar. It should be noted that if g x (i,j)=g y (i, j) = 0, indicating that the pixel has no pixel gradient and is not an edge.

[0071] Hysteresis threshold: define a high threshold and a low threshold. Pixels with gradient strength lower than the low threshold are suppressed and not considered as edge points; pixels with gradient strength higher than the high threshold are defined as strong edges and retained as edge points; pixels between the high and low thresholds are defined as weak edges and reserved for further processing. Afterwards, due to uneven illumination and interference problems that cannot be solved by preprocessing of the extracted grayscale image itself, an accurate circle fitting algorithm helps to separate the working area from the non-working area. At present, random Hough transform circle detection, least squares circle fitting, random sampling consistent circle fitting, and minimum circumscribed circle fitting are all commonly used circle fitting methods. Since there are fewer free interfering pixels on the edge of the disk after threshold segmentation, this application uses the minimum circumscribed circle fitting method to perform circle fitting on the threshold segmented image, set a mask, and thus extract the working surface.

[0072] The minimum circumscribed circle fitting uses the Welzl algorithm, which is a recursive randomized algorithm. The specific steps of the algorithm are as follows: Assume that there is a set of points {P1, P2, …, P n}, where P i =(x i ,y i ) represents a point on the plane. The center of the smallest circumscribed circle (x c ,y c ), with radius R. Then:

[0073]

[0074] The minimum circumscribed circle can be regarded as the smallest circle that encloses a given set of points, so that all points in the point set are inside or on the circle. The algorithm eventually finds the minimum circumscribed circle of the point set and returns the center and radius. It then selects the required circle based on the radius, sets the mask area, and locates and extracts the working surface of the brake disc.

[0075] The preprocessing of the regional image includes: median filtering image denoising and using Laplace operator for image enhancement.

[0076] The defect extraction steps are as follows:

[0077] The OTSU algorithm is used to segment and extract defects, the improved Canny operator is used for scratch detection, the probabilistic Hough transform method is combined to connect scratches, and parallel processing is introduced to shorten the detection time of the improved Canny algorithm.

[0078] When collecting brake disc images, the surrounding environment and the camera itself will inevitably cause noise interference to the image, so the image needs to be denoised. The median filter algorithm has a better effect, so it is selected; due to uneven lighting, the inner ring of the denoised image is brighter, so in order to make the scratches clearer, image enhancement processing is also required;

[0079] The Laplace operator can highlight scratches very well. It can be seen that no matter what color the scratches are, they will appear prominently white after being processed by the Laplace operator, which is beneficial for subsequent scratch extraction. Therefore, the Laplace operator is selected for image enhancement.

[0080] The Laplace operator is defined as:

[0081]

[0082] In the x-direction:

[0083]

[0084] In the y direction:

[0085]

[0086] So, the difference of the Laplace operator is approximately:

[0087]

[0088] This application uses Figure 5 Convolution is performed on the convolution template.

[0089] The center coefficient of the template is negative, and the image after Laplace transformation needs to be subtracted from the original image to obtain a sharpening effect. Therefore, the basic method of Laplace image enhancement is:

[0090]

[0091] Where f(x,y) is the input image, g(x,y) is the sharpened image, and c=-1.

[0092] Due to uneven lighting, brake disc surface texture or environmental dust, the segmented image contains not only scratch features, but also other noise and interference, which makes it more difficult to extract scratches. Therefore, it is necessary to segment the scratch area from the complex background. Otsu's method (OTSU) can extract scratches better and suppress the surrounding texture as much as possible, so the scratch extraction algorithm uses OTSU.

[0093] The scratches segmented by OTSU are broken, which affects the correctness of the scratch size and number. Therefore, it is necessary to connect the broken scratches. Morphological operations can be used to connect the broken scratches. On the basis of opening operations, it is proposed to use the improved Canny operator for scratch detection, combined with the probabilistic Hough transform method to connect the scratches, and introduce parallel processing to shorten the detection time of the improved Canny algorithm.

[0094] Among them, the Canny operator is improved. The basic steps of the Canny edge detection operator are: first use a Gaussian filter to smooth the image; then use the finite difference of the first-order partial derivative to calculate the amplitude and direction of the gradient; then perform non-maximum suppression on the gradient amplitude; finally use a double threshold algorithm to detect and connect edges. In the traditional Canny operator, a hysteresis threshold connection is used to connect strong edge pixels with adjacent weak edge pixels to form a continuous edge line. The implementation process is as follows Figure 6 shown.

[0095] However, using only forward connections may result in incomplete connections of some edge lines. Therefore, this paper introduces an improvement in bidirectional connections in the Canny operator. In bidirectional connections, we first start from the strong edge pixels and connect to the adjacent weak edge pixels along the edge direction and mark them as strong edge pixels. Then, we continue to connect from the new strong edge pixels in the opposite direction to further enhance the continuity of the edge line. In this way, weak edge pixels can be connected from two directions to form a complete edge line, which improves the accuracy of Canny edge detection and reduces false positives.

[0096] Specifically: G x and G y are the gradients of image I in the horizontal and vertical directions respectively. The Sobel operator is used for gradient calculation, which can be expressed as follows:x =Sobel x (I); G y =Sobel y (I). The magnitude M and direction D of the gradient can be calculated by the following formula:

[0097]

[0098] D = arctan2(G y ,G x )

[0099] The gradient is calculated as M, D = calculate_gradient(I), and then non-maximum suppression is performed: S = non_max_suppression(M, D). The gradient strength of the current pixel is compared with the gradient strength of the adjacent pixels along the positive and negative gradient directions. If it is the maximum (that is, the extreme value), the pixel is retained as an edge point. If it is not the maximum, it is suppressed and not regarded as an edge point. Then a high threshold and a low threshold are defined for double threshold processing, strong_threshold = max(S) × threshold2; weak_threshold = strong_threshold × threshold1, and the pixels with gradient strength lower than the low threshold are suppressed; the pixels with gradient strength higher than the high threshold are defined as strong edges and retained as edge points. Finally, a bidirectional connection is implemented, edges[strong_i, strong_j] = 255. If a weak edge pixel is adjacent to a strong edge pixel in its 3x3 neighborhood, it is promoted to a strong edge. The coordinates of these newly marked strong edge pixels are added to strong_i and strong_j. edges[weak_i, weak_j] = 100, if a weak edge pixel is adjacent to a pixel marked as 100 in its 3x3 neighborhood, it is marked as 100, which represents the reverse connection, ensuring connectivity in the opposite direction. Bidirectional connection improves the continuity of the detected edges by considering both directions, and this method makes the algorithm more robust to edge interruptions or gaps. In addition, Canny edge detection involves computationally intensive tasks such as gradient calculation and non-maximum suppression. Use ThreadPoolExecutor to execute calculate_gradient and non_max_suppression in parallel. Parallel processing aims to speed up the entire process by executing these tasks in parallel, and makes full use of multi-core architecture to effectively utilize available resources.

[0100] The improved Canny operator is compared with the directly called Canny operator to quantitatively evaluate the accuracy, recall rate and F1-Score indicators of edge detection.

[0101] Precision:

[0102] Precision=TP / (TP+FP)

[0103] Recall:

[0104] Recall=TP / (TP+FN)

[0105] F1-score: The harmonic mean of precision and recall.

[0106] F1-score=2*(Precision*Recall) / (Precision+Recall)

[0107] Among them, TP is the number of pixels detected as edges and correct; FP is the number of pixels detected as edges but actually are not edges; TN is the number of pixels detected as non-edges and correct; FN is the number of pixels detected as non-edges but actually are edges.

[0108] The improved Canny has achieved positive results in the three evaluation indicators of precision, recall rate and F1-score. On average, the three indicators have been improved by 3.2%, 13.2% and 6.0% respectively after the improvement. Specifically: the precision has been improved by 1% to 6%. The recall rate has been significantly improved by 12% to 16%. The F1-score has been improved by 4% to 10%. These improvements reflect that the optimization of the algorithm has achieved good results in improving accuracy and comprehensiveness, especially the improvement in recall rate is the most significant, indicating that the improved algorithm has captured the information of scratches more comprehensively and effectively, and reduced missed detections. Such an improvement is of practical significance for the application of scratch detection, and can more reliably identify scratches, providing a more reliable foundation for further applications.

[0109] Probabilistic Hough transform. Although the standard Hough transform can accurately detect straight lines in an image, it needs to traverse the entire parameter space and accumulate at each point, which leads to high computational complexity. Therefore, a new Hough transform, namely the probabilistic Hough transform, is used. If the feature point in the original image is

[0110] D={d i ={x,y i}|i=1,2,…}

[0111] Randomly select a pair of feature points (d i ,d j ), where d i =(x i,y i ), d j =(x j ,y j ), so the parameters (a, b) can be obtained by the following formula.

[0112]

[0113] The array H(a,b) is accumulated continuously according to the obtained results. When the calculation continues until a certain array exceeds a specified maximum value, the largest H(a,b) array is the detected straight line.

[0114] By proposing an improved Canny edge detection algorithm, introducing bidirectional connection, and combining the probabilistic Hough transform method to connect scratches, it can better handle complex images and broken edges, improve the accuracy and stability of scratch connection, and suppress the interference of the brake disc surface's own texture.

[0115] In addition, this paper introduces parallel processing based on the improvement of the Canny operator, parallel calculation of gradients and non-maximum suppression, and by using thread pool parallel calculation, it can fully utilize the performance of multi-core processors and speed up the algorithm execution efficiency. It can better connect broken scratches and suppress interference from other information.

[0116] In one embodiment, the camera of the first image acquisition device is arranged on the lower end surface of the rotating platform, and the rotating platform can drive the camera to rotate in a horizontal plane with the central axis of the camera as the rotation axis;

[0117] The previous embodiment uses a deviation parameter determination table to determine the deviation parameters of pixels when the pixel sampling interval, the conveying direction and the conveying speed of the finished product conveying device are known. The analysis is performed through three known parameters. By reducing the number of known parameters used for analysis, the error in the known parameter determination can be reduced, and the accuracy of the restored image can be further improved. Therefore, the present embodiment uses a rotating platform to rotate and adjust the camera to ensure that the horizontal scanning direction is perpendicular to the conveying direction of the finished product conveying device during image acquisition. The deviation parameters can be determined by a second deviation parameter determination table. The pixel sampling interval, the conveying speed and the deviation parameters in the second deviation parameter determination table are correspondingly associated;

[0118] In order to realize automatic calibration of the camera position, a standard object is conveyed on the finished product conveying device. The camera collects images of the standard object multiple times at each rotation position as the rotating platform rotates, and measures the length of the object image in the longitudinal scanning direction of the collected image; the camera is rotationally adjusted with the rotation position with the largest measured value as the target position after automatic adjustment.

[0119] In one embodiment, a second image acquisition device is also provided next to the finished product conveying device, and the second image acquisition device includes: a detection platform, a spherical integral light source provided above the detection platform, a camera provided in the spherical integral light source, a control unit, and a communication unit; a finished product pushing device (a grabbing robot may also be provided) is provided on the other side of the finished product conveying device to push the brake disc from the finished product conveying device to the detection platform, and the second image acquisition device performs random sampling from the finished product conveying device, and adopts a static measurement method. The second image acquired by the second image acquisition device can be used to check whether the longitudinal scanning direction of the camera of the first image acquisition device is parallel to the conveying direction of the finished product conveying device. Specifically, it is to detect whether the deviation between the length of the first image in the longitudinal scanning direction after restoration and the length corresponding to the second image is within the preset deviation range. If not, a prompt indicating that the first image acquisition device needs to be calibrated is output.

[0120] The present invention also provides a brake disc defect online detection system based on machine vision, such as Figure 7 As shown, it includes: an acquisition unit 1, a restoration unit 2, a positioning extraction unit 3 and a defect detection unit 4;

[0121] Among them, the acquisition unit 1 acquires a first image on the finished product conveying device through a first image acquisition device; the restoration unit 2 restores the first image according to the conveying direction and conveying speed of the finished product conveying device to acquire a second image; the positioning and extraction unit 3 performs positioning and extraction operations on the second image to obtain a regional image corresponding to the brake disc; the defect detection unit 4 pre-processes the regional image and extracts defects, and outputs a first alarm message after the defects are extracted.

[0122] The restoration unit 2 performs restoration processing on the first image, including:

[0123] According to the pixel sampling interval, conveying direction and conveying speed of the first image, a preset deviation parameter determination table is searched to retrieve the deviation parameter;

[0124] A restored and reconstructed image is constructed according to the starting pixel point and the pixel sampling order in the first image, and the pixels after the starting pixel point are resampled from the first image according to the deviation parameter to obtain the second image.

[0125] The steps of the positioning extraction unit 3 performing the positioning extraction operation on the second image are as follows:

[0126] Binarizing the first image and then extracting edges to obtain an edge-extracted image;

[0127] The minimum circumscribed circle fitting method is used to fit the edge extraction image, set the mask, extract the working surface, and obtain the regional image.

[0128] The defect detection unit 4 performs preprocessing on the regional image, including: median filtering image denoising and using the Laplace operator for image enhancement.

[0129] Among them, the defect extraction steps of the defect detection unit 4 are as follows:

[0130] The OTSU algorithm is used to segment and extract defects, the improved Canny operator is used for scratch detection, the probabilistic Hough transform method is combined to connect scratches, and parallel processing is introduced to shorten the detection time of the improved Canny algorithm.

[0131] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A brake disc defect online detection method based on machine vision, characterized in that: include: Capturing a first image on the finished product conveying device by a first image acquisition device; According to the conveying direction and conveying speed of the finished product conveying device, the first image is restored to obtain a second image; Performing a positioning extraction operation on the second image to obtain an area image corresponding to the brake disc; The regional image is preprocessed and defects are extracted, and the first alarm information is output after the defects are extracted.

2. The online detection method for brake disc defects based on machine vision according to claim 1 is characterized in that: The step of restoring the first image includes: According to the pixel sampling interval, conveying direction and conveying speed of the first image, a preset deviation parameter determination table is searched to retrieve the deviation parameter; A restored and reconstructed image is constructed according to the starting pixel point and the pixel sampling order in the first image, and the pixels after the starting pixel point are resampled from the first image according to the deviation parameter to obtain the second image.

3. The online detection method for brake disc defects based on machine vision according to claim 1 is characterized in that: The steps of performing the positioning extraction operation on the second image are as follows: Binarizing the first image and then extracting edges to obtain an edge-extracted image; The minimum circumscribed circle fitting method is used to fit the edge extraction image, set the mask, extract the working surface, and obtain the regional image.

4. The online detection method for brake disc defects based on machine vision according to claim 1 is characterized in that: The preprocessing of the regional image includes: median filtering image denoising and Laplacian operator image enhancement.

5. The online detection method for brake disc defects based on machine vision according to claim 1 is characterized in that: The defect extraction steps are as follows: The OTSU algorithm is used to segment and extract defects, the improved Canny operator is used for scratch detection, the probabilistic Hough transform method is combined to connect scratches, and parallel processing is introduced to shorten the detection time of the improved Canny algorithm.

6. A brake disc defect online detection system based on machine vision, characterized in that: include: Acquisition unit, restoration unit, positioning extraction unit and defect detection unit; Wherein, the acquisition unit acquires a first image on the finished product conveying device through a first image acquisition device; The restoration unit restores the first image according to the conveying direction and conveying speed of the finished product conveying device to obtain the second image; the positioning and extraction unit performs positioning and extraction operations on the second image to obtain the area image corresponding to the brake disc; the defect detection unit preprocesses the area image and extracts defects, and outputs the first alarm information after the defects are extracted.

7. The machine vision-based brake disc defect online detection system according to claim 6, characterized in that: The restoration unit performs restoration processing on the first image, including: According to the pixel sampling interval, conveying direction and conveying speed of the first image, a preset deviation parameter determination table is searched to retrieve the deviation parameter; A restored and reconstructed image is constructed according to the starting pixel point and the pixel sampling order in the first image, and the pixels after the starting pixel point are resampled from the first image according to the deviation parameter to obtain the second image.

8. The machine vision-based brake disc defect online detection system according to claim 6, characterized in that: The steps of the positioning extraction unit performing a positioning extraction operation on the second image are as follows: Binarizing the first image and then extracting edges to obtain an edge-extracted image; The minimum circumscribed circle fitting method is used to fit the edge extraction image, set the mask, extract the working surface, and obtain the regional image.

9. The machine vision-based brake disc defect online detection system according to claim 6, characterized in that: The defect detection unit performs preprocessing on the regional image including: median filtering image denoising and using Laplace operator for image enhancement.

10. The machine vision-based brake disc defect online detection system according to claim 6, characterized in that: The defect extraction steps of the defect detection unit are as follows: The OTSU algorithm is used to segment and extract defects, the improved Canny operator is used for scratch detection, the probabilistic Hough transform method is combined to connect scratches, and parallel processing is introduced to shorten the detection time of the improved Canny algorithm.

Images