Space target attitude model searching and matching method for optical-radar co-location observation

Abstract

The invention discloses a space target attitude model searching and matching method for optical-radar co-location observation, and relates to the technical field of space target attitude estimation, and the method comprises the steps: obtaining an optical image and an ISAR image under the same visual angle; determining an attitude angle in the optical image, determining a target neighborhood by taking the attitude angle as a reference and a 5-degree attitude angle as a constraint condition, and determining at least one target ISAR image corresponding to the target neighborhood and a corresponding target feature vector in the spatial target attitude model database; and determining a retrieval feature vector corresponding to the in-orbit space target according to the ISAR image, taking the target ISAR image corresponding to the target feature vector with the minimum Euclidean distance with the retrieval feature vector as a matching result, determining an attitude model corresponding to the target ISAR image, and outputting the attitude model as a search result. According to the method, the three-dimensional attitude information corresponding to the in-orbit space target can be quickly and accurately determined.

Description

Background Art

[0002] Instantaneous attitude estimation is of great significance for monitoring the flight status of on-orbit satellite targets and inverting satellite target intentions. Usually, the instantaneous attitude of a normally operating satellite target is kept relatively stable by the control system. However, once the satellite target loses control, its instantaneous attitude will change due to factors such as rotation and acceleration, resulting in the risk of satellite collision. Therefore, it is particularly important to accurately estimate the motion state of satellite targets, especially the instantaneous attitude. At present, the basic idea of ​​​​the study of space target attitude estimation is to select appropriate target features, and solve the attitude information through accurate target feature detection and establishing a matching relationship between target features, including point feature matching, contour feature matching, and line feature matching.

[0003] The main characteristic data of space target observation are optical images obtained by optical observation equipment and ISAR images obtained by radar. ISAR image sequences contain rich two-dimensional structural information of space targets in different postures and can be used to reconstruct the three-dimensional structure of space targets. Optical data is consistent with human subjective cognition, and the target texture it reflects is rich in details and has good interpretability.

[0004] Since the imaging principles of ISAR images and optical images are different, the target appears as discrete scattering points in the ISAR image. At the same time, the irregular scattering of radar electromagnetic waves at the edge of the target will also cause the edge of the target to be blurred. Therefore, the point features and contour features of the target are difficult to accurately detect from the ISAR image of the target; compared with point features and contour features, considering that the composition structure of space targets is simple and has many linear structural components, such as solar panels, rod antennas, etc., the line features of the target in the ISAR image are more prominent and easy to detect. In the prior art, for the ISAR image sequence of space targets, by extracting the line features of the linear structure of the space target, detecting the projection of the line features in the range and azimuth directions in the ISAR image, the attitude angle estimation of the main linear structural components of the space target is realized, and the problem of the difficulty in extracting nonlinear structural features on the space target is effectively avoided. The existing technology directly uses the projections of line features in the range and azimuth directions on the ISAR image for attitude estimation. Therefore, a complex line feature detection process is required to complete accurate line feature detection, which inevitably increases the complexity of the attitude estimation method. Therefore, how to complete the attitude estimation of space targets when the accuracy of line feature projection detection is not high is a difficult problem in current research.

[0005] For smoothly moving targets, the mapping relationship between the target's on-orbit attitude and ISAR image features is constructed based on the radar projection imaging principle, thereby converting the on-orbit attitude estimation problem of space targets into an optimization problem. A domestic team proposed a space target attitude estimation method based on line feature differential projection. By establishing a two-dimensional differential projection of the line feature under the measured ISAR image and the simulated image under the attitude estimation value, the absolute error of the line feature projection detection is converted into a relative error, which effectively reduces the impact of the line feature projection detection error on the attitude estimation, and further improves the accuracy of the on-orbit attitude parameter estimation of the space target. This method estimates the attitude based on the edge line features of the solar panel in the ISAR image of the space target. Therefore, when the solar panel part is missing in the ISAR image or the line features are not obvious, the algorithm proposed in the literature cannot accurately detect the line features, and the accurate estimation of the target's on-orbit attitude cannot be achieved. Summary of the invention

[0006] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide a method for searching and matching a spatial target attitude model for optical-radar co-site observation, which is as follows:

[0007] 1) In the first aspect, the present invention provides a method for searching and matching a spatial target attitude model for optical-radar co-site observation, and the specific technical scheme is as follows:

[0008] Acquire optical images and ISAR images of any space target on orbit from the same observation station perspective;

[0009] Performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine an attitude angle, determining a target neighborhood based on the attitude angle and a 5° attitude angle as a constraint, determining at least one target ISAR image corresponding to the target neighborhood in a space target attitude model database, and determining a target feature vector corresponding to each target ISAR image;

[0010] A retrieval feature vector corresponding to the on-orbit space target is determined according to the ISAR image, a target ISAR image corresponding to the target feature vector with the smallest Euclidean distance with the retrieval feature vector is taken as a matching result, a posture model corresponding to the target ISAR image is determined, and the posture model is output as a search result.

[0011] The beneficial effects of the space target attitude model search and matching method for optical-radar co-site observation provided by the present invention are as follows:

[0012] Firstly, the three-dimensional attitude of the sailboard structure of the space target in the optical image is estimated based on the surface-to-surface intersection method. Secondly, the radar ISAR image attitude model database is searched for the minimum distance matching in the 5° attitude angle neighborhood. Finally, the attitude model is determined. Using the attitude model to confirm the three-dimensional attitude information of the on-orbit space target can not only accurately obtain the corresponding attitude model and then confirm the three-dimensional attitude information, but also improve the confirmation efficiency of the three-dimensional attitude information.

[0013] Based on the above solution, the present invention can also be improved as follows.

[0014] Further, the process of performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle is specifically as follows:

[0015] The optical projection solution method is used to invert the direction vector, and the attitude angle is determined based on the direction vector.

[0016] Further, the process of determining the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image is specifically as follows:

[0017] Determine an N×N matrix M corresponding to the ISAR image, and determine a retrieval feature vector based on the matrix M, where N is the number of subcomponents in the on-orbit space target, and M ii is the ratio of the surface area of ​​the ith component to the maximum surface area, M ij =1-(d ij -d max ) 2 , d ij is the distance between the centroids of the i-th component and the j-th component, d max is the maximum centroid distance.

[0018] Further, the centroid distance is determined by the centroid coordinates of the two components, and the process of determining the centroid coordinates is:

[0019] The determination is performed based on the two-dimensional first-order moment of the ISAR image.

[0020] 2) In the second aspect, the present invention also provides a space target attitude model search and matching system for optical-radar co-site observation, and the specific technical solution is as follows:

[0021] The acquisition module is used to obtain optical images and ISAR images of any on-orbit space target at the same observation station viewing angle;

[0022] The preprocessing module is used to: perform three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle, determine the target neighborhood based on the attitude angle and the 5° attitude angle as a constraint condition, determine at least one target ISAR image corresponding to the target neighborhood in the space target attitude model database, and determine the target feature vector corresponding to each target ISAR image;

[0023] The search and matching module is used to: determine the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image, take the target ISAR image corresponding to the target feature vector with the smallest Euclidean distance with the retrieval feature vector as the matching result, determine the attitude model corresponding to the target ISAR image, and output the attitude model as the search result.

[0024] Based on the above solution, the present invention can also be improved as follows.

[0025] Further, the process of performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle is specifically as follows:

[0026] The optical projection solution method is used to invert the direction vector, and the attitude angle is determined based on the direction vector.

[0027] Further, the process of determining the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image is specifically as follows:

[0028] Determine an N×N matrix M corresponding to the ISAR image, and determine a retrieval feature vector based on the matrix M, where N is the number of subcomponents in the on-orbit space target, and M ii is the ratio of the surface area of ​​the ith component to the maximum surface area, M ij =1-(d ij -d max ) 2 , d ij is the distance between the centroids of the i-th component and the j-th component, d max is the maximum centroid distance.

[0029] Further, the centroid distance is determined by the centroid coordinates of the two components, and the process of determining the centroid coordinates is:

[0030] The determination is performed based on the two-dimensional first-order moment of the ISAR image.

[0031] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, wherein the processor is coupled to a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements any of the above methods.

[0032] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor so that a computer implements any of the above methods.

[0033] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0035] Figure 1 A schematic diagram of a flow chart of a method for searching and matching a spatial target posture model in optical-radar co-site observation according to an embodiment of the present invention;

[0036] Figure 2 It is a schematic diagram of the principle of obtaining the attitude angle of the central axis of a sailboard through face-to-face intersection in a method for searching and matching the attitude model of a space target observed by optical-radar co-location according to an embodiment of the present invention;

[0037] Figure 3 This is a diagram of the architecture framework of an electronic device of the present invention. DETAILED DESCRIPTION

[0038] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0039] like Figure 1 As shown, a method for searching and matching a spatial target attitude model for optical-radar co-site observation according to an embodiment of the present invention comprises the following steps:

[0040] S1, obtain optical images and ISAR images of any on-orbit space target at the same observation station viewing angle;

[0041] S2, performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle, taking the attitude angle as a reference and the attitude angle of 5° as a constraint condition, determining a target neighborhood, determining at least one target ISAR image corresponding to the target neighborhood in a space target attitude model database, and determining a target feature vector corresponding to each target ISAR image;

[0042] S3, determining a retrieval feature vector corresponding to the on-orbit space target according to the ISAR image, taking the target ISAR image corresponding to the target feature vector with the smallest Euclidean distance with the retrieval feature vector as a matching result, determining a posture model corresponding to the target ISAR image, and outputting the posture model as a search result.

[0043] The beneficial effects of the space target attitude model search and matching method for optical-radar co-site observation provided by the present invention are as follows:

[0044] Firstly, the three-dimensional attitude of the sailboard structure of the space target in the optical image is estimated based on the surface-to-surface intersection method. Secondly, the radar ISAR image attitude model database is searched within the 5° attitude angle neighborhood for minimum distance matching. Finally, the attitude model is determined, and the three-dimensional attitude information of the on-orbit space target is confirmed by the attitude model. Confirming the three-dimensional attitude information of the on-orbit space target with the attitude model can not only accurately obtain the corresponding attitude model and then confirm the three-dimensional attitude information, but also improve the confirmation efficiency of the three-dimensional attitude information.

[0045] The process of performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle is specifically as follows:

[0046] like Figure 2 As shown, the three-dimensional posture of the space target is inverted by the optical projection solution method:

[0047] Solar panels have two sets of mutually orthogonal parallel lines. The two parallel long sides of the panel in a single image are used to perform a face-to-face intersection to calculate the attitude and direction of the central axis of the panel. The two parallel long sides of the panel are straight lines L1 and L2, and the central axis of the panel is straight line L. The images formed by L1 and L2 are l1 and l2 respectively. l1 and l2 determine planes Π1 and Π2 at the optical center C respectively. The intersection of planes Π1 and Π2 gives a spatial straight line L'. The spatial straight line is described by the two spatial plane equations, which is the spatial straight line determined by face-to-face intersection. According to geometric knowledge, the intersection line L' of planes Π1 and Π2 is parallel to the central axis L, and the attitude angles of the two are consistent. Therefore, the pitch angle and yaw angle of the intersection line L' of Π1 and Π2 are the attitude angles of the central axis L.

[0048] The straight line equations of l1 and l2 on the image are expressed as

[0049] a i u+b i v+c i =0(i=1,2) (1)

[0050] Where i=1 represents the equation of the l1 line, and i=2 represents the equation of the l2 line. From formula (1), we get

[0051] Ai X s +B i Y s +C i Z s +D i =0(i=1,2) (2)

[0052] Where i=1 represents the Π1 plane equation, i=2 represents the Π2 plane equation,

[0053]

[0054] Therefore, the equation of the intersection line L' of planes Π1 and Π2 is

[0055]

[0056] Its matrix representation is

[0057]

[0058] Then in the station coordinate system, the direction vector of the line L′ is (l, m, n), where

[0059]

[0060] Based on the direction vector (l, m, n), the attitude angle is determined.

[0061] Taking the attitude angle as a reference and the attitude angle of 5° as a constraint condition, the target neighborhood is determined, that is, under the attitude angle, the attitude angle range of 5° attitude angle deviation is determined, and the attitude angle range is the target neighborhood.

[0062] It should be noted that each target ISAR image is marked with corresponding attitude information (including attitude angle) and corresponding feature vector.

[0063] The specific process of determining the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image is as follows:

[0064] Three-dimensional attitude search and matching of radar ISAR images in attitude angle neighborhood

[0065] This scheme determines the retrieval feature vector through a matrix, and the determination process of the matrix is ​​as follows:

[0066] Define an N×N matrix M, where N is the number of subcomponents in the model. The value M at (i, j) ii is the surface area a of the ith component i With the largest subcomponent area a max The value M at (i, j) ij is 1-(d ij -dmax ) 2 , where d ij is the distance between the centroids of the i-th component and the j-th component, d max is the maximum distance between the centroids of all parts. Therefore, when two parts are far apart, M ij Approaching 1, on the contrary, M ij approaches 0. In this way, the off-diagonal elements of the matrix express the adjacency of each component in the model. The matrix M can be used as a retrieval value for a certain model, and the model is encoded using the eigenvector of the matrix. The advantage is that the number of components in the model is the same as the number of non-zero eigenvalues ​​of the rectangle, and the obtained eigenvalues ​​are scale-invariant, two-dimensional rotation-invariant, and translation-invariant.

[0067] The specific solution method for the centroid distance and the corresponding surface area in the matrix is:

[0068] The two-dimensional (p+q) order moment of a digital image f(x, y) of size M×N is defined as:

[0069]

[0070] Where p = 0, 1, 2, ..., q = 0, 1, 2, .... The corresponding (p+q)-order central moment is defined as:

[0071]

[0072] The two first-order moments m of the image 10 and m 01 Used to determine the center of mass of the region. Its center of mass coordinates are:

[0073]

[0074] The major axis a and minor axis b of the region are approximately:

[0075]

[0076] It should be noted that the centroid distance between two components can be determined through the centroid coordinates, and the surface area information can be fitted through the major axis and the minor axis.

[0077] After using the feature retrieval method to obtain information such as the center of mass and area of ​​each component of the posture model, we can generate feature vectors corresponding to each model, calculate the Euclidean distance between the retrieval vector of the target to be estimated and them, and the model posture with the smallest distance can be used as the approximate posture of the target.

[0078] Further, the process of performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle is specifically as follows:

[0079] The optical projection solution method is used to invert the direction vector, and the attitude angle is determined based on the direction vector.

[0080] Further, the process of determining the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image is specifically as follows:

[0081] Determine an N×N matrix M corresponding to the ISAR image, and determine a retrieval feature vector based on the matrix M, where N is the number of subcomponents in the on-orbit space target, and M ii is the ratio of the surface area of ​​the ith component to the maximum surface area, M ij =1-(d ij -d max ) 2 , d ij is the distance between the centroids of the i-th component and the j-th component, d max is the maximum centroid distance.

[0082] Further, the centroid distance is determined by the centroid coordinates of the two components, and the process of determining the centroid coordinates is:

[0083] The determination is performed based on the two-dimensional first-order moment of the ISAR image.

[0084] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0085] The present invention also provides a space target attitude model search and matching system for optical-radar co-site observation, and the specific technical solution is as follows:

[0086] The acquisition module is used to obtain optical images and ISAR images of any on-orbit space target at the same observation station viewing angle;

[0087] The preprocessing module is used to: perform three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle, determine the target neighborhood based on the attitude angle and the 5° attitude angle as a constraint condition, determine at least one target ISAR image corresponding to the target neighborhood in the space target attitude model database, and determine the target feature vector corresponding to each target ISAR image;

[0088] The search and matching module is used to: determine the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image, take the target ISAR image corresponding to the target feature vector with the smallest Euclidean distance with the retrieval feature vector as the matching result, determine the attitude model corresponding to the target ISAR image, and output the attitude model as the search result.

[0089] Based on the above solution, the present invention can also be improved as follows.

[0090] Further, the process of performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle is specifically as follows:

[0091] The optical projection solution method is used to invert the direction vector, and the attitude angle is determined based on the direction vector.

[0092] Further, the process of determining the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image is specifically as follows:

[0093] Determine an N×N matrix M corresponding to the ISAR image, and determine a retrieval feature vector based on the matrix M, where N is the number of subcomponents in the on-orbit space target, and M ii is the ratio of the surface area of ​​the ith component to the maximum surface area, M ij =1-(d ij -d max ) 2 , d ij is the distance between the centroids of the i-th component and the j-th component, d max is the maximum centroid distance.

[0094] Further, the centroid distance is determined by the centroid coordinates of the two components, and the process of determining the centroid coordinates is:

[0095] The determination is performed based on the two-dimensional first-order moment of the ISAR image.

[0096] It should be noted that the beneficial effects of the space target attitude model search and matching system for optical-radar co-site observation provided by the above embodiment are the same as the beneficial effects of the space target attitude model search and matching method for optical-radar co-site observation, which will not be repeated here. In addition, when the system provided by the above embodiment realizes its functions, it only uses the division of the above-mentioned functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0097] like Figure 3 As shown, an electronic device 300 according to an embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above methods, specifically:

[0098] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements a spatial target attitude model search and matching method for optical-radar co-site observation provided by the above embodiment. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The electronic device 300 may also include other components for realizing device functions, which will not be repeated here.

[0099] A computer-readable storage medium according to an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements any one of the above methods.

[0100] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0101] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs any of the above methods.

[0102] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0103] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0104] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0105] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for searching and matching a spatial target attitude model for optical-radar co-site observation, characterized in that: include: Acquire optical images and ISAR images of any space target on orbit from the same observation station perspective; Performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine an attitude angle, determining a target neighborhood based on the attitude angle and a 5° attitude angle as a constraint, determining at least one target ISAR image corresponding to the target neighborhood in a space target attitude model database, and determining a target feature vector corresponding to each target ISAR image; A retrieval feature vector corresponding to the on-orbit space target is determined according to the ISAR image, a target ISAR image corresponding to the target feature vector with the smallest Euclidean distance with the retrieval feature vector is taken as a matching result, a posture model corresponding to the target ISAR image is determined, and the posture model is output as a search result.

2. The method for searching and matching the spatial target attitude model for optical-radar co-site observation according to claim 1, characterized in that: The process of performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle is specifically as follows: The optical projection solution method is used to invert the direction vector, and the attitude angle is determined based on the direction vector.

3. The method for searching and matching the spatial target attitude model for optical-radar co-site observation according to claim 1, characterized in that: The specific process of determining the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image is as follows: Determine an N×N matrix M corresponding to the ISAR image, and determine a retrieval feature vector based on the matrix M, where N is the number of subcomponents in the on-orbit space target, and M ii is the ratio of the surface area of ​​the ith component to the maximum surface area, M ij =1-(d ij -d max ) 2 , d ij is the distance between the centroids of the i-th component and the j-th component, d max is the maximum centroid distance.

4. The method for searching and matching the spatial target attitude model for optical-radar co-site observation according to claim 3, characterized in that: The centroid distance is determined by the centroid coordinates of the two components, and the process of determining the centroid coordinates is: The determination is performed based on the two-dimensional first-order moment of the ISAR image.

5. A space target attitude model search and matching system for optical-radar co-site observation, characterized in that: include: The acquisition module is used to obtain optical images and ISAR images of any on-orbit space target at the same observation station viewing angle; The preprocessing module is used to: perform three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle, determine the target neighborhood based on the attitude angle and the 5° attitude angle as a constraint condition, determine at least one target ISAR image corresponding to the target neighborhood in the space target attitude model database, and determine the target feature vector corresponding to each target ISAR image; The search and matching module is used to: determine the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image, take the target ISAR image corresponding to the target feature vector with the smallest Euclidean distance with the retrieval feature vector as the matching result, determine the attitude model corresponding to the target ISAR image, and output the attitude model as the search result.

6. The space target attitude model search and matching system for optical-radar co-site observation according to claim 5, characterized in that: The process of performing three-dimensional attitude estimation processing on the space target sailboard structure in the optical image to determine the attitude angle is specifically as follows: The optical projection solution method is used to invert the direction vector, and the attitude angle is determined based on the direction vector.

7. The space target attitude model search and matching system for optical-radar co-site observation according to claim 5, characterized in that: The specific process of determining the retrieval feature vector corresponding to the on-orbit space target according to the ISAR image is as follows: Determine an N×N matrix M corresponding to the ISAR image, and determine a retrieval feature vector based on the matrix M, where N is the number of subcomponents in the on-orbit space target, and M ii is the ratio of the surface area of ​​the ith component to the maximum surface area, M ij =1-(d ij -d max ) 2 , d ij is the distance between the centroids of the i-th component and the j-th component, d max is the maximum centroid distance.

8. The space target attitude model search and matching system for optical-radar co-site observation according to claim 7, characterized in that: The centroid distance is determined by the centroid coordinates of the two components, and the process of determining the centroid coordinates is: The determination is performed based on the two-dimensional first-order moment of the ISAR image.

9. An electronic device, characterized in that: The electronic device comprises a processor, the processor is coupled to a memory, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements the method according to any one of claims 1 to 4.

Images