Multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram

Abstract

The present invention relates to the technical field of multimodal remote sensing image registration. Multimodal remote sensing image imaging sensors and imaging mechanisms are quite different. Image registration methods suffer from decreased registration performance and robustness in different modal remote sensing image registration tasks. The present invention provides a multimodal remote sensing image registration method based on co-occurrence filtering and directional gradient histograms. The method performs coarse matching on a reference image and an image to be registered, obtains spatial relationship constraint information, uses a gradient directional histogram to adjust coarse matching same-name point pairs, improves matching accuracy, updates a homography matrix, and completes image registration by resampling the image to be registered. The method is not only adaptable to multimodal remote sensing image registration scenarios, but also has good robustness to rotation and scale changes of multimodal remote sensing images. Image registration experiments are carried out on multimodal remote sensing images, and the experimental results show that registration accuracy and robustness can be maintained in different scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of multimodal remote sensing image registration, and more particularly to a multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram. Background Art

[0002] Different remote sensing imagery modalities, due to their use of different sensors and technologies, possess unique imaging characteristics. For example, visible light remote sensing imagery was developed the earliest, boasts mature technology, and aligns with human visual habits and perception patterns, offering advantages such as low imaging cost, high resolution, and rich data. However, visible light is a passive imaging method susceptible to weather conditions such as cloud cover and haze, limiting the time and quality of observations and preventing all-weather observations. Synthetic Aperture Radar (SAR) imagery utilizes the active imaging technology of SAR, offering all-weather and all-day observation capabilities. It is widely used in assessing and calculating building damage after disasters such as earthquakes, debris flows, and flash floods. However, SAR imagery is less intuitive than optical imagery in capturing ground features, making object classification more difficult and requiring processing and interpretation. Infrared remote sensing imagery primarily utilizes infrared radiation within the atmospheric window, providing specialized information such as heat distribution and vegetation growth. For example, in the military, visible light imagery is fused with infrared imagery for precision strikes. However, atmospheric absorption and scattering will affect the observation quality and spatial resolution of the infrared band, and it is impossible to penetrate the cloud layer to obtain surface information. Compared with optical images, the spatial resolution of infrared images is relatively low.

[0003] It can be seen that while the imaging mechanisms of remote sensing images of different modalities differ significantly, their images possess rich complementary characteristics and possess broad application potential. If multimodal remote sensing images can be fused, analyzed, and understood, more information can be extracted than from single-modal remote sensing images, solving problems that cannot be solved by single-modal images alone. Multimodal remote sensing image registration is a prerequisite and key step in multimodal remote sensing image fusion analysis. Traditional remote sensing image registration methods generally perform only a single image match between the reference image and the image to be registered. The mapping relationship between the two images is derived based on the matched pairs of same-name points, and the image to be registered is then resampled to complete the image registration. However, multimodal remote sensing images exhibit significant differences in both imaging sensors and imaging mechanisms. Furthermore, images are subject to complex illumination and contrast variations as well as various types of noise pollution, making it difficult for image registration methods to maintain robust performance and performance in multimodal image registration scenarios. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram. The invention can not only adapt to the multimodal remote sensing image registration scenario, but also has good robustness to the rotation and scale changes of multimodal remote sensing images.

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

[0006] A multimodal remote sensing image registration method based on co-occurrence filtering and directional gradient histogram is proposed. The co-occurrence filters with different parameters are used to smooth the image to be registered and the reference influence, and a co-occurrence filter image pyramid scale space is generated. The initial homography matrix, rotation angle, scale constraint spatial relationship constraint information, and directional gradient histogram after rough matching of local feature points extracted on the image pyramid are used to improve the matching accuracy. The image to be registered is resampled to complete the image registration task. The method specifically includes the following steps:

[0007] Step 1. Input the reference image and the image to be registered, and use the co-occurrence filter to smooth the image details of the two images while maintaining the influence edge;

[0008] Step 2. Construct image pyramids for the reference image and the image to be registered. Smooth the "group" image and "layer" image in the pyramid using co-occurrence filters with different parameters. Extract local feature points from the reference image and the image to be registered, and filter the extracted local feature points using the non-maximum suppression method.

[0009] Step 3. Construct the local feature descriptor of the image, use the Euclidean distance as the matching criterion, perform coarse matching on the reference image and the image to be registered, and obtain the coarse matching same-name point pairs between the reference image and the image to be registered;

[0010] Step 4. Obtain the spatial relationship constraint information between the reference image and the image to be registered based on the results of the rough matching: initial homography matrix, rotation angle, and scale constraint;

[0011] Step 5. Based on the spatial constraint relationship information, the directional gradient histogram is used to improve the matching accuracy of the coarse matching same-name point pairs between the reference image and the image to be registered. The adjusted same-name point pairs are used to update the mapping relationship homography matrix between the reference image and the image to be registered.

[0012] Step 6. Use the mapping relationship homography matrix between the adjusted reference image obtained in step 5 and the image to be registered to resample the image to be registered to complete the image registration.

[0013] Furthermore, the co-occurrence filter formula is as follows:

[0014]

[0015]

[0016] Where Jp and Iq are the output and input pixel values, and p and q are pixel indices; is the contribution weight of pixel q to the output of pixel p; M(a,b) is a 256×256 matrix obtained by dividing the co-occurrence matrix C(a,b) of values ​​a and b by the frequency of values ​​a and b; C(a,b) represents the co-occurrence matrix of values ​​a and b; h(a) and h(b) represent the number of image input pixels with values ​​equal to a and equal to b, respectively; d(p,q) is the Euclidean distance between pixels p and q in the image plane.

[0017] Furthermore, the co-occurrence filter window size has the following relationship with the "group" image and "layer" image of the image pyramid:

[0018]

[0019] Wherein, o represents the oth group of the image difference pyramid; i represents the i-th layer image in the oth group of the image difference pyramid; σ s,i represents the parameters of the i-th layer image co-occurrence filter, σ i Represents the filtering parameters of the co-occurrence matrix C(a,b) of value a and value b; round() is the integer function.

[0020] Furthermore, in step 4, the coarse matching of the same-name point pairs between the reference image and the image to be registered is used to obtain the initial homography matrix between the reference image and the image to be registered, and the singular value decomposition method is used to separate the rotation angle between the reference image and the image to be registered from the initial homography matrix; the coarse matching of the same-name point pairs is used to obtain the scale constraint of the reference image and the image to be registered through a voting mechanism.

[0021] Furthermore, in step 4, the singular value decomposition method is used to separate the rotation angle between the reference image and the image to be registered from the homography matrix. The specific steps are as follows:

[0022] Step 4.1 Normalize the homography matrix:

[0023] H_normalized=H / H(3,3)

[0024] H: initial homography matrix; H_normalized: normalized homography matrix;

[0025] Step 4.2 Decompose the homography matrix using SVD:

[0026] [U,~,V]=svd(H_normalized(1:2,1:2))

[0027] svd(): singular value decomposition function;

[0028] Step 4.3 Extract the rotation part of the homography matrix: R = U * V';

[0029] Step 4.4 obtains the rotation angle between the reference image and the image to be registered:

[0030] theta=atan2d(R(2,1),R(1,1))

[0031] theta: The rotation angle between the two images, atan2d: The inverse tangent function, which calculates the rotation angle.

[0032] Furthermore, in step 4, the scale constraint between the reference image and the image to be registered is obtained through a voting mechanism. The specific process is as follows: according to the coarse matching results of the same-name point pairs between the reference image and the image to be registered, the "group" image of the pyramid where the matching points are located is voted, and the "group" image with the most votes is the "group" in the scale constraint; the same-name point pairs in the "group" are screened, and the "layer" images of the same-name point pairs are voted, and the "layer" image with the most votes is the "layer" in the scale constraint.

[0033] Furthermore, in step 5, the matching accuracy of the coarse matching homonymous points is improved based on the spatial relationship constraint information, as follows:

[0034] Step 5.1: After roughly matching the reference image and the image to be registered to obtain coarse matching same-name point pairs, the gradient features of the same-name point support area of ​​the reference image are extracted and a gradient direction histogram is constructed;

[0035] Step 5.2: Extract the gradient features of the region supporting the key points of the image to be registered and construct a gradient direction histogram. Iteratively adjust the key points of the image to be registered within the spatial relationship constraint range, and measure the similarity between the key points in the image to be registered and the reference image until the key points with the highest structural similarity are obtained after the iteration.

[0036] Step 5.3 repeats steps 5.1 to 5.2 to adjust all the same-name points in the image to be registered, improve the matching accuracy of the same-name point pairs between the reference image and the image to be registered, and update the mapping relationship homography matrix between the reference image and the image to be registered.

[0037] In summary, the invention has the following beneficial effects:

[0038] The present invention first performs coarse matching on the reference image and the image to be registered to obtain coarse matching same-name point pairs, and obtains the spatial relationship constraint information between the reference image and the image to be registered from the coarse matching result: the initial homography matrix, rotation angle, and scale constraint. Under the spatial relationship constraint information, the gradient direction histogram is used to improve the matching accuracy of the coarse matching same-name point pairs between the reference image and the image to be registered; then, the homography matrix between the reference image and the image to be registered is updated using the same-name point pairs with improved accuracy; finally, the updated homography matrix is ​​used to resample the image to be registered to complete the image registration.

[0039] This paper addresses the issue of unreliable performance and robustness of image registration methods in multimodal remote sensing image registration scenarios. It proposes first performing a coarse match between the reference image and the image to be registered. The coarse match primarily aims to obtain spatial relationship constraint information between the reference image and the image to be registered, with low matching accuracy requirements. Subsequently, based on the spatial relationship constraint information, the gradient direction histogram is used to adjust the coarse matching same-name point pairs between the reference image and the image to be registered, improving matching accuracy. The homography matrix is ​​then updated, and image registration is completed by resampling the image to be registered. Experimental results show that the present invention can effectively improve the matching accuracy of coarse matching same-name point pairs between the reference image and the image to be registered, thereby improving image registration accuracy. This method is not only applicable to multimodal remote sensing image registration scenarios such as visible light, infrared, SAR, lidar images, and maps, but also exhibits excellent robustness to rotational and scale changes between multimodal remote sensing images. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of the present invention;

[0041] Figure 2 This is a flow chart for improving the accuracy of the homography matrix between the reference image and the image to be registered according to the present invention;

[0042] Figure 3 The image rough matching result and image chessboard registration result of Example 1;

[0043] Figure 4 The image matching accuracy improved result and the image chessboard registration result of Example 1;

[0044] Figure 5 The image rough matching result and image chessboard registration result of Example 2;

[0045] Figure 6 The image matching accuracy improved result and the image chessboard registration result of Example 2;

[0046] Figure 7 The image rough matching result and image chessboard registration result of Example 3;

[0047] Figure 8The image matching accuracy improved result and the image chessboard registration result of Example 3;

[0048] Figure 9 The image rough matching result and image chessboard registration result of Example 4;

[0049] Figure 10 The image matching accuracy improved result and the image chessboard registration result of Example 4;

[0050] Figure 11 The image rough matching result and image chessboard registration result of Example 5;

[0051] Figure 12 The image matching accuracy improved result and the image chessboard registration result of Example 5;

[0052] Figure 13 The image rough matching result and image chessboard registration result of Example 6;

[0053] Figure 14 This is the result after the image matching accuracy is improved and the image chessboard registration result of Example 6. DETAILED DESCRIPTION

[0054] The present invention will be described in further detail below with reference to the accompanying drawings.

[0055] It should be noted that, for the sake of convenience, the directions described below are consistent with the directions of the drawings themselves, but do not limit the structure of the present invention.

[0056] like Figures 1 to 14 As shown, the present invention discloses a multimodal remote sensing image registration method based on co-occurrence filtering and directional gradient histogram. The co-occurrence filters with different parameters are used to smooth the image to be registered and the reference influence, and a co-occurrence filter image pyramid scale space is generated. The initial homography matrix, rotation angle, scale constraint spatial relationship constraint information, and directional gradient histogram after rough matching of local feature points extracted on the image pyramid are used to improve the matching accuracy. The image to be registered is resampled to complete the image registration task. The method specifically includes the following steps:

[0057] Step 1. Input the reference image and the image to be registered, and use the co-occurrence filter to smooth the image details of the two images while maintaining the influence edge; preprocess the reference image and the image to be registered, and complete the construction of the scale space based on the co-occurrence filter on the reference image and the image to be registered.

[0058] Step 2. Build image pyramids for the reference image and the image to be registered. Use co-occurrence filters with different parameters to smooth the "group" image and "layer" image in the pyramid. Extract the gradient features of the support area of ​​the same-name points in the image to be registered and construct a directional gradient histogram. The formula of the co-occurrence filter is as follows:

[0059]

[0060] Where Jp and Iq are the output and input pixel values, and p and q are pixel indices; is the contribution weight of pixel q to the output of pixel p; M(a,b) is a 256×256 matrix obtained by dividing the co-occurrence matrix C(a,b) of values ​​a and b by the frequency of values ​​a and b; C(a,b) represents the co-occurrence matrix of values ​​a and b; h(a) and h(b) represent the number of image input pixels with values ​​equal to a and equal to b, respectively; d(p,q) is the Euclidean distance between pixels p and q in the image plane.

[0061] The co-occurrence filter window size has the following relationship with the "group" and "layer" images of the image pyramid:

[0062]

[0063] Wherein, o represents the oth group of the image difference pyramid; i represents the i-th layer image in the oth group of the image difference pyramid; σ s,i represents the parameters of the i-th layer image co-occurrence filter; σ i Represents the filtering parameters of the co-occurrence matrix C(a,b) of value a and value b; round() is the integer function.

[0064] Local feature points are extracted from the reference image and the image to be registered respectively, and the extracted local feature points are screened using the non-maximum suppression method; in step 2, the local feature points obtained do not correspond, and the local feature points are matched in subsequent steps.

[0065] Step 3. Extract local feature points in the scale space, construct rotation and scale invariant descriptors in the feature point support area, use Euclidean distance as the matching criterion, perform coarse matching on the reference image and the image to be registered, and obtain coarse matching same-name point pairs between the reference image and the image to be registered; achieve the correspondence between the local feature points affected by the reference image and the image to be registered through step 3, and the corresponding incorrect local feature points are matched with the corresponding correct local feature points in this step.

[0066] Step 4. Based on the results of the coarse matching, obtain the spatial relationship constraint information between the reference image and the image to be registered: initial homography matrix, rotation angle, and scale constraint; use the coarse matching same-name point pairs between the reference image and the image to be registered to obtain the initial homography matrix between the reference image and the image to be registered, and use the singular value decomposition method to separate the rotation angle between the reference image and the image to be registered from the initial homography matrix; use the coarse matching same-name point pairs to obtain the scale constraint of the reference image and the image to be registered through a voting mechanism, and the rotation angle and scale constraint can be calculated simultaneously.

[0067] Use the singular value decomposition method to separate the rotation angle between the reference image and the image to be registered from the homography matrix. The specific steps are as follows:

[0068] Step 4.1 Normalize the homography matrix:

[0069] H_normalized=H / H(3,3)

[0070] H: initial homography matrix; H_normalized: normalized homography matrix.

[0071] Step 4.2 Decompose the homography matrix using SVD:

[0072] [U,~,V]=svd(H_normalized(1:2,1:2))

[0073] svd(): singular value decomposition function;

[0074] Step 4.3 Extract the rotation part of the homography matrix: R = U * V';

[0075] Step 4.4 obtains the rotation angle between the reference image and the image to be registered:

[0076] theta=atan2d(R(2,1),R(1,1))

[0077] theta: The rotation angle between the two images, atan2d: The inverse tangent function, which calculates the rotation angle.

[0078] The scale constraint between the reference image and the image to be registered is obtained through a voting mechanism. The specific process is as follows: according to the coarse matching results of the same-name point pairs between the reference image and the image to be registered, the "group" image of the pyramid where the matching points are located is voted, and the "group" image with the most votes is the "group" in the scale constraint; the same-name point pairs in the "group" are screened, and the "layer" images of the same-name point pairs are voted, and the "layer" image with the most votes is the "layer" in the scale constraint.

[0079] Step 5. Based on the spatial constraint relationship information, the directional gradient histogram is used to improve the matching accuracy of the coarse matching of the same-name point pairs between the reference image and the image to be registered. The method is as follows:

[0080] Step 5.1: After roughly matching the reference image and the image to be registered to obtain roughly matched pairs of same-name points, extract the gradient features of the support area of ​​the same-name points in the reference image and construct a gradient direction histogram.

[0081] Step 5.2 extracts the gradient features of the feature support area of ​​the same-name points in the image to be registered and constructs the gradient direction histogram of the feature support area of ​​the same-name points in the image to be registered. Iteratively adjusts the same-name points in the image to be registered within the spatial relationship constraint range, and measures the similarity between the same-name points in the image to be registered and the reference image until the iteration is completed to obtain the same-name points with the highest structural similarity.

[0082] Step 5.3 repeats steps 5.1 to 5.2 to adjust all the same-name points in the image to be registered, improve the matching accuracy of the same-name point pairs between the reference image and the image to be registered, and update the mapping relationship homography matrix between the reference image and the image to be registered.

[0083] The adjusted same-name point pairs are used to update the homography matrix, a mapping relationship between the reference image and the image to be registered.

[0084] Step 6. Use the mapping relationship homography matrix between the adjusted reference image obtained in step 5 and the image to be registered to resample the image to be registered to complete the image registration.

[0085] The present invention constructs a scale space based on a co-occurrence filter on a reference image and an image to be registered respectively; extracts local feature points in the scale space, and constructs a rotation and scale invariant descriptor in the feature point support area; performs coarse matching on the reference image and the image to be registered to obtain spatial relationship constraint information between the two images, such as an initial homography matrix, rotation constraints, and scale constraints; constructs directional gradient histograms for the coarsely matched same-name points of the reference image and the image to be registered respectively; adjusts the same-name point pairs using the directional gradient histograms based on the spatial relationship constraint information using a similarity criterion to improve the matching accuracy of the same-name point pairs; calculates the mapping relationship homography matrix between the reference image and the image to be registered based on the adjusted same-name point pairs, and resamples the image to be registered to complete the image registration task.

[0086] like Figures 3 to 14 As shown in the figure, the present invention conducted an image registration experiment on multimodal remote sensing images. The experimental results show that the present invention can maintain good registration accuracy and robustness in visible light, infrared, lidar, SAR, map and other scenarios.

[0087] from Figure 3 and Figure 4It can be seen that after the present invention improves the matching accuracy of the reference image and the image to be registered, the image registration accuracy is significantly improved. Figure 3 and Figure 4 Shown in red circle on the right.

[0088] from Figures 3 to 10 It can be seen that after the present invention improves the matching accuracy of the reference image and the image to be registered, the image registration accuracy is significantly improved. Figure 3 and Figure 4 、 Figure 5 and Figure 6 、 Figure 7 and Figure 8 、 Figure 9 and Figure 10 As shown in the red circle on the right image.

[0089] Figure 11 and Figure 12 The image is rotated 90 degrees, from Figure 11 and Figure 12 It can be seen that there is a 90-degree rotation change between the reference image and the image to be registered, but the method proposed in the present invention can still perform high-precision image registration. Moreover, when the coarse matching accuracy is already very good, the use of the gradient direction histogram to adjust the same-name points between the reference image and the image to be registered will not affect the coarse matching image registration accuracy.

[0090] Figure 13 and Figure 14 There is also a rotation change of nearly 90 degrees between the reference image and the image to be registered. It can be seen from the chessboard registration result on the right that the present invention can not only cope with large-angle image registration scenarios but also improve the matching accuracy between the reference image and the image to be registered through the gradient direction histogram, thereby further improving the image registration accuracy, as shown by the red circle in the figure on the right.

[0091] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram, characterized in that: The co-occurrence filters with different parameters are used to smooth the image to be registered and the reference influence, and the co-occurrence filter image pyramid scale space is generated. The initial homography matrix, rotation angle, scale constraint spatial relationship constraint information, and directional gradient histogram after rough matching of local feature points extracted on the image pyramid are used to improve the matching accuracy. The image to be registered is resampled to complete the image registration task. The specific steps include: Step 1. Input the reference image and the image to be registered, and use the co-occurrence filter to smooth the image details of the two images while maintaining the influence edge; Step 2. Construct image pyramids for the reference image and the image to be registered. Use co-occurrence filters with different parameters to smooth the "group" image and "layer" image in the pyramid. Extract local feature points from the reference image and the image to be registered, and use non-maximum suppression to filter the extracted local feature points. Step 3. Construct the local feature descriptor of the image, use the Euclidean distance as the matching criterion, perform coarse matching on the reference image and the image to be registered, and obtain the coarse matching same-name point pairs between the reference image and the image to be registered; Step 4. Based on the coarse matching results, obtain the spatial relationship constraint information between the reference image and the image to be registered: initial homography matrix, rotation angle, and scale constraint. Use the coarse matching same-name point pairs between the reference image and the image to be registered to obtain the initial homography matrix between the reference image and the image to be registered. Use the singular value decomposition method to separate the rotation angle between the reference image and the image to be registered from the initial homography matrix. Use the coarse matching same-name point pairs to obtain the scale constraint of the reference image and the image to be registered through a voting mechanism. Step 5. Based on the spatial constraint relationship information, the directional gradient histogram is used to improve the matching accuracy of the coarse matching same-name point pairs between the reference image and the image to be registered. The adjusted same-name point pairs are used to update the mapping relationship homography matrix between the reference image and the image to be registered. The matching accuracy of the coarse matching same-name points is improved based on the spatial relationship constraint information. The method is as follows: Step 5.1: After roughly matching the reference image and the image to be registered to obtain coarse matching same-name point pairs, the gradient features of the same-name point support area of ​​the reference image are extracted and a gradient direction histogram is constructed; Step 5.2: Extract the gradient features of the region supporting the key points of the image to be registered and construct a gradient direction histogram. Iteratively adjust the key points of the image to be registered within the spatial relationship constraint range, and measure the similarity between the key points in the image to be registered and the reference image until the key points with the highest structural similarity are obtained after the iteration. Step 5.3: Repeat steps 5.1 to 5.2 to adjust all the key points in the image to be registered, improve the matching accuracy of the key points between the reference image and the image to be registered, and update the homography matrix between the reference image and the image to be registered. Step 6. Use the mapping relationship homography matrix between the adjusted reference image obtained in step 5 and the image to be registered to resample the image to be registered to complete the image registration.

2. The multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram according to claim 1, characterized in that: The co-occurrence filter formula is as follows: Among them, and are the output and input pixel values, p and q are the pixel indices, Σ q∈N(p) It means summing the data of pixel index q within the range of number N(p) of pixel index p; is the contribution weight of pixel q to the output of pixel p, Represents the parameters of the image co-occurrence filter of the i-th layer. M(a,b) is a 256×256 matrix, which is obtained by dividing the co-occurrence matrix C(a,b) of value a and value b by the frequency of value a and value b. represents the filter parameters of the co-occurrence matrix C(a,b) of values ​​a and b; C(a,b) represents the co-occurrence matrix of values ​​a and b; h(a) and h(b) represent the number of image input pixels with values ​​equal to a and equal to b, respectively; d(p,q) is the Euclidean distance between pixel p and pixel q in the image plane.

3. The multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram according to claim 1, characterized in that: The co-occurrence filter window size has the following relationship with the "group" image and "layer" image of the image pyramid: in, o Represents the first o group; i represents the first o The i-th layer image in the group; represents the parameters of the i-th layer image co-occurrence filter, Represents the filtering parameters of the co-occurrence matrix C(a,b) of value a and value b; round() is the integer function.

4. The multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram according to claim 1, characterized in that: In step 4, the singular value decomposition method is used to separate the rotation angle between the reference image and the image to be registered from the homography matrix. The specific steps are as follows: Step 4.1 Normalize the homography matrix: H_normalized = H / H(3,3) H: initial homography matrix; H_normalized: normalized homography matrix; Step 4.2 Decompose the homography matrix using SVD: [U,~,V] =svd(H_normalized (1:2, 1:2)) svd(): singular value decomposition function; Step 4.3 Extract the rotation part of the homography matrix: R=U*V'; Step 4.4 obtains the rotation angle between the reference image and the image to be registered: theta = atan2d(R(2,1), R(1,1)) theta: The rotation angle between the two images, atan2d: The inverse tangent function, which calculates the rotation angle.

5. The multimodal remote sensing image registration method based on co-occurrence filtering and oriented gradient histogram according to claim 1, characterized in that: In step 4, the scale constraint between the reference image and the image to be registered is obtained through a voting mechanism. The specific process is as follows: based on the coarse matching results of the same-name point pairs between the reference image and the image to be registered, the "group" image of the pyramid where the matching points are located is voted, and the "group" image with the most votes is the "group" in the scale constraint; the same-name point pairs in the "group" are screened, and the "layer" images of the same-name point pairs are voted, and the "layer" image with the most votes is the "layer" in the scale constraint.

Images