Cross-modal alignment method for rock slice images

Abstract

The invention relates to the technical field of image processing, in particular to a cross-modal alignment method for rock slice images, which comprises the following steps of: firstly, preprocessing an aligned cross-modal rock slice image data set, extracting an effective core contour common to two modalities by using a Mean Shift-Canny rock core contour detection algorithm based on the acquired data set, and extracting an effective core contour common to the two modalities; and forming a feature descriptor based on the extracted core contour, matching feature points, and completing rock slice image feature alignment and extraction of a common effective core contour of two modalities. On the basis of the extracted core contour, angular points with obvious angles are taken as feature points, after the feature points of different modal images are extracted respectively, the main direction and the auxiliary direction of the feature points are extracted, so that angular point coordinates and response value intensity are combined to jointly serve as descriptors, and a judgment basis of a subsequent matching algorithm is formed; and finally, matching the feature points to realize rock slice feature alignment.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to a cross-modal alignment method for rock thin section images. Background Art

[0002] The study of semantic segmentation of rock thin section images based on cross-modal datasets often requires separate information alignment between each modality during the training process. This is because the information misalignment in spatial, temporal and other dimensions between different modalities caused by error calibration methods, data acquisition methods of each modality or sensor defects. In the cross-modal dataset composed of multiple rock thin section polarization images, since the image acquisition process under different optical conditions is affected by factors such as lens jitter, sample displacement, and sensor defects, there is a problem of consistency in spatial dimensions in the rock thin section polarization images under different modalities, which has a certain impact on the accuracy of network training and models, and will also interfere with the judgment of rock thin section identification workers on the semantic segmentation results. Traditional image matching algorithms usually rely on edge detection and feature point matching when dealing with the problem of cross-modal alignment of rock thin sections. However, the complexity and diversity of features of rock thin section images make these algorithms perform poorly in practical applications. In view of the problems of traditional algorithms, a cross-modal rock thin section modal alignment algorithm for data label information is proposed.

[0003] In summary, it is necessary to propose a cross-modal alignment method for rock thin section images to solve the above problems. Summary of the invention

[0004] The object of the present invention is to provide a cross-modal alignment method for rock thin section images to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A cross-modal alignment method for rock thin section images, the method comprising the following steps:

[0007] S10. Preprocessing of cross-modal rock thin section image dataset for alignment:

[0008] Manual semantic segmentation was performed on the polarized images of rock thin sections obtained under single polarization and orthogonal polarization conditions. The quartz areas in the images were gradually marked using manual annotation tools to provide segmentation label information for subsequent image analysis and model training.

[0009] S20. Based on the collected data set, the MeanShift-Canny rock core contour detection algorithm is used to extract the effective core contours common to the two modes:

[0010] Apply mean shift filtering to smooth the image. Mean shift filtering smoothes the image by considering the neighborhood of each pixel in multidimensional space, thereby maintaining edge features.

[0011] Check whether the filtering process converges through the preset convergence condition. If the change in the image reaches the preset convergence condition, it is considered that the process has been completed and the subsequent steps are entered. If it does not converge, the mean shift filtering is continued until the convergence condition is met.

[0012] Apply Gaussian filtering to further smooth the image. Gaussian filtering filters out the high-frequency components of the image and retains the low-frequency components of the image. While reducing noise interference, it blurs the edge to a certain extent.

[0013] The gradient amplitude of the image processed by Gaussian filtering is calculated to detect the edge in the image. The edge area is emphasized by calculating the gradient amplitude of each pixel. The gradient image is processed using non-maximum suppression technology to remove the gradient intensity of non-edges and ensure that the edge is retained with a single pixel width. Finally, only the local maximum value is retained as the edge.

[0014] Double threshold selection is applied to detect edges. Two high and low thresholds are set to distinguish strong edges, weak edges and non-edges. Strong edges are directly retained, while weak edges are retained only when they are connected to strong edges. Then the image is binarized to generate a contour map and morphological dilation and multi-scale contour fusion are performed.

[0015] S30. Form a feature descriptor based on the extracted core contour:

[0016] The Shi-Tomasi corner detection algorithm is used to calculate the corner points in the image. The important corner point areas in the image are determined according to the response values ​​of the corner points. The response value classification threshold is set according to the specific situation of the image and the requirements of corner point detection, and the points with high response values ​​are selected as key corner points.

[0017] Take the key corner points with obvious angles in the contour as feature points;

[0018] Define the descriptors of feature points in the image;

[0019] S40. Match feature points to complete rock slice image feature alignment:

[0020] First, the FLANN algorithm is used to find the K nearest neighbor feature points of each feature point in the reference image corresponding to the image to be matched;

[0021] Then, the RANSAC algorithm is used to calculate the homography matrix while eliminating the wrong matching pairs;

[0022] Preferably, after the smoothing process is performed in step S20, an adaptive mean shift filtering is performed, and the steps are as follows:

[0023] S2011. Analyze the complexity of image content and automatically adjust the bandwidth parameters of the mean shift filter according to the texture density and contrast in the image;

[0024] S2012. Implement adaptive mean shift filtering and dynamically adjust the filtering strength according to local image features;

[0025] S2013. Evaluate the filtering effect by comparing the edge clarity of the image before and after filtering, and adjust the filtering times or parameters until the optimal effect is achieved.

[0026] Preferably, the specific operations of binarizing the image to generate a contour map and performing morphological dilation in step S20 are: converting the edge information of the image into a black and white format, performing a morphological dilation operation on the binarized contour map, and filling small gaps in the detected edges by expanding edge pixels and enhancing edge features.

[0027] Preferably, the specific steps of forming the feature descriptor are as follows:

[0028] The multi-scale contour fusion in step S20 comprises the following steps:

[0029] S2021. Perform multi-scale morphological dilation on the binary contour image to generate contour images of different scales;

[0030] S2022. Use image fusion technology to fuse multi-scale contour images to enhance the integrity and coherence of the contours;

[0031] S2023. Optimize the fused contour image by edge refinement method to ensure the accuracy and clarity of the contour.

[0032] Preferably, the step S30 takes key corner points with obvious angles in the contour as feature points, and the steps are as follows:

[0033] S3011. Set the obvious angle threshold to 45 degrees. When the angle between two adjacent edges on the contour is greater than 45 degrees, it is considered to have an obvious angle. Select key feature points based on the contrast and texture complexity image features of the feature points.

[0034] S3012. Perform weighted processing on the selected feature points, and assign different weights according to their importance and stability in the image;

[0035] S3013. Update the feature point descriptor and incorporate the weighted information into the descriptor.

[0036] Preferably, the steps of defining the descriptors of the feature points in the image in step S30 are as follows:

[0037] S3021. The start edge and the end edge at the corner point are understood as the two directions with the most white pixels in the neighborhood of the feature point, and are defined as the main direction and the auxiliary direction respectively;

[0038] S3022. Combine the response value intensity information of the coordinates of the feature point to form a descriptor of the feature point.

[0039] Preferably, in step S20, the upper threshold is 75% of the maximum value of the gradient amplitude, which is used to determine a strong edge, and the lower threshold is 25% of the maximum value of the gradient amplitude, which is used to determine a weak edge.

[0040] Preferably, in step S40, when erroneous matches are caused by noise, illumination change, or image distortion, the RANSAC algorithm robustness estimation method is used to eliminate the erroneous matching pairs.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention designs a MeanShift-Canny rock core contour detection algorithm for rock thin section scenes by improving the Canny algorithm, and extracts the effective core contours common to the two modes; then based on the extracted core contours, the corner points with obvious angles are taken as feature points, and after respectively extracting the feature points of different modal images, the main direction and auxiliary direction of the feature points are extracted, and the corner point coordinates and the response value intensity are combined as descriptors to form the judgment basis of the subsequent matching algorithm; finally, the feature points are matched to realize the feature alignment of the rock thin section. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A single polarization image of a rock slice of the present invention is shown;

[0043] Figure 2 The figure shows the contour extraction result of the MeanShift-Canny algorithm of the present invention;

[0044] Figure 3 The corner point detection result diagram of the present invention is shown;

[0045] Figure 4 The fan-shaped area of ​​the present invention is rotated around the corner point to determine the corner point direction diagram;

[0046] Figure 5 A feature point matching result diagram of the present invention is shown. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 , Figure 2 , Figure 3 , Figure 4 as well as Figure 5 The present invention proposes a cross-modal alignment method for rock thin section images, the method comprising the following steps:

[0049] S10. Preprocessing of cross-modal rock thin section image dataset for alignment:

[0050] Manual semantic segmentation was performed on the polarized images of rock thin sections obtained under single polarization and orthogonal polarization conditions. The quartz areas in the images were gradually marked using manual annotation tools to provide segmentation label information for subsequent image analysis and model training.

[0051] S20. Based on the collected data set, the MeanShift-Canny rock core contour detection algorithm is used to extract the effective core contours common to the two modes:

[0052] Apply mean shift filtering to smooth the image. Mean shift filtering smoothes the image by considering the neighborhood of each pixel in multidimensional space, thereby maintaining edge features.

[0053] Check whether the filtering process converges through the preset convergence condition. If the change in the image reaches the preset convergence condition, it is considered that the process has been completed and the subsequent steps are entered. If it does not converge, the mean shift filtering is continued until the convergence condition is met.

[0054] Apply Gaussian filtering to further smooth the image. Gaussian filtering filters out the high-frequency components of the image and retains the low-frequency components of the image. While reducing noise interference, it blurs the edge to a certain extent.

[0055] The gradient amplitude of the image processed by Gaussian filtering is calculated to detect the edge in the image. The edge area is emphasized by calculating the gradient amplitude of each pixel. The gradient image is processed using non-maximum suppression technology to remove the gradient intensity of non-edges and ensure that the edge is retained with a single pixel width. Finally, only the local maximum value is retained as the edge.

[0056] Double threshold selection is applied to detect edges. Two high and low thresholds are set to distinguish strong edges, weak edges and non-edges. Strong edges are directly retained, while weak edges are retained only when they are connected to strong edges. Then the image is binarized to generate a contour map and morphological dilation and multi-scale contour fusion are performed.

[0057] S30. Form a feature descriptor based on the extracted core contour:

[0058] The Shi-Tomasi corner detection algorithm is used to calculate the corner points in the image. The important corner point areas in the image are determined according to the response values ​​of the corner points. The response value classification threshold is set according to the specific situation of the image and the requirements of corner point detection, and the points with high response values ​​are selected as key corner points.

[0059] Take the key corner points with obvious angles in the contour as feature points;

[0060] Define the descriptors of feature points in the image;

[0061] S40. Match feature points to complete rock slice image feature alignment:

[0062] First, the FLANN algorithm is used to find the K nearest neighbor feature points of each feature point in the reference image corresponding to the image to be matched;

[0063] Then, the RANSAC algorithm is used to calculate the homography matrix while eliminating the wrong matching pairs;

[0064] In this embodiment, it should also be noted that after the smoothing process is performed in step S20, an adaptive mean shift filtering is performed, and the steps are as follows:

[0065] S2011. Analyze the complexity of image content and automatically adjust the bandwidth parameters of the mean shift filter according to the texture density and contrast in the image;

[0066] S2012. Implement adaptive mean shift filtering and dynamically adjust the filtering strength according to local image features;

[0067] S2013. Evaluate the filtering effect by comparing the edge clarity of the image before and after filtering, and adjust the filtering times or parameters until the optimal effect is achieved.

[0068] In this embodiment, it should also be noted that the specific operations of binarizing the image to generate a contour map and performing morphological dilation in step S20 are: converting the edge information of the image into a black and white format, performing a morphological dilation operation on the binarized contour map, and expanding edge pixels to enhance edge features and fill small gaps in the detected edges.

[0069] In this embodiment, it should be noted that the specific steps of forming the feature descriptor are as follows:

[0070] The multi-scale contour fusion in step S20 comprises the following steps:

[0071] S2021. Perform multi-scale morphological dilation on the binary contour image to generate contour images of different scales;

[0072] S2022. Use image fusion technology to fuse multi-scale contour images to enhance the integrity and coherence of the contours;

[0073] S2023. Optimize the fused contour image by edge refinement method to ensure the accuracy and clarity of the contour.

[0074] In this embodiment, it should be noted that the step S30 takes key corner points with obvious angles in the contour as feature points, and the steps are as follows:

[0075] S3011. Set the obvious angle threshold to 45 degrees. When the angle between two adjacent edges on the contour is greater than 45 degrees, it is considered to have an obvious angle. Select key feature points based on the contrast and texture complexity image features of the feature points.

[0076] S3012. Perform weighted processing on the selected feature points, and assign different weights according to their importance and stability in the image;

[0077] S3013. Update the feature point descriptor and incorporate the weighted information into the descriptor.

[0078] In this embodiment, it should be noted that the steps of defining the descriptors of the feature points in the image in step S30 are as follows:

[0079] S3021. The start edge and the end edge at the corner point are understood as the two directions with the most white pixels in the neighborhood of the feature point, and are defined as the main direction and the auxiliary direction respectively;

[0080] S3022. Combine the response value intensity information of the coordinates of the feature point to form a descriptor of the feature point.

[0081] In this embodiment, it should be noted that in step S20, the upper threshold is 75% of the maximum value of the gradient amplitude, which is used to determine a strong edge, and the lower threshold is 25% of the maximum value of the gradient amplitude, which is used to determine a weak edge.

[0082] In this embodiment, it should also be noted that in step S40, when erroneous matches are caused by noise, illumination change, or image distortion, the RANSAC algorithm robustness estimation method is used to eliminate the erroneous matching pairs.

[0083] Example

[0084] In practical applications, the cross-modal alignment method for rock thin section images specifically includes the following steps:

[0085] (1) Preprocessing of cross-modal rock thin section image datasets for alignment;

[0086] The data set used in this paper contains two modal information: single polarization and orthogonal polarization of rock slices. It is mainly taken from sandstone rock samples from Sichuan Basin and Ordos Basin. The rock storage layers in the two places are mainly composed of quartz and feldspar. Figure 1 As shown;

[0087] The dataset was prepared under the guidance of professional geologists. Polarized images of rock slices from the two sites were obtained under single polarized light and cross polarized light optical conditions by using the standard operating procedures of electron polarizing microscopes.

[0088] A total of 369 single polarization images of rock thin sections and 369 orthogonal polarization images of rock thin sections were obtained, and 738 semantic segmentation labels were manually made. The main segmentation object was quartz in the image. The specific process is as follows:

[0089] Cut the rock into thin slices and observe them under a polarizing microscope;

[0090] The acquisition of single polarized light image and orthogonal polarized light image of rock slice is realized by superposition of polarized light filters. Two polarized light filters are placed between the light source and the object to be detected and between the objective lens and the eyepiece. When only a single polarized light filter is used, a single polarized light image can be obtained. When two polarized light filters are used at the same time and made perpendicular to each other, an orthogonal offset is formed to obtain an orthogonal polarized light image.

[0091] There are single refracting bodies and double refracting bodies in rock slice images. We can judge by changing the direction of light irradiation and observing whether the optical properties such as the refractive index and absorptivity of the material change.

[0092] If a change occurs, it is a birefringent body (such as the identification target quartz of the present invention), otherwise it is a single refractive body (such as pores, non-crystalline particles, etc.);

[0093] (2) Based on the collected data set, the MeanShift-Canny rock core contour detection algorithm is used to extract the effective core contours common to the two modes;

[0094] Firstly, the rock thin section image is smoothed and segmented by the mean shift filter, which blurs the texture details of the rock area and better retains the core contour features, thereby reducing the noise and useless rock texture information of the rock thin section image.

[0095] The implementation process of mean shift is based on statistical methods to find the pixel with the highest frequency in a specific context in the image. The basic process in the present invention is as follows:

[0096] (2.1) Traverse and select each pixel point in the RGB input image, set the currently selected point as m0, and loop to complete the drift calculation from step (2.2) to step (2.4);

[0097] (2.2) Establish an iteration space: Take pixel point m0 ​​as the starting center and establish a physical space size r p And the color space size is r c Drift window;

[0098] (2.3) Obtaining mass points: Calculate the drift vectors of all pixels in the drift window relative to m0, and take the mean of the color vectors relative to m0 as the centroid m1 of this window;

[0099] (2.4) Drift iteration: Take the centroid m1 as the new starting center, repeat steps (2.2) and (2.3) to obtain the next centroid m2;

[0100] This process is iterated to the nth time, satisfying the starting center point m n-1 Equal to the centroid m of the drift window at this time n When the condition is met, the iteration is terminated and the pixel value of the original center point m0 ​​in the input image is set to the iteration end point m n The color value at

[0101] Mean shift has the function of merging similar color regions and removing small color regions. However, due to the large number of fine rock textures and dissolved regions in rock thin section images, it is difficult to be processed by the mean shift algorithm at one time.

[0102] The present invention sets the mean shift round number i, improves the interference of useless feature information through multiple rounds of mean shift algorithm, and further extracts key profile information;

[0103] And by adjusting the physical space size r p and color space size r c To compare the smoothing effect, the results are shown in the attached Figure 2 As shown;

[0104] (3) Form a feature descriptor based on the extracted core contour;

[0105] First, the corner points in the image are calculated using the Shi-Tomasi corner detection algorithm;

[0106] Determine the important corner point areas in the image based on the response values ​​of the corner points, and select those points with higher response values ​​as key corner points;

[0107] Then take the key corner points with obvious angles in the contour as feature points;

[0108] Finally, the starting edge and the ending edge at the corner point are understood as the two directions with the most white pixels in the neighborhood of the feature point, which are defined as the main direction and the auxiliary direction respectively;

[0109] Finally, the coordinates of the feature points, the intensity of the response values ​​in these two directions and other information are combined to form the descriptor of the feature points;

[0110] (4) Match feature points to complete rock slice image feature alignment;

[0111] First, the FLANN algorithm is used to find the K nearest neighbor feature points of each feature point in the reference image corresponding to the image to be matched;

[0112] Specifically, the Hamming distance between feature point descriptors is calculated, and a difference threshold is set to determine whether the matched feature point pairs originate from the core contour at the same position;

[0113] Then use the RANSAC algorithm to calculate the optimal homography matrix. The specific steps are as follows:

[0114] (4.1) Denoise and select 4 pairs of non-collinear point pairs from all matched corner point pairs, calculate the homography matrix H, and record it as model N;

[0115] (4.2) Calculate the error of all remaining matching points to model N. If the error is within the threshold range, add it to the set D and use it as the best set Db;

[0116] (4.3) Repeat steps (4.1) and (4.2). If the number of matching corner point pairs in the set D obtained in the new round of calculation is greater than the current optimal set Db, update Db = D;

[0117] (4.4) When the number of repetitions exceeds the set maximum value, the operation ends, otherwise the cycle continues;

[0118] The matrix H corresponding to the best set Db is the best homography matrix output by this algorithm.

[0119] Use this matrix to perform geometric transformation on the image to be matched, and finally obtain the matched image, as shown in the attached figure. Figure 5 shown.

[0120] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A cross-modal alignment method for rock thin section images, characterized in that: The method comprises the following steps: S10. Preprocessing of cross-modal rock thin section image dataset for alignment: Manual semantic segmentation was performed on the polarized images of rock thin sections obtained under single polarization and orthogonal polarization conditions. The quartz areas in the images were gradually marked using manual annotation tools to provide segmentation label information for subsequent image analysis and model training. S20. Based on the collected data set, the MeanShift-Canny rock core contour detection algorithm is used to extract the effective core contours common to the two modes: Apply mean shift filtering to smooth the image. Mean shift filtering smoothes the image by considering the neighborhood of each pixel in multidimensional space, thereby maintaining edge features. Check whether the filtering process converges through the preset convergence condition. If the change in the image reaches the preset convergence condition, it is considered that the process has been completed and the subsequent steps are entered. If it does not converge, the mean shift filtering is continued until the convergence condition is met. Apply Gaussian filtering to further smooth the image. Gaussian filtering filters out the high-frequency components of the image and retains the low-frequency components of the image. While reducing noise interference, it blurs the edge to a certain extent. The gradient amplitude of the image processed by Gaussian filtering is calculated to detect the edge in the image. The edge area is emphasized by calculating the gradient amplitude of each pixel. The gradient image is processed using non-maximum suppression technology to remove the gradient intensity of non-edges and ensure that the edge is retained with a single pixel width. Finally, only the local maximum value is retained as the edge. Double threshold selection is applied to detect edges. Two high and low thresholds are set to distinguish strong edges, weak edges and non-edges. Strong edges are directly retained, while weak edges are retained only when they are connected to strong edges. Then the image is binarized to generate a contour map and morphological dilation and multi-scale contour fusion are performed. S30. Form a feature descriptor based on the extracted core contour: The Shi-Tomasi corner detection algorithm is used to calculate the corner points in the image. The important corner point areas in the image are determined according to the response values ​​of the corner points. The response value classification threshold is set according to the specific situation of the image and the requirements of corner point detection, and the points with high response values ​​are selected as key corner points. Take the key corner points with obvious angles in the contour as feature points; Define the descriptors of feature points in the image; S40. Match feature points to complete rock slice image feature alignment: First, the FLANN algorithm is used to find the K nearest neighbor feature points of each feature point in the reference image corresponding to the image to be matched; Then, the RANSAC algorithm is used to calculate the homography matrix while eliminating the wrong matching pairs.

2. A cross-modal alignment method for rock thin section images according to claim 1, characterized in that: After the smoothing process is performed in step S20, an adaptive mean shift filtering is performed, and the steps are as follows: S2011. Analyze the complexity of image content and automatically adjust the bandwidth parameters of the mean shift filter according to the texture density and contrast in the image; S2012. Implement adaptive mean shift filtering and dynamically adjust the filtering strength according to local image features; S2013. Evaluate the filtering effect by comparing the edge clarity of the image before and after filtering, and adjust the filtering times or parameters until the optimal effect is achieved.

3. A cross-modal alignment method for rock thin section images according to claim 1, characterized in that: The specific operations of binarizing the image to generate a contour map and performing morphological dilation in step S20 are: converting the edge information of the image into a black and white format, performing a morphological dilation operation on the binarized contour map, and filling small gaps in the detected edges by expanding edge pixels and enhancing edge features.

4. A cross-modal alignment method for rock thin section images according to claim 1, characterized in that: The specific steps of forming the feature descriptor are as follows: The multi-scale contour fusion in step S20 comprises the following steps: S2021. Perform multi-scale morphological dilation on the binary contour image to generate contour images of different scales; S2022. Use image fusion technology to fuse multi-scale contour images to enhance the integrity and coherence of the contours; S2023. Optimize the fused contour image by edge refinement method to ensure the accuracy and clarity of the contour.

5. The cross-modal alignment method for rock thin section images according to claim 1, characterized in that: The step S30 takes key corner points with obvious angles in the contour as feature points, and the steps are as follows: S3011. Set the obvious angle threshold to 45 degrees. When the angle between two adjacent edges on the contour is greater than 45 degrees, it is considered to have an obvious angle. Select key feature points based on the contrast and texture complexity image features of the feature points. S3012. Perform weighted processing on the selected feature points, and assign different weights according to their importance and stability in the image; S3013. Update the feature point descriptor and incorporate the weighted information into the descriptor.

6. A cross-modal alignment method for rock thin section images according to claim 1, characterized in that: The steps of defining the descriptors of the feature points in the image in step S30 are as follows: S3021. The start edge and the end edge at the corner point are understood as the two directions with the most white pixels in the neighborhood of the feature point, and are defined as the main direction and the auxiliary direction respectively; S3022. Combine the response value intensity information of the coordinates of the feature point to form a descriptor of the feature point.

7. A cross-modal alignment method for rock thin section images according to claim 1, characterized in that: In step S20, the upper threshold is 75% of the maximum value of the gradient amplitude, which is used to determine a strong edge, and the lower threshold is 25% of the maximum value of the gradient amplitude, which is used to determine a weak edge.

8. The cross-modal alignment method for rock thin section images according to claim 1, characterized in that: In the step S40, when erroneous matching is caused by noise, illumination change, or image distortion, the RANSAC algorithm robustness estimation method is used to eliminate the erroneous matching pairs.

Images