Remote sensing image registration method and device, electronic equipment and storage medium

Abstract

The invention provides a remote sensing image registration method and device, electronic equipment and a storage medium. The remote sensing image registration method comprises the following steps: acquiring a target feature point of a target image, wherein the target image comprises a to-be-registered remote sensing image and a reference remote sensing image; for each of the target images, determining the overall phase consistency feature of the target image according to the local energy and phase intensity of all scales and directions of the target image; determining a logarithm polar coordinate descriptor of the target feature point according to the overall phase consistency feature; and registering the remote sensing image to be registered and the reference remote sensing image according to the logarithm polar coordinate descriptor of the target feature point. According to the scheme, the image registration of the remote sensing image to be registered can be more accurately carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image processing, and in particular, to a remote sensing image registration method, a remote sensing image registration device, an electronic device, a storage medium, and a computer program product. Background Art

[0002] Image registration is the process of matching and superimposing two or more remote sensing images obtained at different times, by different sensors (imaging devices), or under different conditions (weather, illumination, camera position and angle, etc.), and it has been widely applied to the analysis of remote sensing data.

[0003] After extracting feature points in two or more remote sensing images, the two or more remote sensing images can be registered according to the feature point information corresponding to the feature points. The feature point information corresponding to the feature points affects the effect of image registration.

[0004] For two or more remote sensing images in different situations, traditional image registration methods usually select corresponding feature point extraction methods to extract feature points in the two or more remote sensing images, thereby improving the effect of image registration. However, when performing image registration, the feature point information of the extracted feature points depends on the feature point extraction method. Because the image information in different remote sensing images is different, traditional image registration methods are not suitable for remote sensing image registration in complex situations. Summary of the Invention

[0005] The present invention is proposed in view of the above problems.

[0006] According to a first aspect of the present invention, there is provided a remote sensing image registration method. The method includes: obtaining target feature points of a target image, where the target image includes a remote sensing image to be registered and a reference remote sensing image; for each of the target images, determining an overall phase consistency feature of the target image according to the local energy and phase intensity of all scales and directions of the target image; determining a log-polar coordinate descriptor of the target feature points according to the overall phase consistency feature; and registering the remote sensing image to be registered and the reference remote sensing image according to the log-polar coordinate descriptor of the target feature points.

[0007] Exemplarily, the obtaining target feature points of the target image includes: for each of the target images, determining a minimum distance and a maximum distance according to the phase intensity response of the target image; extracting first corner feature points from the target image according to the minimum distance; extracting first edge feature points from the target image according to the maximum distance; and determining the target feature points of the target image from the first edge feature points and the first corner feature points.

[0008] Exemplarily, determining the target feature points of the target image among the first edge feature points and the first corner feature points includes: obtaining the confidence of each first edge feature point and the confidence of each first corner feature point; dividing the target image into multiple regions; for each region, respectively determining the first feature points and the second feature points in the region, where the first feature points include the first edge feature point with the highest confidence in the region, and the distance between the first feature points in the region is not less than the first distance threshold, the second feature points include the first corner feature point with the highest confidence in the region, and the distance between the second feature points in the region is not less than the first distance threshold; selecting the target feature points of the target image among the first feature points and the second feature points.

[0009] Exemplarily, extracting the first corner feature points from the target image according to the minimum distance includes: using a FAST feature extractor to determine second corner feature points according to the minimum distance; using a SIFT feature extractor to determine third corner feature points according to the minimum distance; determining the same points among the second corner feature points and the third corner feature points as the first corner feature points; and / or

[0010] Extracting the first edge feature points from the target image according to the maximum distance includes: using a FAST feature extractor to determine second edge feature points according to the maximum distance; using a SIFT feature extractor to determine third edge feature points according to the maximum distance; determining the same points among the second edge feature points and the third edge feature points as the first edge feature points.

[0011] Exemplarily, determining the log-polar coordinate descriptor of the target feature points according to the overall phase consistency feature includes: performing a convolution operation on the target image using an odd filter to obtain the overall phase direction feature of the target image; determining the first phase consistency feature of the neighborhood of each target feature point according to the position of the neighborhood of each target feature point and the overall phase consistency feature, where for each target feature point, the pixel where the target feature point is located is the central pixel of the neighborhood of the target feature point; determining the first phase direction feature of the neighborhood of each target feature point according to the position of the neighborhood of each target feature point and the overall phase direction feature; for each target feature point, determining the log-polar coordinate descriptor of the target feature point according to the first phase consistency feature and the first phase direction feature of the neighborhood of the target feature point.

[0012] Exemplarily, determining the log-polar coordinate descriptor of the target feature point according to the first phase consistency feature and the first phase direction feature in the domain of the target feature point includes: dividing the domain of the target feature point into a plurality of sub-regions; for each sub-region, determining the local direction and the phase consistency intensity information respectively corresponding to each pixel in the sub-region according to the first phase consistency feature and the first phase direction feature in the domain of the target feature point; and determining the log-polar coordinate descriptor of the target feature point according to the local direction and the phase consistency intensity information respectively corresponding to each pixel in each sub-region.

[0013] Exemplarily, the areas of the plurality of sub-regions are equal.

[0014] Exemplarily, determining the log-polar coordinate descriptor of the target feature point according to the local direction and the phase consistency intensity information respectively corresponding to each pixel in each sub-region includes: for the pixels in each sub-region, determining the pixels in the sub-region as pixels corresponding to different local direction ranges according to the local direction respectively corresponding to each pixel; for each local direction range, adding the phase consistency intensity information of the pixels corresponding to the local direction range to obtain the second phase consistency feature of the pixels corresponding to the local direction range; and determining the log-polar coordinate descriptor of the target feature point according to the second phase consistency features of the pixels in each sub-region respectively corresponding to different local direction ranges.

[0015] According to a second aspect of the present invention, there is also provided a remote sensing image registration device, including:

[0016] A feature point acquisition module, configured to acquire target feature points of a target image, where the target image includes a remote sensing image to be registered and a reference remote sensing image;

[0017] A feature determination module, configured to determine the overall phase consistency feature of the target image for each of the target images according to the local energy and phase intensity at all scales and directions of the target image;

[0018] A description module, configured to determine the log-polar coordinate descriptor of the target feature point according to the overall phase consistency feature;

[0019] A registration module, configured to register the remote sensing image to be registered and the reference remote sensing image according to the log-polar coordinate descriptor of the target feature point.

[0020] According to a third aspect of the present invention, there is also provided an electronic device, including: a processor and a memory, where computer program instructions are stored in the memory, and when the computer program instructions are run by the processor, they are used to execute the above-mentioned remote sensing image registration method.

[0021] According to a fourth aspect of the present invention, there is also provided a storage medium on which program instructions are stored, and the program instructions are used to execute the above-mentioned remote sensing image registration method when running.

[0022] According to a fifth aspect of the present invention, there is also provided a computer program product including computer program instructions, and the computer program instructions are used to execute the above-mentioned remote sensing image registration method when running.

[0023] In the above technical solution, in the above technical solution, target feature points of a target image are obtained. The target image includes a remote sensing image to be registered and a reference remote sensing image. Then, for each of the target images, according to the local energy and phase intensity of all scales and directions of the target image, the overall phase consistency feature of the target image is determined. After that, according to the overall phase consistency feature, the log-polar coordinate descriptor of the target feature points is determined. Finally, according to the log-polar coordinate descriptor of the target feature points, the remote sensing image to be registered and the reference remote sensing image are registered. The overall phase consistency feature of the target image enhances the response of the phase consistency information. Determining the log-polar coordinate descriptor of the target feature points according to the overall phase consistency feature can more accurately characterize the feature point information of the target feature points. In this way, the image registration of the remote sensing image to be registered can be more accurately performed.

[0024] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the following specifically gives the specific embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By describing the embodiments of the present invention in more detail in conjunction with the drawings, the above and other purposes, features and advantages of the present invention will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the description. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

[0026] Figure 1 Shows a schematic flowchart of a remote sensing image registration method according to an embodiment of the present invention;

[0027] Figure 2 Shows a schematic flowchart of a method for obtaining target feature points of a target image according to an embodiment of the present invention;

[0028] Figure 3 Shows a schematic flowchart of determining the target feature points of the target image among the first edge feature points and the first corner feature points according to an embodiment of the present invention;

[0029] Figure 4 Shows a schematic flowchart of extracting the first corner feature points from the target image according to the minimum distance according to an embodiment of the present invention;

[0030] Figure 5 Shows a schematic flowchart of extracting the first edge feature points from the target image according to the maximum distance according to an embodiment of the present invention;

[0031] Figure 6 Shows a schematic flowchart of determining the log-polar coordinate descriptor of the target feature points according to the overall phase consistency feature according to an embodiment of the present invention;

[0032] Figure 7 Shows a schematic flowchart of determining the log-polar coordinate descriptor of the target feature points according to the first phase consistency feature and the first phase direction feature in the neighborhood of the target feature points according to an embodiment of the present invention;

[0033] Figure 8 Shows a schematic flowchart of determining the log-polar coordinate descriptor of the target feature points according to the local direction and phase consistency intensity information respectively corresponding to each pixel in each sub-region according to an embodiment of the present invention;

[0034] Figure 9 Shows a schematic diagram of determining the log-polar coordinate descriptor of the target feature points according to an embodiment of the present invention;

[0035] Figure 10 Shows a schematic block diagram of a remote sensing image registration device according to an embodiment of the present invention;

[0036] Figure 11 Shows a schematic block diagram of an electronic device according to an embodiment of the present invention. Detailed implementation manners

[0037] In order to make the objectives, technical solutions and advantages of the present invention more obvious, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0038] To at least partially solve the above problems, a remote sensing image registration method is proposed. The method obtains the target feature points of the target image, where the target image includes the remote sensing image to be registered and the reference remote sensing image. Then, for each of the target images, according to the local energy and phase intensity of all scales and directions of the target image, the overall phase consistency feature of the target image is determined. After that, according to the overall phase consistency feature, the log-polar coordinate descriptor of the target feature points is determined. Finally, based on the log-polar coordinate descriptor of the target feature points, the remote sensing image to be registered and the reference remote sensing image are registered. The overall phase consistency feature of the target image enhances the response of the phase consistency information. Determining the log-polar coordinate descriptor of the target feature points according to the overall phase consistency feature can more accurately characterize the feature point information of the target feature points, so that the image registration of the remote sensing image to be registered can be more accurately performed.

[0039] Figure 1 FIG. shows a schematic flowchart of a remote sensing image registration method according to an embodiment of the present invention. As Figure 1 shown, the remote sensing image registration method may include steps S110 to S140.

[0040] In step S110, the target feature points of the target image are obtained, and the target image includes the remote sensing image to be registered and the reference remote sensing image.

[0041] The target feature points of the target image may include multiple types of feature points, such as corner points, blobs, edge feature points, corner feature points, etc.

[0042] The feature extraction algorithm can be used to detect the remote sensing image to be registered and the reference remote sensing image respectively to obtain the target feature points in the remote sensing image to be registered and the reference remote sensing image respectively. Alternatively, after obtaining the target feature points, the target feature points can be screened and updated to obtain the desired target feature points in the remote sensing image to be registered and the reference remote sensing image respectively.

[0043] In step S120, for each of the target images, according to the local energy and phase intensity of all scales and directions of the target image, the overall phase consistency feature of the target image is determined.

[0044] Each in the target image can be any suitable remote sensing image acquired by an infrared remote sensing device. Exemplarily, the target image can be an image in the form of an RGB image, a grayscale image, a binary image, etc. The target image can be a static image or any video frame in a dynamic video. The target image can be an image of any suitable size and suitable resolution. The target image can be the original image directly collected by a remote sensing sensor or an image after preprocessing operations on the original image. The preprocessing operations can include all operations for improving the visual effect of the target image, enhancing its clarity, or highlighting certain features in the image. Exemplarily but not restrictively, the preprocessing operations can include operations such as digitization, geometric transformation, normalization, filtering, etc. of the original image. Without affecting subsequent image processing, the target image can also be a synthesized image. Among them, the reference remote sensing image serves as the reference image, and the remote sensing image to be registered serves as the image to be registered.

[0045] The target image can be analyzed at multiple scales through filters of different sizes or pyramid representations, and directional filters (such as Gabor filters) can be used to capture information in different directions. For each combination of scale and direction, the local energy at each combination of scale and direction can be calculated separately. The local energy under the combination of a single scale and a single direction cannot well reflect the texture characteristics of the entire target image, so it is necessary to obtain the local energy of multiple scales and directions of the target image. The number of directions and scales is not limited here.

[0046] Techniques such as Gabor filters or multi-scale wavelet transforms can be used to analyze the target image to capture information at different scales and directions, and calculate the corresponding phase intensity to obtain the phase intensity of the target image at multiple scales and directions.

[0047] After obtaining the local energy and phase intensity at multiple scales and directions, the local energy of all scales and directions can be added to obtain a first addition result, and the phase intensity of all scales and directions can be added to obtain a second addition result. Then, based on the first addition result and the second addition result, the overall phase consistency feature of the target image is determined. The overall phase consistency feature obtained in this way enhances the sum response of the phase consistency information and can better reflect the complete image information in the target image.

[0048] Exemplarily, the overall phase consistency feature of the target image can be determined according to the following formula 1:

[0049]

[0050] Where PC FA represents the overall phase consistency feature of the target image, ∑ s ∑ oEnergy s,o Represents the sum of local energies (the first summation result) for all scales and directions, ∑ s ∑ o An s,o Represents the sum of phase intensities (the second summation result) for all scales and directions, where s is the scale, o is the direction, and ξ is a bias term.

[0051] Exemplarily, the above local energy can be a weighted and noise-compensated local energy.

[0052] Step S130: Determine the log-polar coordinate descriptor of the target feature points according to the overall phase consistency feature.

[0053] Based on the overall phase consistency feature and other relevant information (such as gradient direction), a log-polar coordinate descriptor can be generated for each target feature point. This descriptor can characterize the properties of each target feature point, thereby distinguishing each target feature point. It can be understood that different target feature points will have different properties due to their positions, the texture of the surrounding image regions, and other image information. The log-polar coordinate descriptor can accurately distinguish each target feature point.

[0054] Step S140: Register the remotely sensed image to be registered and the reference remotely sensed image according to the log-polar coordinate descriptor of the target feature points.

[0055] The log-polar coordinate descriptors of each target feature point between the remotely sensed image to be registered and the reference remotely sensed image can be compared separately. When the similarity between a certain log-polar coordinate descriptor in the remotely sensed image to be registered and a certain log-polar coordinate descriptor in the reference remotely sensed image meets the condition, it indicates that these two target feature points correspond. The remotely sensed image to be registered and the reference remotely sensed image can be registered according to each pair of corresponding target feature points.

[0056] In the above technical solution, the target feature points of the target image are obtained. The target image includes the remotely sensed image to be registered and the reference remotely sensed image. Then, for each of the target images, according to the local energies and phase intensities of all scales and directions of the target image, the overall phase consistency feature of the target image is determined. After that, according to the overall phase consistency feature, the log-polar coordinate descriptor of the target feature points is determined. Finally, according to the log-polar coordinate descriptor of the target feature points, the remotely sensed image to be registered and the reference remotely sensed image are registered. The overall phase consistency feature of the target image enhances the response of the phase consistency information. Determining the log-polar coordinate descriptor of the target feature points according to the overall phase consistency feature can more accurately characterize the feature point information of the target feature points. In this way, the image registration of the remotely sensed image to be registered can be performed more accurately.

[0057] Figure 2The figure shows a schematic flowchart of a method for obtaining target feature points of a target image according to an embodiment of the present invention. As Figure 2 shown, the above step S110 may include steps S210 to S240.

[0058] In step S210, for each of the target images, the minimum distance and the maximum distance are determined according to the phase intensity response of the target image.

[0059] The phase intensity responses in different directions and scales of the target image can be extracted by using a Gabor filter or a multi-scale wavelet transform, etc.

[0060] The following takes the Gabor filter as an example for illustration. The Fourier transform is performed on the target image to be extracted with features to obtain the frequency-domain image of the target image. After setting the direction and scale, the 2D Log-Gabor filtering can be performed on the frequency-domain image by using the Gabor filter to obtain the odd-symmetric components and even-symmetric components in different directions and scales in the frequency domain. Then, the inverse Fourier transform is performed on the odd-symmetric components and even-symmetric components in different directions and scales in the frequency domain to obtain the odd-symmetric components and even-symmetric components in the spatial domain. Finally, the phase intensity response (intensity component) can be calculated based on the odd-symmetric components and even-symmetric components in the spatial domain.

[0061] Exemplarily, the phase intensity response can be calculated by using the following formula 2:

[0062]

[0063] where An s,o is the phase intensity response (intensity component), s is the scale, o is the direction, E s,o is the even-symmetric component in the spatial domain, O s,o is the odd-symmetric component in the spatial domain.

[0064] After obtaining the phase intensity response (intensity component), the phase consistency information in each direction can be calculated based on the intensity component, the weighted sum in the direction, and the local energy of noise compensation. Then, the phase consistency moment can be calculated according to the phase consistency information to obtain the maximum moment and the minimum moment of the target image.

[0065] Exemplarily, the phase consistency information in each direction can be determined according to the following formula 3:

[0066]

[0067] where PC(θ) is the phase consistency information in each direction, Energy(θ)s is the weighted sum in each direction and the local energy of noise compensation, ∑ s An s,o($\theta$) is the sum of the phase intensity responses (intensity components) in all directions.

[0068] Exemplarily, after obtaining the phase consistency information in each direction, the maximum moment and the minimum moment can be determined according to the following formulas 3 to 7:

[0069] a = ∑ o (PC($\theta$)cos($\theta$)) 2 Formula 3

[0070] b = 2∑ o (PC($\theta$)cos($\theta$)) × (PC($\theta$)sin($\theta$)) Formula 4

[0071] c = ∑ o (PC($\theta$)sin($\theta$)) 2 Formula 5

[0072]

[0073] Wherein, a, b, and c are intermediate covariance data in the phase consistency moment calculation, M max and M min are the maximum moment and the minimum moment respectively.

[0074] In step S220, according to the minimum distance, the first corner feature points are extracted from the target image.

[0075] Any feature extraction algorithm can be used to extract the first corner feature points from the target image according to the minimum distance. Among them, the feature extraction algorithm can include FAST, SUPER, SIFT, etc.

[0076] In step S230, according to the maximum distance, the first edge feature points are extracted from the target image.

[0077] Any feature extraction algorithm can be used to extract the first edge feature points from the target image according to the minimum distance. Among them, the feature extraction algorithm can include FAST, SUPER, SIFT, etc.

[0078] The feature extraction algorithms for extracting the first corner feature points and the first edge feature points can be the same or different. For example, the FAST feature extractor can be used to extract the first corner feature points, and the SUPER feature extractor can be used to extract the first edge feature points. Another example is that the FAST feature extractor can be used to extract both the first edge feature points and the first corner feature points.

[0079] In step S240, the target feature points of the target image are determined among the first edge feature points and the first corner feature points.

[0080] The first edge feature points and the first corner feature points extracted may not meet the expectations and need to be screened again. For example, when the distance, confidence level, quantity, etc. between the extracted first edge feature points and the first corner feature points do not meet the expectations, the first edge feature points and the first corner feature points can be screened according to the corresponding expected conditions to obtain feature points that meet the expectations.

[0081] In the above technical solution, for each of the target images, according to the phase intensity response of the target image, the minimum distance and the maximum distance are determined, and then according to the minimum distance and the minimum moment, the first corner feature points and the first edge feature points are respectively extracted from the target image, and finally the target feature points of the target image are determined from the first edge feature points and the first corner feature points. In this way, by combining the phase consistency information of the target image, the edge feature points and the corner feature points can be merged to obtain the target feature points representing the combined edge and corner features, which can improve the quality of the target feature points.

[0082] Figure 3 FIG. shows a schematic flowchart of determining the target feature points of the target image from the first edge feature points and the first corner feature points according to an embodiment of the present invention. As Figure 3 shown, the above step S240 may include steps S310 to S340.

[0083] In step S310, obtain the confidence level of each first edge feature point and the confidence level of each first corner feature point.

[0084] The feature point detection algorithm can be used to detect the feature points of the target image to determine the initial feature points of the target image and the confidence level of each initial feature point, that is, when extracting each first edge feature point and each first corner feature point, the confidence level of each first edge feature point and the confidence level of each first corner feature point are respectively determined.

[0085] In step S320, divide the target image into multiple regions.

[0086] The multiple regions can be regions of the same size or regions of different sizes. The multiple regions can be regions of a fixed size or the size of each region can be determined according to the density of the first edge feature points and the first corner feature points determined in the target image. Among them, the greater the density, the smaller each region can be; the smaller the density, the larger each region can be.

[0087] In step S330, for each region, determine the first feature points and the second feature points in the region respectively. Among them, the first feature points include the first edge feature points with the highest confidence in the region, and the distance between the first feature points in the region is not less than the first distance threshold. The second feature points include the first corner feature points with the highest confidence in the region, and the distance between the second feature points in the region is not less than the first distance threshold.

[0088] Optionally, the confidence levels between every two first edge feature points in the region can be compared, and the smaller one of the two first edge feature points with a distance less than the first distance threshold can be removed until the distance between any two first edge feature points in the region is not less than the first distance threshold. The unremoved first edge feature points are used as the first feature points. Similar operations are performed on the first corner feature points to obtain the unremoved first corner feature points as the second feature points.

[0089] Optionally, starting from the first edge feature point with the highest confidence value, all first edge feature points with a distance less than the first distance threshold from this first edge feature point can be removed. Then, starting from the remaining first edge feature point with the highest confidence, this process can be repeated until the distance between any two first edge feature points is not less than the first distance threshold. The unremoved first edge feature points are used as the first feature points. Similar operations are performed on the first corner feature points to obtain the unremoved first corner feature points as the second feature points.

[0090] In step S340, select the target feature points of the target image from the first feature points and the second feature points.

[0091] Exemplarily, a confidence threshold can be set to remove the first feature points and the second feature points with a confidence less than the confidence threshold, and then the remaining first feature points and second feature points are used as the target feature points of the target image.

[0092] Exemplarily, a quantity threshold can also be set to only retain the first feature points and the second feature points with the highest confidence and not less than the quantity threshold, and then the retained first feature points and second feature points are used as the target feature points of the target image.

[0093] Exemplarily, the confidence levels of each first feature point and second feature point can also be normalized respectively to obtain the normalized confidence levels corresponding to each first feature point and second feature point. Then, the first feature points and second feature points with a confidence less than the normalized confidence threshold are removed, and the remaining first feature points and second feature points are used as the target feature points of the target image.

[0094] In the above technical solution, the confidence of each first edge feature point and the confidence of each first corner feature point are obtained, and the target image is divided into multiple regions. Then, for each region, the first feature points and the second feature points in the region are respectively determined. Among them, the first feature points include the first edge feature point with the highest confidence in the region, and the distance between the first feature points in the region is not less than the first distance threshold. The second feature points include the first corner feature point with the highest confidence in the region, and the distance between the second feature points in the region is not less than the first distance threshold. Finally, the target feature points of the target image are selected from the first feature points and the second feature points. In this way, the obtained feature points can be screened to obtain high-quality target feature points.

[0095] Figure 4 FIG. shows a schematic flowchart of extracting the first corner feature points from the target image according to the minimum distance according to an embodiment of the present invention. As Figure 4 shown, the above step S220 may include steps S410 to S430.

[0096] In step S410, using the FAST feature extractor, the second corner feature points are determined according to the minimum distance.

[0097] In step S420, using the SIFT feature extractor, the third corner feature points are determined according to the minimum distance.

[0098] In step S430, the same points among the second corner feature points and the third corner feature points are determined as the first corner feature points.

[0099] The FAST feature extractor is the FAST feature point detection algorithm, and the SIFT feature extractor is the SIFT feature point detection algorithm. By using different feature point detection algorithms, second corner feature points and third corner feature points with different characteristics can be obtained. Then, the same points are determined from the second corner feature points and the third corner feature points as the first corner feature points. In this way, the advantages of the two feature point detection algorithms can be combined to obtain better first corner feature points.

[0100] In the above technical solution, the second corner feature points are determined according to the minimum distance using the FAST feature extractor, and the third corner feature points are determined according to the minimum distance using the SIFT feature extractor. Then, the same points among the second corner feature points and the third corner feature points are determined as the first corner feature points. In this way, better first corner feature points can be extracted.

[0101] Figure 5 FIG. shows a schematic flowchart of extracting the first edge feature points from the target image according to the maximum distance according to an embodiment of the present invention. As Figure 5 shown, the above step S230 may include steps S510 to S530.

[0102] In step S510, using a FAST feature extractor, determine the second edge feature points according to the maximum distance.

[0103] In step S520, using a SIFT feature extractor, determine the third edge feature points according to the maximum distance.

[0104] In step S530, determine the same points among the second edge feature points and the third edge feature points as the first edge feature points.

[0105] Similar to the above steps S410 to S420, by using different feature point detection algorithms, second edge feature points and third edge feature points with different characteristics can be obtained. Then, determine the same points among the second edge feature points and the third edge feature points as the first edge feature points. In this way, the advantages of the two feature point detection algorithms can be combined to obtain better first edge feature points. Details are not described here.

[0106] In the above technical solution, use a FAST feature extractor to determine the second edge feature points according to the minimum distance, and use a SIFT feature extractor to determine the third edge feature points according to the minimum distance. Then, determine the same points among the second edge feature points and the third edge feature points as the first edge feature points. In this way, better first edge feature points can be extracted.

[0107] Optionally, the SIFT feature extractor for extracting the third corner feature points and the third edge feature points can also be replaced by other feature extractors, such as SURF, ORB, etc.

[0108] Exemplarily, the above steps S410 to S430 and the above steps S510 to S530 can be combined to obtain better first edge feature points and first corner feature points.

[0109] Figure 6 Shows a schematic flowchart of a log-polar coordinate descriptor for determining target feature points according to the overall phase consistency feature according to an embodiment of the present invention. As Figure 6 shown, the above step S130 may include steps S610 to S630.

[0110] In step S610, perform a convolution operation on the target image using an odd filter to obtain the overall phase direction feature of the target image.

[0111] The direction of the odd filter (such as a Gabor filter) can be set first, and then the target image is convolved using the odd filter to obtain convolution results in different directions. Then, according to the phase direction features of each direction and scale of the target image, the overall phase direction feature of the target image can be obtained.

[0112] Exemplarily, the overall phase direction feature of the target image can be determined according to the following formula 8.

[0113]

[0114] Wherein, Sum odd (θ) represents the sum of the convolution results obtained by the odd filter operation in the direction θ, and PO represents the overall phase direction feature. The overall phase direction feature of the target image represents the angular information of the local directions corresponding to all the pixels of the target image respectively.

[0115] Exemplarily, when PO is less than 0, adding π is used to eliminate the forward angle reversal caused by convolution.

[0116] In step S620, according to the position of the neighborhood of each target feature point and the overall phase consistency feature, the first phase consistency feature of the neighborhood of each target feature point is determined, wherein, for each target feature point, the pixel where the target feature point is located is the central pixel of the neighborhood of the target feature point.

[0117] The neighborhood of the target feature point can be in the shape of a regular figure such as a circle or a rectangle for the convenience of calculation. Among them, when the neighborhood of the target feature point is a circle, it is more conducive to determining the log-polar coordinate descriptor.

[0118] The neighborhood of the target feature point can be of a preset size, for example, it can be a circle with a diameter of 33 pixels.

[0119] The position of the neighborhood of each target feature point can be determined according to the edge coordinates of the neighborhood of the target feature point. For example, when the neighborhood of the target feature point is a circle with a diameter of 33 pixels, the leftmost edge coordinate is (a, b), the uppermost edge coordinate is (c, d), then the rightmost edge coordinate is (a + 32, b), and the lowermost edge coordinate is (c, d - 32). According to these 4 coordinates, the position of the circular neighborhood of the target feature point and the pixels in this neighborhood can be determined.

[0120] The overall phase consistency feature represents the phase consistency information of each feature point of the target image. Therefore, according to the position of the neighborhood of each target feature point, the local phase consistency feature corresponding to the pixels in each neighborhood can be determined as the first phase consistency feature.

[0121] In step S630, according to the position of the neighborhood of each target feature point and the overall phase direction feature, the first phase direction feature of the neighborhood of each target feature point is determined.

[0122] Similar to step S640, it will not be elaborated here.

[0123] In step S640, for each target feature point, according to the first phase consistency feature and the first phase direction feature of the neighborhood of the target feature point, the logarithmic polar coordinate descriptor of the target feature point is determined.

[0124] The logarithmic polar coordinate descriptor of each target feature point can be determined by mapping the image of the neighborhood of each target feature point into the polar exponential space, and according to the pixels, the first phase consistency feature, and the first phase direction feature in the neighborhood of the target feature point in the polar exponential space.

[0125] Exemplarily, the logarithmic polar coordinate descriptor can be data in vector form, and the number of elements of the vector can be determined according to the number of local directions represented by the first phase direction feature and the number of sub-regions of the neighborhood of the target feature point. The data in each element represents the sum of the intensities of the phase consistency information (the first phase consistency feature) of each pixel in the same local direction in the corresponding sub-region. The intensity of the phase consistency information represents the phase consistency intensity information.

[0126] In the above technical solution, the target image is convolved using an odd filter to obtain the overall phase direction feature of the target image, and then according to the position of the neighborhood of each target feature point and the overall phase consistency feature, the first phase consistency feature of the neighborhood of each target feature point is determined. Among them, for each target feature point, the pixel where the target feature point is located is the central pixel of the neighborhood of the target feature point. Then, according to the position of the neighborhood of each target feature point and the overall phase direction feature, the first phase direction feature of the neighborhood of each target feature point is determined. Finally, for each target feature point, according to the first phase consistency feature and the first phase direction feature of the neighborhood of the target feature point, the logarithmic polar coordinate descriptor of the target feature point is determined. In this way, the overall phase consistency feature and the overall phase direction feature can be combined to determine a descriptor that can accurately describe the target feature point.

[0127] Figure 7 FIG. shows a schematic flowchart of determining the logarithmic polar coordinate descriptor of the target feature point according to the first phase consistency feature and the first phase direction feature of the neighborhood of the target feature point according to an embodiment of the present invention. As Figure 7 shown, the above step S130 may include steps S710 to S730.

[0128] In step S710, the neighborhood of the target feature point is divided into a plurality of sub-regions.

[0129] Exemplarily, the areas of the plurality of sub-regions are equal.

[0130] When the areas of the plurality of sub-regions are equal, it is possible to avoid calculation errors caused by different amounts of image information contained in each sub-region.

[0131] In step S720, for each sub-region, according to the first phase consistency feature and the first phase direction feature of the neighborhood of the target feature point, the local direction and the phase consistency intensity information corresponding to each pixel in the sub-region are determined respectively.

[0132] For each sub-region, the pixels in the sub-region can be determined according to the position of the sub-region, and the local direction and the phase consistency intensity information corresponding to each pixel in the sub-region are determined respectively. Here, reference can be made to the above step S620, which will not be elaborated here.

[0133] In step S730, according to the local direction and the phase consistency intensity information corresponding to each pixel in each sub-region, the logarithmic polar coordinate descriptor of the target feature point is determined.

[0134] The logarithmic polar coordinate descriptor of the target feature point can be determined by mapping the image of each sub-region into the polar exponential space and according to the pixels in the sub-region in the polar exponential space, the local direction and the phase consistency intensity information corresponding to each pixel respectively.

[0135] Exemplarily, the logarithmic polar coordinate descriptor can be data in vector form, and the number of elements of the vector can be determined according to the number of local directions corresponding to each pixel in the sub-region and the total number of sub-regions. The data in each element respectively represents the intensity of the phase consistency information of each pixel in the same local direction in the corresponding sub-region.

[0136] In the above technical solution, the neighborhood of the target feature point is divided into multiple sub-regions, and then for each sub-region, according to the first phase consistency feature and the first phase direction feature of the neighborhood of the target feature point, the local direction and the phase consistency intensity information corresponding to each pixel in the sub-region are determined respectively. Finally, according to the local direction and the phase consistency intensity information corresponding to each pixel in each sub-region, the logarithmic polar coordinate descriptor of the target feature point is determined. In this way, the neighborhood of the target feature point can be refined to obtain a more accurate logarithmic polar coordinate descriptor, which is more conducive to image registration.

[0137] Figure 8 Shows a schematic flowchart of determining the logarithmic polar coordinate descriptor of the target feature point according to the local direction and the phase consistency intensity information corresponding to each pixel in each sub-region according to an embodiment of the present invention. As Figure 8 shown, the above step S730 may include steps S810 to S830.

[0138] In step S810, for the pixels in each sub-region, the pixels in the sub-region are determined as pixels corresponding to different local direction ranges according to the local direction corresponding to each pixel respectively.

[0139] Each local direction range may include multiple local directions. For example, the local direction can be any direction within 360 degrees. The local direction can be divided into multiple consecutive interval ranges as the local direction range. Then, the local direction corresponding to each pixel is divided into the local direction range to which it belongs. For example, when there is a local direction range of 0 to 45 degrees and the local direction corresponding to a certain pixel is 30 degrees, this pixel can be classified as a pixel within the local direction range of 0 to 45 degrees.

[0140] In step S820, for each local direction range, the phase consistency intensity information of the pixels corresponding to this local direction range is added up to obtain the second phase consistency feature of the pixels corresponding to this local direction range.

[0141] In step S830, according to the second phase consistency features of the pixels corresponding to different local direction ranges in each sub-region, the log-polar coordinate descriptor of this target feature point is determined.

[0142] The log-polar coordinate descriptor can be represented by a vector. The second phase consistency features of the pixels in different local direction ranges can be used as each element in the log-polar coordinate descriptor respectively, and then the log-polar coordinate descriptor of this target feature point is obtained.

[0143] Exemplarily, before determining each element in the log-polar coordinate descriptor, a weight coefficient can also be determined according to the distance between the sub-region and the target feature point. Among them, the higher the weight coefficient of the pixels in the same local direction within the sub-region closer to the target feature point. The second phase consistency feature weighted by this weight coefficient is used as the value of each element in the log-polar coordinate descriptor.

[0144] In the above technical solution, for the pixels in each sub-region, according to the local direction corresponding to each pixel, the pixels in this sub-region are determined as pixels corresponding to different local direction ranges. Then, for each local direction range, the phase consistency intensity information of the pixels corresponding to this local direction range is added up to obtain the second phase consistency feature of the pixels corresponding to this local direction range. Finally, according to the second phase consistency features of the pixels corresponding to different local direction ranges in each sub-region, the log-polar coordinate descriptor of this target feature point is determined. In this way, the local direction can be discretized, reducing the amount of data required for determining the log-polar coordinate descriptor.

[0145] Figure 9 Shows a schematic diagram of determining the log-polar coordinate descriptor of a target feature point according to an embodiment of the present invention. As Figure 9As shown, after determining the overall phase consistency feature and the overall phase orientation feature of the target image, the neighborhood of the target feature point P(x, y) can be divided into 32 sub-regions with the same area size, and the 8 local direction ranges corresponding to the pixels in each sub-region are determined. The local direction range to which each pixel belongs is determined according to the 8 local direction ranges. Then, according to the 32 sub-regions and the 8 local direction ranges, a 256-bit log-polar coordinate descriptor is determined. The polar coordinate descriptor can be represented in vector form, and each element represents the sum of the intensity values of the phase consistency information corresponding to the pixels in the same local direction range within the sub-region.

[0146] Figure 10 FIG. shows a schematic block diagram of a remote sensing image registration device according to an embodiment of the present invention. As Figure 10 shown, the remote sensing image registration device includes a feature point acquisition module 1010, a feature determination module 1020, a description module 1030, and a registration module 1040.

[0147] The feature point acquisition module 1010 is used to acquire the target feature points of the target image, and the target image includes the remote sensing image to be registered and the reference remote sensing image.

[0148] The feature determination module 1020 is used to determine the overall phase consistency feature of each target image according to the local energy and phase intensity of all scales and directions of the target image.

[0149] The description module 1030 is used to determine the log-polar coordinate descriptor of the target feature point according to the overall phase consistency feature.

[0150] The registration module 1040 is used to register the remote sensing image to be registered and the reference remote sensing image according to the log-polar coordinate descriptor of the target feature point.

[0151] Exemplarily, the feature point acquisition module 1010 includes a first determination sub-module, a first extraction sub-module, a second extraction sub-module, and a second determination sub-module. The first determination sub-module is used to determine the minimum distance and the maximum distance for each target image according to the phase intensity response of the target image. The second extraction sub-module is used to extract the first corner feature points from the target image according to the minimum distance. The third extraction sub-module is used to extract the first edge feature points from the target image according to the maximum distance. The second determination sub-module is used to determine the target feature points of the target image from the first edge feature points and the first corner feature points.

[0152] Exemplarily, the second determination sub-module includes a first acquisition sub-module, a first division sub-module, a third determination sub-module, and a first selection sub-module. The first acquisition sub-module is configured to acquire the confidence of each first edge feature point and the confidence of each first corner feature point. The first division sub-module is configured to divide the target image into a plurality of regions. The third determination sub-module is configured to, for each region, respectively determine the first feature points and the second feature points in the region, where the first feature points include the first edge feature point with the highest confidence in the region, and the distance between the first feature points in the region is not less than a first distance threshold, and the second feature points include the first corner feature point with the highest confidence in the region, and the distance between the second feature points in the region is not less than the first distance threshold. The first selection sub-module is configured to select the target feature points of the target image from the first feature points and the second feature points.

[0153] Exemplarily, the first extraction sub-module includes a first feature extraction sub-module, a second feature extraction sub-module, and a corner feature point determination sub-module; and / or the second extraction sub-module includes a third feature extraction sub-module, a fourth feature extraction sub-module, and an edge feature point determination sub-module. The first feature extraction sub-module is configured to use a FAST feature extractor to determine a second corner feature point according to a minimum distance. The second feature extraction sub-module is configured to use a SIFT feature extractor to determine a third corner feature point according to the minimum distance. The corner feature point determination sub-module is configured to determine the same points among the second corner feature points and the third corner feature points as the first corner feature points. The third feature extraction sub-module is configured to use a FAST feature extractor to determine a second edge feature point according to a maximum distance. The fourth feature extraction sub-module is configured to use a SIFT feature extractor to determine a third edge feature point according to the maximum distance. The edge feature point determination sub-module is configured to determine the same points among the second edge feature points and the third edge feature points as the first edge feature points.

[0154] Exemplarily, the description module 1030 includes a convolution sub-module, a first phase congruency feature determination sub-module, a first phase direction feature determination sub-module, and a first descriptor determination sub-module. The convolution sub-module is used to perform a convolution operation on the target image using an odd filter to obtain the overall phase direction feature of the target image. The first phase congruency feature determination sub-module is used to determine the first phase congruency feature of the neighborhood of each target feature point according to the position of the neighborhood of each target feature point and the overall phase congruency feature, wherein, for each target feature point, the pixel where the target feature point is located is the central pixel of the neighborhood of the target feature point. The first phase direction feature determination sub-module is used to determine the first phase direction feature of the neighborhood of each target feature point according to the position of the neighborhood of each target feature point and the overall phase direction feature. The first descriptor determination sub-module is used to determine the log-polar coordinate descriptor of each target feature point according to the first phase congruency feature and the first phase direction feature of the neighborhood of the target feature point.

[0155] The first descriptor determination sub-module includes a second division sub-module, a pixel analysis sub-module, and a second descriptor determination sub-module. The second division sub-module is used to divide the neighborhood of the target feature point into a plurality of sub-regions. The pixel analysis sub-module is used to determine the local direction and phase congruency intensity information corresponding to each pixel of each sub-region according to the first phase congruency feature and the first phase direction feature of the neighborhood of the target feature point. The second descriptor determination sub-module is used to determine the log-polar coordinate descriptor of the target feature point according to the local direction and phase congruency intensity information corresponding to each pixel in each sub-region.

[0156] Exemplarily, the areas of the plurality of sub-regions are equal.

[0157] Exemplarily, the second descriptor determination sub-module includes a pixel assignment sub-module, a second phase congruency feature determination sub-module, and a third descriptor determination sub-module. The pixel assignment sub-module is used to determine the pixels in each sub-region as pixels corresponding to different local direction ranges according to the local direction corresponding to each pixel. The second phase congruency feature determination sub-module is used to add the phase congruency intensity information of the pixels corresponding to the local direction range for each local direction range to obtain the second phase congruency feature of the pixels corresponding to the local direction range. The third descriptor determination sub-module is used to determine the log-polar coordinate descriptor of the target feature point according to the second phase congruency features of the pixels corresponding to different local direction ranges in each sub-region.

[0158] According to another aspect of the present invention, an electronic device is further provided. Figure 11 A schematic block diagram of an electronic device according to an embodiment of the present invention is shown. AsFigure 11 As shown, the electronic device includes a processor and a memory. Among them, computer program instructions are stored in the memory, and when the computer program instructions are run by the processor, they are used to execute the remote sensing image registration method as described above.

[0159] In addition, according to another aspect of the present invention, a storage medium is also provided. Program instructions are stored on the storage medium, and when the program instructions are run by a computer or a processor, the computer or the processor is caused to execute the corresponding steps of the above-mentioned remote sensing image registration method of the embodiments of the present invention, and is used to implement the corresponding modules in the above-mentioned remote sensing image registration device according to the embodiments of the present invention. The storage medium may, for example, include a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0160] According to another aspect of the present invention, a computer program product is also provided, including computer program instructions, and the computer program instructions are used to execute the above-mentioned remote sensing image registration method when running.

[0161] Those of ordinary skill in the art can understand the specific implementation and beneficial effects of the above-mentioned remote sensing image registration device, electronic device, storage medium, and computer program product by reading the above specific description of the remote sensing image registration method. For the sake of brevity, it will not be elaborated here.

[0162] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present invention thereto. Those of ordinary skill in the art can make various changes and modifications therein without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as claimed in the appended claims.

[0163] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0164] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0165] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0166] Similarly, it should be understood that, in order to streamline the present invention and assist in understanding one or more of the various inventive aspects, in the description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present invention should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected by the corresponding claims, the inventive point lies in that the corresponding technical problems can be solved by features less than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, where each claim itself serves as a separate embodiment of the present invention.

[0167] Those skilled in the art can understand that, except for features that are mutually exclusive, any combination can be adopted for all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0168] In addition, those skilled in the art can understand that, although some of the embodiments described herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0169] Each component embodiment of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules in the remote sensing image registration device according to the embodiments of the present invention. The present invention can also be implemented as a device program (for example, a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0170] It should be noted that the above embodiments illustrate the present invention rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0171] As described above, it is only the specific implementation manner of the present invention or the description of the specific implementation manner. The protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all of them should be covered by the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A remote sensing image registration method, characterized in that: The method comprises: Acquire target feature points of a target image, wherein the target image includes a remote sensing image to be registered and a reference remote sensing image; For each of the target images, determining an overall phase consistency feature of the target image based on the local energy and phase intensity of all scales and directions of the target image; Determining a log polar coordinate descriptor of a target feature point according to the overall phase consistency feature; The remote sensing image to be registered and the reference remote sensing image are registered according to the logarithmic polar coordinate descriptor of the target feature point.

2. The method according to claim 1, characterized in that: The step of acquiring target feature points of a target image comprises: For each of the target images, Determine the minimum distance and the maximum distance according to the phase intensity response of the target image; Extracting a first corner feature point from the target image according to the minimum distance; Extracting a first edge feature point from the target image according to the maximum distance; A target feature point of the target image is determined among the first edge feature points and the first corner feature points.

3. The method according to claim 2, characterized in that The step of determining the target feature point of the target image from the first edge feature point and the first corner feature point comprises: Obtaining the confidence of each first edge feature point and the confidence of each first corner feature point; Dividing the target image into a plurality of regions; For each region, respectively determine the first feature point and the second feature point in the region, wherein the first feature point includes the first edge feature point with the highest confidence in the region, and the distance between the first feature points in the region is not less than the first distance threshold, and the second feature point includes the first corner feature point with the highest confidence in the region, and the distance between the second feature points in the region is not less than the first distance threshold; A target feature point of the target image is selected from the first feature point and the second feature point.

4. The method according to claim 2, characterized in that: The extracting the first corner feature point from the target image according to the minimum distance comprises: Using a FAST feature extractor, determining a second corner feature point according to the minimum distance; Using a SIFT feature extractor, determining a third corner feature point according to the minimum distance; Determine the same point between the second corner feature point and the third corner feature point as the first corner feature point; and / or The extracting a first edge feature point from the target image according to the maximum distance comprises: Using a FAST feature extractor, determining a second edge feature point according to the maximum distance; Using a SIFT feature extractor, determining a third edge feature point according to the maximum distance; The same point between the second edge feature point and the third edge feature point is determined as the first edge feature point.

5. The method according to claim 1, characterized in that Determining the logarithmic polar coordinate descriptor of the target feature point according to the overall phase consistency feature includes: Performing a convolution operation on the target image using an odd-numbered filter to obtain an overall phase direction feature of the target image; Determine a first phase consistency feature of the domain of each target feature point according to the position of the domain of each target feature point and the overall phase consistency feature, wherein, for each target feature point, the pixel where the target feature point is located is the central pixel of the domain of the target feature point; Determine a first phase direction feature of the field of each target feature point according to the position of the field of each target feature point and the overall phase direction feature; For each target feature point, a log polar coordinate descriptor of the target feature point is determined according to a first phase consistency feature and a first phase direction feature of a domain of the target feature point.

6. The method according to claim 5, characterized in that The step of determining the logarithmic polar coordinate descriptor of the target feature point according to the first phase consistency feature and the first phase direction feature of the field of the target feature point comprises: Divide the area of ​​the target feature point into multiple sub-areas; For each sub-region, determine the local direction and phase consistency strength information corresponding to each pixel of the sub-region according to the first phase consistency feature and the first phase direction feature of the field of the target feature point; According to the local direction and phase consistency strength information corresponding to each pixel in each sub-region, the logarithmic polar coordinate descriptor of the target feature point is determined.

7. The method according to claim 6, characterized in that The multiple sub-regions have equal areas.

8. The method according to claim 6, characterized in that The step of determining the logarithmic polar coordinate descriptor of the target feature point according to the local direction and phase consistency strength information respectively corresponding to each pixel in each sub-region comprises: For pixels in each sub-region, the pixels in the sub-region are determined as pixels corresponding to different local direction ranges according to the local directions corresponding to each pixel; For each local direction range, adding phase consistency intensity information of pixels corresponding to the local direction range to obtain a second phase consistency feature of the pixels corresponding to the local direction range; The logarithmic polar coordinate descriptor of the target feature point is determined according to the second phase consistency features of the pixels in each sub-region respectively corresponding to different local direction ranges.

9. A remote sensing image registration device, characterized in that: include: A feature point acquisition module, used to acquire target feature points of a target image, wherein the target image includes a remote sensing image to be registered and a reference remote sensing image; A feature determination module, for determining, for each of the target images, an overall phase consistency feature of the target image based on the local energy and phase intensity of all scales and directions of the target image; A description module, used for determining a logarithmic polar coordinate descriptor of a target feature point according to the overall phase consistency feature; The registration module is used to register the remote sensing image to be registered with the reference remote sensing image according to the logarithmic polar coordinate descriptor of the target feature point.

10. An electronic device comprising a processor and a memory, characterized in that: The memory stores computer program instructions, which are used by the processor to execute the remote sensing image registration method according to any one of claims 1 to 8 when the processor runs the computer program instructions.

11. A storage medium having program instructions stored thereon, characterized in that: The program instructions are used to execute the remote sensing image registration method according to any one of claims 1 to 8 when running.

12. A computer program product comprising computer program instructions, characterized in that The computer program instructions are used to execute the remote sensing image registration method according to any one of claims 1 to 8 when running.

Images