Vision Intelligent Detection Method for Laser Seeker Based on Computer Vision

Abstract

This application relates to the field of image processing technology, specifically to a visual intelligent detection method for a laser seeker based on computer vision. The method includes: obtaining a grayscale image of the laser seeker; determining the side length of the light spot detection window for each pixel point; determining the suspected light spot index for each pixel point based on the degree of chaos of the gray values of all pixel points in the light spot detection window of each pixel point, and the difference between the gray value of each pixel point and the gray values of all pixel points in its light spot detection window, and combining the suspected light spot index to determine the light spot certainty index for each pixel point to detect the laser seeker. This application sets an adaptive light spot detection window for each pixel point, and combines the light spot certainty index to exclude the interference of light spots on the detection of the laser seeker, improving the accuracy of the detection of the laser seeker.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and particularly to a visual intelligent detection method for a laser seeker based on computer vision. Background Art

[0002] As an accurate guidance method, laser guidance has been widely applied in actual combat. The laser seeker processes the laser signals obtained on the detector to acquire the position information of the target. Therefore, the optical imaging performance of the seeker will directly affect the ability of the laser seeker to track the target.

[0003] As one of the important components of the laser seeker, the radome is located at the forefront of the seeker and plays a role in protecting the internal components from external environmental erosion and rectification. During the optical processing, due to reasons such as equipment and technology, there will be fine defects such as scratches and pockmarks on the surface of the radome. At present, when using computer vision algorithms to detect the defects of the radome of the laser seeker, the light spots formed by the reflection on the surface of the radome will seriously interfere with the capture of fine defects in the image, resulting in a decrease in the defect detection accuracy of the radome. Therefore, how to reduce the influence of the reflection light spots on the surface of the radome of the laser seeker on the detection and improve the detection accuracy of fine defects is an urgent problem to be solved at present. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides a visual intelligent detection method for a laser seeker based on computer vision to solve the existing problems.

[0005] The visual intelligent detection method for a laser seeker based on computer vision of this application adopts the following technical solutions:

[0006] An embodiment of this application provides a visual intelligent detection method for a laser seeker based on computer vision, and this method includes the following steps:

[0007] Obtain grayscale images of the laser seeker at different light source angles;

[0008] Determine the side length of the light spot detection window for each pixel point according to the distribution of the grayscale values of each pixel point in the grayscale image of the laser seeker;

[0009] Determine the suspected light spot index for each pixel point according to the degree of chaos of the grayscale values of all pixel points in the light spot detection window of each pixel point, and the difference between the grayscale value of each pixel point and the grayscale values of all pixel points in its light spot detection window;

[0010] Based on the side length of the light spot detection window of each pixel point and the distribution of all pixel points around the central pixel point inside it, combine the suspected light spot index to determine the light spot confidence index for each pixel point, so as to detect the laser seeker.

[0011] Preferably, the expression for the side length of the light spot detection window of each pixel is: ; in the formula, represents the side length of the light spot detection window of the i-th pixel in the gray-scale image of the laser seeker; represents the gray value of the i-th pixel in the gray-scale image of the laser seeker; and respectively represent the preset reference window side length and the preset minimum window side length; ceil( ) represents the ceiling function; norm( ) represents the normalization function.

[0012] Preferably, the determination process of the suspected light spot index of each pixel is as follows:

[0013] Determine the chaos degree of each pixel according to the chaos degree of all pixel gray values in the light spot detection window of each pixel;

[0014] Determine the suspected light spot degree of each pixel according to the difference between the gray value of each pixel and the gray values of all pixels in its light spot detection window;

[0015] Based on the chaos degree and the suspected light spot degree, determine the suspected light spot index of each pixel.

[0016] Preferably, the chaos degree of each pixel is the image entropy of the light spot detection window where each pixel is located.

[0017] Preferably, the suspected light spot degree of each pixel is the ratio of the gray value of each pixel to the minimum gray value of all pixels in its light spot detection window.

[0018] Preferably, the suspected light spot index of each pixel is the product of the chaos degree and the suspected light spot of each pixel.

[0019] Preferably, the determination process of the light spot certainty index of each pixel is as follows:

[0020] Based on the side length of the light spot detection window of each pixel and the distribution of all pixels around the central pixel inside it, determine the light spot area ratio of each pixel;

[0021] Based on the light spot area ratio and the suspected light spot index, determine the light spot certainty index of each pixel.

[0022] Preferably, the determination process of the light spot area ratio of each pixel is as follows:

[0023] Cluster all pixels in the light spot detection window of each pixel to obtain multiple clustering clusters;

[0024] The spot area ratio of each pixel is the ratio of the number of all pixels in the cluster where the central pixel is located within the spot detection window of each pixel to the square of the side length of the spot detection window.

[0025] Preferably, the spot confidence index of each pixel is the product of the suspected spot index of each pixel and the spot area.

[0026] Preferably, the detection of the laser seeker includes:

[0027] Taking the spot confidence indices of all pixels in the laser seeker grayscale image as the input of the threshold segmentation algorithm to obtain the segmentation threshold;

[0028] Marking the pixels in the laser seeker grayscale image whose spot confidence indices are less than or equal to the segmentation threshold as valid pixels;

[0029] Taking the mean value of the grayscale values of all valid pixels in the spot detection window of each pixel as the fusion weight of each pixel;

[0030] The grayscale value of each pixel in the optimized grayscale image of the laser seeker is the sum of the products of the grayscale values of the pixels at the same positions in all laser seeker grayscale images and the fusion weights;

[0031] Using the U²-Net neural network model to perform defect detection on the optimized grayscale image of the laser seeker.

[0032] This application has at least the following beneficial effects:

[0033] This application determines the side length of the spot detection window of each pixel according to the distribution of the grayscale values of each pixel in the laser seeker grayscale image, avoiding misjudging subsequent defects as spots for segmentation; determines the suspected spot index of each pixel according to the degree of chaos of the grayscale values of all pixels in the spot detection window of each pixel and the difference between the grayscale value of each pixel and the grayscale values of all pixels in its spot detection window; determines the spot confidence index of each pixel based on the side length of the spot detection window of each pixel and the distribution of all pixels around the central pixel therein, in combination with the suspected spot index; to enhance the distinguishability between spot pixels and other pixels and improve the accuracy of the spot segmentation on the fairing surface. This application sets an adaptive spot detection window for each pixel, combines the spot confidence index to exclude the interference of spots on the laser seeker detection, and improves the accuracy of the laser seeker detection. Description of the Drawings

[0034] To more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0035] Figure 1 It is a flowchart of the steps of a vision intelligent detection method for a laser seeker based on computer vision;

[0036] Figure 2 It is a schematic diagram for extracting the spot confidence index;

[0037] Figure 3 It is a flowchart of the laser seeker defect recognition process;

[0038] Figure 4 It is a schematic diagram of the laser seeker defect intelligent detection process. Detailed implementation manners

[0039] In order to further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of the vision intelligent detection method for a laser seeker based on computer vision proposed according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0041] The following specifically describes the specific solution of the vision intelligent detection method for a laser seeker based on computer vision provided by the present application in combination with the accompanying drawings.

[0042] A vision intelligent detection method for a laser seeker based on computer vision provided by an embodiment of the present application. Specifically, the following vision intelligent detection method for a laser seeker based on computer vision is provided. Please refer to Figure 1 This method includes the following steps:

[0043] Step S1: Use an industrial CCD camera to take pictures of the laser seeker fairing, and perform denoising processing on the captured grayscale images. By adjusting the angle of the annular light source, obtain the grayscale images of the laser seeker under different angles of illumination.

[0044] Irradiate the fairing of the laser seeker with a ring light source, and use an industrial CCD camera to take a grayscale image with a resolution of Q*H. In order to eliminate the influence of noise during the shooting process and enhance the accuracy of subsequent analysis, a filtering algorithm is used to denoise the taken grayscale image, and the denoised grayscale image is denoted as the grayscale image of the laser seeker. By adjusting the irradiation angle of the ring light source, the position of the light spot in each image is changed, and grayscale images of the laser seeker under a preset number of different light source angles are obtained.

[0045] It should be noted that the values of Q, H, the preset number, and the light source angle are set artificially. In this embodiment, Q and H are respectively set to 3088 and 2064, the preset number is set to 4, and the irradiation angles of the ring light source are respectively selected as 30°, 45°, 60°, and 90°. The implementer can set and adjust according to the actual situation, and this embodiment does not make special restrictions.

[0046] It should be understood that there are many common filtering algorithms. In this embodiment, the Gaussian filtering algorithm is used to denoise the grayscale image of the laser seeker. The implementer can also use filtering algorithms such as median filtering or bilateral filtering to denoise the grayscale image of the laser seeker, and this embodiment does not make special restrictions.

[0047] Step S2: Determine the side length of the light spot detection window for each pixel point according to the distribution of the grayscale values of each pixel point in the grayscale image of the laser seeker.

[0048] As a key component of the laser seeker, the fairing has a great influence on the laser signal obtained by the laser seeker. During the optical processing, due to reasons such as equipment and technology, fine defects such as scratches and pits will appear on the surface of the fairing, resulting in optical errors when the laser seeker images, affecting the quality of the optical imaging of the laser seeker and the accuracy of target detection. Compared with other optical defects, the scratches and pits on the surface of the fairing have a small existence range and are randomly distributed. At the same time, the light spots generated by the light reflection on the surface of the fairing have grayscale values in the image close to those of the defects. When the light spots coincide with the fine defects on the surface, it will seriously interfere with the detection of surface defects, resulting in a decrease in detection accuracy and missed detection of some fine defects.

[0049] In order to reduce the influence of the light spots on the surface of the fairing on defect detection, it is necessary to segment the light spots in the grayscale image of the laser seeker. Since the range of change in the grayscale values of the pixel points at the edge of the light spot in the image is large, if the entire image is directly segmented, it is difficult to obtain a good segmentation effect at the edge of the light spot, thereby affecting the subsequent defect detection at the edge of the light spot.

[0050] Therefore, a window with a size of r×r is established centered on each pixel of the gray-scale image of the laser seeker, and it is denoted as the spot detection window for each pixel, where r is the side length of the spot detection window for each pixel.

[0051] Determine the side length of the spot detection window for each pixel according to the distribution of the gray-scale values of each pixel in the gray-scale image of the laser seeker. The expression for the side length of the spot detection window for each pixel is: ; in the formula, represents the side length of the spot detection window for the i-th pixel in the gray-scale image of the laser seeker; represents the gray-scale value of the i-th pixel in the gray-scale image of the laser seeker; and respectively represent the preset reference window side length and the preset minimum window side length; ceil( ) represents the ceiling function; norm( ) represents the normalization function. and respectively represent the preset reference window side length and the preset minimum window side length. In the present invention, takes a value of 200, takes a value of 10.

[0052] It should be noted that the values of the preset reference window side length and the preset minimum window side length are set artificially. In this embodiment, the preset reference window side length takes a value of 200, and the preset minimum window side length takes a value of 10. The implementer can set them according to specific situations by himself / herself, and this embodiment does not make special restrictions.

[0053] The larger the gray-scale value of the pixel in the gray-scale image of the laser seeker, the larger the side length of its spot detection window. On the one hand, the gray-scale value at the center of the spot is the highest. By using a larger spot detection window, the situation where only spot pixels are included in the window is avoided; at the same time, a smaller spot detection window is used for the normal pixels near the spot, reducing the excessive expansion of the subsequent spot segmentation area. On the other hand, the gray-scale values of defects such as scratches and pockmarks are relatively high. By using a larger spot detection window, the proportion of scratches, pockmarks and other defects in the window is reduced, increasing the distinguishability between scratches, pockmarks and other defects and spot pixels, and avoiding misjudging defects as spots for subsequent segmentation.

[0054] Step S3: Determine the suspected spot index for each pixel according to the degree of chaos of the gray-scale values of all pixels in the spot detection window of each pixel and the difference between the gray-scale value of each pixel and the gray-scale values of all pixels in its spot detection window.

[0055] The gray values of the pixel points where defects such as pitting and scratches are located are relatively high, and the corresponding light spot detection windows are relatively large. However, due to the small defect area, the proportion in the window is not large, and the degree of chaos in the gray value distribution within the window is small. The gray value of the pixel point where the light spot is located is relatively high, and the corresponding light spot detection window is relatively large. However, the area of the light spot is large and the range of gray value changes at the light spot is large, corresponding to a large degree of chaos in the gray value distribution within its window.

[0056] The gray values of the normal pixel points on the surface of the laser seeker fairing are relatively low, and the light spot detection windows are relatively small. When the distance between the normal pixel point and the light spot on the fairing surface is far, only the nearby normal pixel points are included in its light spot detection window, and the gray value distribution is uniform. When the normal pixel point approaches the light spot, light spot pixel points will appear in the corresponding light spot detection window, resulting in an increase in the degree of chaos in the gray value distribution of the pixel points in the light spot detection window. Moreover, the farther the normal pixel point is from the light spot, the smaller the degree of chaos in the gray value distribution of the pixel points in the light spot detection window.

[0057] Therefore, according to the degree of chaos of all pixel points' gray values in the light spot detection window of each pixel point, and the difference between the gray value of each pixel point and the gray values of all pixel points in its light spot detection window, a suspected light spot index of each pixel point is constructed to exclude the influence of light spot pixel points on the detection of defects such as pitting and scratches. Specifically:

[0058] Analyze the image entropy of the image in the light spot detection window where each pixel point is located, denoted as the chaos degree of each pixel point;

[0059] Determine the ratio of the gray value of each pixel point to the minimum gray value of all pixel points in its light spot detection window, denoted as the suspected light spot degree of each pixel point;

[0060] Based on the chaos degree and the suspected light spot degree, determine the suspected light spot index of each pixel point. The suspected light spot index of each pixel point is the product of the chaos degree and the suspected light spot degree of each pixel point.

[0061] It should be noted that the calculation process of image entropy is a well-known technology, and the specific calculation process will not be elaborated here.

[0062] The gray values of the defects on the surface of the laser seeker fairing and the pixel points at the light spot are relatively high, and the ratios to the minimum gray values in their respective light spot detection windows are relatively large; while the gray values of the normal pixel points are relatively low, and the ratios to the minimum gray values in their light spot detection windows are relatively small, and the calculated suspected light spot indexes are relatively small. In addition, when the degree of chaos in the pixel point distribution of the light spot detection window is greater, the image entropy of the image in the light spot detection window where each pixel point is located is greater, and the calculated suspected light spot index of the central pixel point is greater. Therefore, the suspected light spot index of the pixel points at the light spot is greater than the suspected light spot indexes of the defects on the laser seeker surface and the pixel points at the normal positions.

[0063] Step S4: Based on the side length of the light spot detection window of each pixel and the distribution of all the pixels around the central pixel within it, and in combination with the suspected light spot index, determine the light spot confidence index of each pixel.

[0064] When the surface defect of the laser seeker is relatively close to the light spot, the difference between the suspected light spot index of the defective pixel and the window gray value of the light spot pixel in the optimized gray map of the laser seeker is small. In the subsequent image segmentation process, it is easy to mis-segment the defective pixels close to the light spot, reducing the detection accuracy of the surface defects of the laser seeker. However, the areas of the surface pockmarks, scratches, etc. on the laser seeker fairing are small, and the difference from the area of the light spot is large.

[0065] To further improve the accuracy of light spot segmentation on the fairing surface, all the pixels in the light spot detection window of each pixel are used as the input of the clustering algorithm to obtain multiple clustering clusters.

[0066] It should be understood that there are many common clustering algorithms. In this embodiment, the DBSCAN algorithm is used to cluster all the pixels in the light spot detection window of each pixel. Among them, the neighborhood radius of the DBSCAN algorithm is set to a, and the number of clustering clusters is set to m. The values of the neighborhood radius and the number of clustering clusters are both set artificially. In this embodiment, the value of a is 2, and the value of m is 10. Implementers can use other algorithms such as the k-means clustering algorithm according to specific circumstances, or can also set the values of the neighborhood radius and the number of clustering clusters by themselves according to specific circumstances. This embodiment does not make special restrictions.

[0067] Among them, the DBSCAN algorithm is a well-known technology, and the specific process of its clustering will not be elaborated here.

[0068] Further, based on the side length of the light spot detection window of each pixel and the distribution of all the pixels around the central pixel within it, and in combination with the suspected light spot index, determine the light spot confidence index of each pixel, specifically as follows:

[0069] Analyze that the light spot area ratio of each pixel is the ratio of the number of all the pixels in the clustering cluster where the central pixel in the light spot detection window of each pixel is located to the square of the side length of the light spot detection window, denoted as the light spot area ratio of each pixel;

[0070] Based on the light spot area ratio and the suspected light spot index, determine the light spot confidence index of each pixel. The light spot confidence index of each pixel is the product of the suspected light spot index of each pixel and the light spot area ratio.

[0071] Compared with the normal pixel points and defective pixel points of the gray-scale image of the laser seeker, the suspected spot index at the spot on the surface of the laser seeker is relatively large, and the calculated spot confidence index is relatively large. In addition, at the defective parts such as pockmarks and scratches on the surface of the fairing, the ratio of the clustering cluster where the central pixel point in the spot detection window is located to the window is relatively small, while the ratio at the spot is relatively large. Therefore, the spot confidence index of the pixel points at the spot is significantly greater than that of the normal pixel points and defective pixel points.

[0072] Preferably, as an embodiment of the present application, the schematic diagram for extracting the spot confidence index is as Figure 2 shown.

[0073] Step S5: Detect the laser seeker based on the spot confidence index of each pixel point.

[0074] (1) Take the spot confidence indices of all pixel points in the gray-scale image of the laser seeker as the input, and calculate the segmentation threshold by using the maximum inter-class variance method.

[0075] (2) Denote the pixel points in the gray-scale image of the laser seeker whose spot confidence index is greater than the segmentation threshold as spot pixel points, representing the pixel points interfered by the spot on the surface of the fairing; denote the pixel points whose spot confidence index does not exceed the segmentation threshold as valid pixel points, representing the pixel points not interfered by the spot.

[0076] (3) Further, obtain the gray-scale images of the laser seeker in a preset number for the same laser seeker. For the pixel points at the same position in the preset number of gray-scale images of the laser seeker, count the number of valid pixel points in the spot detection window of each pixel point, and take the mean value of the gray-scale values of all valid pixel points in the spot detection window of each pixel point as the fusion weight of each pixel point.

[0077] (4) The gray-scale value of each pixel point in the optimized gray-scale image of the laser seeker is the cumulative sum of the products of the gray-scale values of the pixel points at the same positions in all gray-scale images of the laser seeker and the fusion weights.

[0078] (5) Send the optimized gray-scale image of the laser seeker into the pre-trained U²-Net network that can identify defects such as pockmarks and scratches. Among them, the loss function uses the binary cross-entropy loss function, and the optimizer in the network structure uses the Adam optimizer, and output the laser seeker defect segmentation image containing defect labels such as pockmarks and scratches.

[0079] (6) When defects such as pockmarks and scratches appear in the laser seeker defect segmentation image, the corresponding laser seeker fairing is determined to be unqualified; when no defects appear in the laser seeker defect segmentation image, the corresponding laser seeker fairing is determined to be qualified, and the visual intelligent detection of the laser seeker is completed.

[0080] Preferably, as an embodiment of the present application, the flowchart of the laser seeker defect recognition process is as follows Figure 3 shown.

[0081] It should be noted that the U²-Net network and the binary cross-entropy loss function are both well-known technologies, and their specific contents and operation processes will not be elaborated herein.

[0082] Preferably, as an embodiment of the present application, the schematic diagram of the laser seeker defect intelligent detection process is as follows Figure 4 shown.

[0083] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] Each embodiment in this specification is described in a progressive manner. For the same or similar parts between each embodiment, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0085] The above-described embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; any modification to the technical solutions recorded in the foregoing embodiments, or any equivalent replacement of some of the technical features, does not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of each embodiment of the present application, and should all be included within the protection scope of the present application.

Claims

1. A vision intelligent detection method for a laser seeker based on computer vision, characterized in that, The method includes the following steps: Obtain the grayscale images of the laser seeker at different light source angles; Determine the side length of the spot detection window for each pixel point according to the distribution of the grayscale values of each pixel point in the grayscale image of the laser seeker; Determine the chaos degree of each pixel point according to the chaos degree of all pixel points in the spot detection window of each pixel point; determine the suspected spot degree of each pixel point according to the difference between the grayscale value of each pixel point and the grayscale values of all pixel points in its spot detection window; determine the suspected spot index of each pixel point based on the chaos degree and the suspected spot degree; Determine the spot area ratio of each pixel point based on the side length of the spot detection window of each pixel point and the distribution of all pixel points around the central pixel point inside it; determine the spot confidence index of each pixel point based on the spot area ratio and the suspected spot index, use the spot confidence indices of all pixel points in the grayscale image of the laser seeker as the input of the threshold segmentation algorithm to obtain the segmentation threshold; mark the pixel points with spot confidence indices less than or equal to the segmentation threshold in the grayscale image of the laser seeker as valid pixel points; use the mean value of the grayscale values of all valid pixel points in the spot detection window of each pixel point as the fusion weight of each pixel point; the grayscale value of each pixel point in the optimized grayscale image of the laser seeker is the sum of the products of the grayscale values of the pixel points at the same positions in all grayscale images of the laser seeker and the fusion weight; use the U²-Net neural network model to perform defect detection on the optimized grayscale image of the laser seeker.

2. The computer vision-based visual intelligent detection method for a laser seeker according to claim 1, wherein, The expression for the side length of the light spot detection window of each pixel is as follows: ; where represents the side length of the light spot detection window of the i-th pixel in the grayscale image of the laser seeker; represents the grayscale value of the i-th pixel in the grayscale image of the laser seeker; and respectively represent the preset reference window side length and the preset minimum window side length; ceil( ) represents the ceiling function; norm( ) represents the normalization function.

3. The computer vision-based visual intelligent detection method for a laser seeker according to claim 1, wherein The chaos degree of each pixel point is the image entropy of the spot detection window where each pixel point is located.

4. The vision intelligent detection method of the laser seeker based on computer vision according to claim 1, characterized in that The suspected spot degree of each pixel point is the ratio of the grayscale value of each pixel point to the minimum grayscale value of all pixel points in its spot detection window.

5. The computer vision-based visual intelligent detection method for a laser seeker according to claim 1, wherein The suspected spot index of each pixel point is the product of the chaos degree and the suspected spot of each pixel point.

6. The computer vision-based visual intelligent detection method for a laser seeker according to claim 1, wherein The determination process of the spot area ratio of each pixel point is as follows: Cluster all pixel points in the spot detection window of each pixel point to obtain multiple clustering clusters; The spot area ratio of each pixel point is the ratio of the number of all pixel points in the clustering cluster where the central pixel point inside the spot detection window of each pixel point is located to the square of the side length of the spot detection window.

7. The computer vision-based visual intelligent detection method for a laser seeker according to claim 1, wherein The spot confidence index of each pixel point is the product of the suspected spot index and the spot area of each pixel point.

Images