Near-earth space target identification method and device

Abstract

The invention discloses a near-earth space target identification method and device, and the method comprises the steps: obtaining a space-based measurement picture, obtaining the form information of a to-be-identified space target and the mass center position of the to-be-identified space target based on the space-based measurement picture, and obtaining image features based on the form information and the mass center position; obtaining observation data, constructing a geometrical relationship among a to-be-identified space target, an observation platform and the earth core based on the observation data, determining a target track of the to-be-identified space target based on the geometrical relationship and a Laplace method, and obtaining track characteristics; and splicing based on the image features and the track features to obtain fusion features, and identifying the to-be-identified space target based on the fusion features and a historical cataloguing database to obtain an identification result. According to the method, the image features and the track features are combined, the fusion features are generated, the image features and the motion features of the space target are fully utilized, the space target is comprehensively described, and the accuracy of space-based optical target recognition is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of space target recognition, and in particular to a near-Earth space target recognition method and device. Background Art

[0002] With the rapid development of human space industry, by 2024, the number of various space targets in near-Earth space has exceeded 50,000, and it is still maintaining an explosive growth trend. It is of great engineering significance to focus on detecting and tracking space targets with relatively important value and obtain the orbital elements, shapes, sizes and categories of various space targets. Space target detection and identification are mainly divided into two means: ground-based observation and space-based observation. The ground-based observation system is usually composed of an optical telescope and a radar detector, which can detect and track space targets that pass over its top. The ground-based space target monitoring system has mature technology and low cost, but it is easily affected by the curvature of the earth, the atmospheric environment and the lighting and meteorological conditions, and the observation range is limited. The space-based optical observation platform flies around the earth at high speed in orbit, which can obtain a wider field of view, and weaken the influence of the curvature of the earth, which can improve the observation arc of space targets. In addition, since the space-based platform itself has a certain height, it improves the observation geometry, reduces the adverse effects of the atmosphere during the observation process, and is more conducive to optical observation. Combining the respective advantages of space-based platforms and optical observations, space-based optical observations have obvious advantages over ground-based observations in terms of airspace coverage and monitoring timeliness.

[0003] There are two main approaches to existing space-based optical target recognition methods. One is to extract the target pixel coordinates in the observation payload, and obtain the target's relative right ascension and declination based on the coordinate transformation principle, and then complete the relative orbit calculation. It relies on dynamic calculation to determine the target type, which sometimes leads to misjudgment. At this time, a large amount of other image information obtained in the observation payload is discarded or wasted; the other is to directly judge based on image characteristics, such as grayscale, size and other features. At this time, due to ignoring the target's dynamic characteristics, it is easy to be misled and lead to misjudgment. Summary of the invention

[0004] The present invention provides a near-Earth space target recognition method and device to improve the accuracy of space-based optical target recognition.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a near-Earth space target recognition method, comprising: Acquire a space-based measurement picture, acquire morphological information of a space target to be identified and a centroid position of the space target to be identified based on the space-based measurement picture, and acquire image features based on the morphological information and the centroid position; Acquire observation data based on the observation platform, construct a geometric relationship model based on the observation data, and determine the target orbit of the space target to be identified based on the geometric relationship model and the Laplace method to obtain orbital characteristics; the geometric relationship model is a geometric relationship model between the space target to be identified, the observation platform and the center of the earth; A fusion feature is obtained based on the image feature and the orbit feature, and the space target to be identified is identified based on the fusion feature and a historical catalog database to obtain a space target identification result.

[0006] The present invention obtains the morphological information and the center of mass position of the space target through space-based measurement pictures, expresses the appearance characteristics of the space target according to the morphological information and the center of mass position, and then generates image features; at the same time, constructs the geometric relationship between the space target, the observation platform and the center of the earth through observation data, expresses the motion characteristics of the space target according to the geometric relationship, and then obtains the orbital characteristics; generates fusion features by combining image features and orbital features, and the fusion features make full use of the image characteristics and motion characteristics of the space target, and can comprehensively describe the space target; finally, the space target to be identified is identified based on the historical cataloging database and the fusion features, so as to associate the space target to be identified with the prior cataloging information, obtain the recognition result of the near-Earth space target, and improve the accuracy of the recognition result of the near-Earth space target in space-based optics.

[0007] Furthermore, the acquiring of the morphological information of the space target and the center of mass position of the space target based on the space-based measurement image includes: Generate a filter operator matrix based on a preset filter, and perform filtering processing on the space-based measurement image based on the filter operator matrix to obtain a filtered image; Binarize the filtered image based on a preset grayscale threshold to generate a grayscale image; Extracting edges of the grayscale image based on a preset first edge detection algorithm to obtain morphological information of the space target; The target contour of the grayscale image is identified based on a preset second edge detection algorithm, and the center of mass position of the space target is acquired based on the target contour.

[0008] The present invention removes noise and simplifies images through filtering and binarization, monitors the binarized images through an edge detection algorithm, extracts morphological information of the space target to be identified, and simultaneously obtains the centroid position of the space target to be identified through target contour recognition and pixel threshold calculation, thereby generating image features for describing the image characteristics of the target to be identified through the morphological information and the centroid position.

[0009] Furthermore, the observation data includes a space target position vector and an observation platform position vector, the space target position vector is a position vector of the space target relative to the center of the earth, and the observation platform position vector is a position vector of the observation platform relative to the center of the earth; and constructing a geometric relationship model based on the observation data includes: Constructing the geometric relationship based on the space target position vector and the observation platform position vector; Constructing a geocentric distance equation of the space target based on the Laplace method, and obtaining initial orbit parameters based on the geometric relationship and the geocentric distance equation; An observation model and an error model are constructed based on the initial orbit parameters, and the initial orbit parameters are optimized based on the observation model and the error model to determine the target orbit and obtain orbit characteristics.

[0010] The present invention establishes a geometric relationship between the space target and the observation platform and the center of the earth by utilizing the position vectors thereof, thereby constructing the geocentric distance equation by the Laplace method, and obtaining the initial orbital parameters according to the geocentric distance equation and the geometric relationship, thereby realizing the conversion of the observation data into the orbital parameters, obtaining the orbital characteristics of the space target to be identified, and describing the dynamic characteristics of the space target to be identified based on the orbital characteristics.

[0011] Furthermore, the acquiring of fusion features based on the image features and the orbital features, and identifying the space target to be identified based on the fusion features and a historical catalog database to obtain a space target identification result includes: Performing standardization processing on the image features and the track features to obtain standard image features and standard track features; Perform stitching based on the standard image features and the standard track features to obtain fusion features; Inputting the fusion features into a pre-trained target recognition model, identifying the spatial target to be identified, and obtaining a preliminary recognition result; The preliminary recognition result is verified based on the historical cataloging data to obtain a space target recognition result.

[0012] The present invention can convert feature values ​​of different dimensions to the same scale through standardization processing, and splice the standardized image features and orbit features together to form a comprehensive feature vector containing information from multiple aspects, so as to comprehensively describe the image characteristics and kinematic characteristics of the space target to be identified through fusion features, thereby identifying the space target to be identified and improving the recognition accuracy.

[0013] Further, the preliminary recognition result includes basic information of the space target to be recognized, and the verification of the preliminary recognition result based on the historical cataloging data to obtain the space target recognition result includes: matching a verification target in the historical catalog database based on the basic information; The orbit error is calculated based on the basic information and the verification target, the preliminary recognition result is verified based on a preset orbit error, and the space target recognition result is obtained based on the verification result.

[0014] The present invention uses the basic information in the preliminary recognition result to search for matching targets in the historical catalog database, and quantifies the difference between the orbital parameters of the preliminary recognition result and the target in the historical catalog database based on the orbital error, thereby verifying the preliminary recognition result, and judging whether the preliminary recognition result meets the requirements based on a preset orbital error threshold, thereby determining the space target recognition result to improve recognition accuracy and avoid misjudgment.

[0015] In a second aspect, the present invention provides a near-Earth space target recognition device, comprising: an image feature extraction module, a track feature extraction module and a fusion recognition module; The image feature extraction module is used to obtain a space-based measurement picture, obtain morphological information of a space target to be identified and a centroid position of the space target to be identified based on the space-based measurement picture, and obtain image features based on the morphological information and the centroid position; The orbit feature extraction module is used to obtain observation data based on the observation platform, build a geometric relationship model based on the observation data, and determine the target orbit of the space target to be identified based on the geometric relationship model and the Laplace method to obtain orbit features; the geometric relationship model is a geometric relationship model between the space target to be identified, the observation platform and the center of the earth; The fusion recognition module is used to obtain fusion features based on the image features and the orbital features, and to identify the space target to be identified based on the fusion features and the historical catalog database to obtain a space target identification result.

[0016] Furthermore, the image feature extraction module is used to: Generate a filter operator matrix based on a preset filter, and perform filtering processing on the space-based measurement image based on the filter operator matrix to obtain a filtered image; Binarize the filtered image based on a preset grayscale threshold to generate a grayscale image; Extracting edges of the grayscale image based on a preset first edge detection algorithm to obtain morphological information of the space target; The target contour of the grayscale image is identified based on a preset second edge detection algorithm, and the center of mass position of the space target is acquired based on the target contour.

[0017] Furthermore, the observation data includes a space target position vector and an observation platform position vector, wherein the space target position vector is a position vector of the space target relative to the center of the earth, and the observation platform position vector is a position vector of the observation platform relative to the center of the earth; the orbit feature extraction module is used to: Constructing the geometric relationship based on the space target position vector and the observation platform position vector; Constructing a geocentric distance equation of the space target based on the Laplace method, and obtaining initial orbit parameters based on the geometric relationship and the geocentric distance equation; An observation model and an error model are constructed based on the initial orbit parameters, and the initial orbit parameters are optimized based on the observation model and the error model to determine the target orbit and obtain orbit characteristics.

[0018] Furthermore, the fusion recognition module is used to: Performing standardization processing on the image features and the track features to obtain standard image features and standard track features; Perform stitching based on the standard image features and the standard track features to obtain fusion features; Inputting the fusion features into a pre-trained target recognition model, identifying the spatial target to be identified, and obtaining a preliminary recognition result; The preliminary recognition result is verified based on the historical cataloging data to obtain a space target recognition result.

[0019] Furthermore, the preliminary recognition result includes basic information of the space target to be recognized, and the fusion recognition module is used to: matching a verification target in the historical catalog database based on the basic information; The orbit error is calculated based on the basic information and the verification target, the preliminary recognition result is verified based on a preset orbit error, and the space target recognition result is obtained based on the verification result. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a flow chart of a near-Earth space target identification method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a space target to be identified provided by an embodiment of the present invention; Figure 3 A grayscale feature map of a space target to be identified provided by an embodiment of the present invention; Figure 4 A schematic diagram of the geometric relationship of word observation moments provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0022] The terms "first" and "second" and the like in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0023] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0024] Example 1 See also Figure 1 , Figure 1 A flowchart of a near-Earth space target identification method provided by an embodiment of the present invention. The embodiment of the present invention provides a near-Earth space target identification method, including steps 101 to 103, which are as follows: Step 101: obtaining a space-based measurement picture, obtaining morphological information of a space target to be identified and a centroid position of the space target to be identified based on the space-based measurement picture, and obtaining image features based on the morphological information and the centroid position; In this embodiment, a space-based measurement image is obtained, and the space-based observation image is classified and stored according to image data frames, and the space-based observation image is preprocessed. The preprocessing includes slicing and data cleaning, and then the large image in the space-based measurement image is divided into smaller sub-images for processing, while removing noise and invalid information to ensure data quality.

[0025] In this embodiment, after preprocessing the space-based measurement image, the morphological information of the space target to be identified and the centroid position of the space target to be identified are obtained based on the space-based measurement image.

[0026] In this embodiment, the step of acquiring the morphological information of the space target and the centroid position of the space target based on the space-based measurement image includes: Generate a filter operator matrix based on a preset filter, and perform filtering processing on the space-based measurement image based on the filter operator matrix to obtain a filtered image; Binarize the filtered image based on a preset grayscale threshold to generate a grayscale image; Extracting edges of the grayscale image based on a preset first edge detection algorithm to obtain morphological information of the space target; The target contour of the grayscale image is identified based on a preset second edge detection algorithm, and the center of mass position of the space target is acquired based on the target contour.

[0027] In this embodiment, the preprocessed image data is loaded into the filter-related compilation environment, and the grayscale information of all pixels of the image slice is traversed, and the type and size of noise in the image, such as Gaussian noise, background noise, etc., is determined, and the filter is selected according to the number of isolated noise points and the type of noise in the image slice, so as to generate a specified filter operator matrix according to the filter, wherein the filter includes a mean filter, a Gaussian filter, and a median filter. Then the filter window size is determined, the image pixels are traversed, and the filter image is obtained by calculating the weighted surrounding pixel values; the edge pixels of the image slice are replaced by the grayscale mean.

[0028] In this embodiment, specific mathematical operations are performed on pixels in an image slice to change the appearance of the image or enhance specific features of a spatial target in the image.

[0029] In this embodiment, the filtered image is binarized. Specifically, a grayscale threshold is pre-set, and based on the grayscale threshold, the pixel values ​​in the grayscale image are divided into two categories, one is a pixel value greater than the grayscale threshold, and the other is a pixel value less than or equal to the grayscale threshold. For each pixel in the filtered image, its grayscale value is compared with the grayscale threshold. If the grayscale value of the pixel is greater than the threshold, the grayscale value of the pixel is retained to represent the target object; if the grayscale value of the pixel is less than or equal to the threshold, the pixel is set to black (grayscale is 0) to represent the background, until all pixels in the image are binarized to generate a grayscale image.

[0030] In this embodiment, after the binarization process, the image is binary segmented according to the process result, and then the edge of the grayscale image is extracted based on a preset first edge detection algorithm to obtain the morphological information of the space target.

[0031] In this embodiment, in space-based measurement image processing, edge extraction of space targets is used to identify and analyze the morphology, structure and boundaries of celestial bodies and various space targets. The principle of edge extraction is to detect the pixel value changes of the target in the image, find the boundaries between different areas in the image, and thus depict the outline and shape of the target.

[0032] In this embodiment, the gradient or edge response of the pixel value is calculated based on a preset first edge detection algorithm to detect the edge in the image, and after the edge detection, the broken or discontinuous edge line segments are connected based on a preset edge connection algorithm to form a complete edge contour.

[0033] In this embodiment, the first edge detection algorithm includes a Sobel edge detection algorithm, Prewitt, Canny, and the like.

[0034] In this embodiment, after obtaining the edge contour, the detected edge needs to be optimized and refined to remove noise and unnecessary details to obtain a more accurate target edge contour, and the morphological information of the spatial target to be identified is obtained based on the extracted target contour. The morphological information includes size, shape, direction and other features.

[0035] In this embodiment, the morphological information of the space target can be effectively extracted from the space-based image through edge extraction, providing important data support for subsequent analysis and research.

[0036] In this embodiment, after the edge extraction of the space target to be identified is completed, the target contour of the grayscale image is identified based on a preset second edge detection algorithm, and the centroid position of the space target is obtained based on the target contour.

[0037] In this embodiment, in the space-based measurement of space target image processing, determining the centroid position of celestial bodies and various space targets is the basis for generating the space target sight vector and completing the space target orbit determination, and then performing position measurement, motion analysis, etc. The principle of centroid extraction is to find the image centroid position of the target by calculating the pixel value and position information of the target in the image.

[0038] In this embodiment, the grayscale image is identified based on threshold segmentation and a second edge detection algorithm to obtain the target contour of the spatial target to be identified, and the weighted average of the pixel values ​​is calculated based on the target contour to determine the center of mass position. Specifically, the pixel value is used as the weight to calculate the center of mass position, or a morphological method is used to find the geometric center of the target.

[0039] In this embodiment, since the space target moves at a high speed, it is easy to form a tailing phenomenon in the image. To address this phenomenon, when obtaining the centroid coordinates of the space target image, the Gaussian surface fitting method based on various anisotropies is preferentially used to calculate the centroid position of the space target to be identified. After obtaining the preliminary centroid position, further correction and optimization can be performed, such as removing noise interference and eliminating errors, so as to obtain the final centroid position.

[0040] In this embodiment, the centroid position is used to measure the position, motion trajectory, morphological characteristics, etc. of the target. By extracting the centroid, the center position of the space target can be accurately determined, providing basic data for subsequent analysis and research.

[0041] Please refer to Figure 2 , Figure 2 A schematic diagram of a space target to be identified provided in an embodiment of the present invention.

[0042] In this embodiment, image features are acquired based on the morphological information and the centroid position, wherein the image features are grayscale features of the space target, including the grayscale maximum value, the space target diffusion area, the grayscale gradient and the grayscale average value, which are used to describe the brightness, size, shape and other features of the space target to be identified.

[0043] Please refer to Figure 3 , Figure 3 A grayscale feature map of a space target to be identified provided in an embodiment of the present invention.

[0044] In this embodiment, the maximum grayscale value of the spatial target refers to the maximum grayscale value of the pixels in the target area. By calculating the maximum grayscale value, the brightest part of the target can be understood, which is helpful for evaluating the brightness intensity of the target.

[0045] In this embodiment, the diffuse area of ​​the spatial target refers to the total area of ​​all pixels in the target area. The size information of the target can be obtained by calculating the number or area of ​​non-zero pixels in the target area, thereby evaluating the size of the target.

[0046] In this embodiment, the grayscale average value of the spatial target refers to the average value of the grayscale values ​​of the pixels in the target area. By calculating the grayscale average value, the overall brightness level of the target can be understood, which is helpful for evaluating the overall brightness characteristics of the target.

[0047] In this embodiment, the grayscale gradient refers to the rate of change of the grayscale value of the pixel in the image, reflecting the grayscale change in the target area. The grayscale change characteristics of the target can be obtained by calculating the gradient or gradient amplitude of the pixel grayscale value, which is helpful for analyzing the edge information and texture characteristics of the target.

[0048] In this embodiment, in this embodiment, noise is removed and the image is simplified through filtering and binarization, and the binarized image is monitored by an edge detection algorithm to extract the morphological information of the spatial target to be identified. At the same time, the center of mass position of the spatial target to be identified is obtained through target contour recognition and pixel threshold calculation, thereby generating image features for describing the image characteristics of the target to be identified through the morphological information and the center of mass position.

[0049] In this embodiment, after obtaining the grayscale features, the image recognition of the space target to be identified can be performed based on the grayscale features. Specifically: first, the grayscale features of each space target are extracted, including the grayscale maximum value, diffuse area, grayscale gradient, grayscale average value, etc. The grayscale features of each space target are represented as a feature vector, where each feature corresponds to a dimension. For example, a feature vector may include the grayscale maximum value, diffuse area, grayscale gradient, and grayscale average value. Then, the feature vectors are classified based on the use of a machine learning algorithm or a classification algorithm, thereby realizing the type recognition of the space target.

[0050] In this embodiment, commonly used classification algorithms include support vector machine (SVM), K nearest neighbor (KNN), decision tree, etc.

[0051] In this embodiment, the result of image recognition will be used as an auxiliary data to assist in determining whether the final recognition result is correct.

[0052] Step 102: acquiring observation data based on the observation platform, constructing a geometric relationship model based on the observation data, and determining the target orbit of the to-be-identified space target based on the geometric relationship model and the Laplace method to obtain orbital characteristics; the geometric relationship model is a geometric relationship model between the to-be-identified space target, the observation platform and the center of the earth; In this embodiment, the observation data includes a space target position vector and an observation platform position vector, the space target position vector is a position vector of the space target relative to the center of the earth, and the observation platform position vector is a position vector of the observation platform relative to the center of the earth; and constructing a geometric relationship model based on the observation data includes: Constructing the geometric relationship based on the space target position vector and the observation platform position vector; Constructing a geocentric distance equation of the space target based on the Laplace method, and obtaining initial orbit parameters based on the geometric relationship and the geocentric distance equation; An observation model and an error model are constructed based on the initial orbit parameters, and the initial orbit parameters are optimized based on the observation model and the error model to determine the target orbit and obtain orbit characteristics.

[0053] In this embodiment, by utilizing the position vectors of the space target and the observation platform, a geometric relationship between them and the center of the earth is established, and then the geocentric distance equation is constructed through the geometric relationship and the Laplace method to obtain the initial orbital parameters, thereby realizing the conversion of observation data to orbital parameters, obtaining the orbital characteristics of the space target to be identified, and describing the dynamic characteristics of the space target to be identified based on the orbital characteristics.

[0054] In this embodiment, the orbit parameters are identified based on the observed data including a time series ti (i=1,2, …,n), using a space-based or ground-based optical platform to observe uncataloged space targets, and extracting the direction vector L of the target relative to the platform i , combined with the geocentric position vector R of the observation platform i , determine the orbital parameters of the target.

[0055] In this embodiment, the observation data includes a space target position vector and an observation platform position vector, wherein the space target vector includes the position, velocity and acceleration of the space target relative to the center of the earth, the observation platform vector includes a space-based observation platform vector and a ground-based observation platform vector, the space-based observation platform vector includes the position, velocity and acceleration of the space-based observation platform relative to the center of the earth, and the ground-based observation platform vector includes the position, velocity and acceleration of the ground-based observation platform relative to the center of the earth.

[0056] In this embodiment, in a time series t i (i=1,2, …,n), the geometric relationship between the space target, ground-based or space-based observation platform and the center of the earth at a single observation time is constructed based on the observation data.

[0057] Please refer to Figure 4 , Figure 4 A schematic diagram of the geometric relationship of word observation moments provided by an embodiment of the present invention.

[0058] In this embodiment, the geometric configuration of a single observation of a space target is: (1) The first-order derivative and second-order derivative of the geometric configuration of a single observation of a space target are: (2) (3) in, , , They are slope range, first-order and second-order derivatives of slope range respectively; and are the first and second order derivatives of the observation vector, respectively; , , and , , are the position, velocity and acceleration vectors of the space target and the observation platform respectively. In this embodiment, the octave equation of the target geocentric distance is constructed based on the Laplace method and the geometric relationship. The octet equation, (4) Among them, A, B, and C are coefficients that depend on the relative positions of the center of the earth, the observation platform, and the target. Specifically: (5) (6) (7) In this embodiment, the octave equation contains information such as the position, velocity, and acceleration of the space target and the observation platform. The coefficients in the equation depend on the relative positions of the center of the earth, the observation platform, and the space target. Therefore, the nature of the roots of the octave equation also depends on the relative position relationship of the three.

[0059] In this embodiment, based on the geocentric distance equation and the position of the space target to be identified at the time of orbit determination, and the initial value of the velocity vector , based on the position at the orbit determination time and the initial value of the velocity vector The slope distance is calculated by the geometric relationship 0 and slope range rate , and finally based on the slope distance 0 and slope range rate Calculate the number of orbital elements.

[0060] In this embodiment, it can be seen from the geometric relationship that there is no essential difference between space-based orbit determination and ground-based orbit determination, that is, the basic formula is the same. When the Laplace-like method is used for orbit determination, since the short arc motion equation of the space target basically follows the Kepler motion, it is easy to cause the orbit determination result to converge to the orbit of the observation platform. That is: (8) The subscript 0 indicates the orbit determination epoch time. Indicates the position of the space target relative to the center of the earth at the orbit determination epoch, Represents the acceleration vector of the space target relative to the center of the earth at the orbit determination epoch.

[0061] In this embodiment, the trivial solution of the target geocentric distance is eliminated. After the trivial solution elimination operation, the original octave equation is reduced to a septave equation, which can be solved using the Newton iteration method: (9) (10) (11) In the formula, is the value of r0 iterated for the kth time. The initial value r0 is obtained through iterative calculation, so that the estimated value of the slant range and slant range rate of the space target can be obtained: (12) (13) Therefore, based on the slant range, the slant range change rate and the geometric relationship, the position and velocity of the space target at the time of orbit determination, that is, the initial orbit parameters, can be obtained.

[0062] In this embodiment, the orbital characteristics of the space target are obtained based on the position and velocity of the space target. The orbital characteristics specifically include orbital altitude, target flight velocity, acceleration, orbital type, and orbital eccentricity.

[0063] In this embodiment, the observation model and the error model are constructed based on the initial orbit parameters, that is, the initial value of the differential equation of the formula is determined in reverse by the boundary value conditions (observation values).

[0064] In this embodiment, an observation model is constructed based on the initial orbit parameters: (14) in, =[ , ], represents the orbit determination epoch time, Indicates the predicted spatial target at the future time location and direction, Indicates the direction angle of the space target relative to the observation platform, Indicates the elevation angle of the space target relative to the observation platform.

[0065] In this embodiment, the observation model is linearized and the initial value of the state Taylor expansion is performed near the approximate value of , and only the linear terms are retained to obtain its error equation, specifically: (15) (16) in, is the observed residual, is the correction value of the state vector, is an approximation of the state vector.

[0066] In this embodiment, the least squares method is used to solve the error equation, with the goal of minimizing the sum of squares of the observed residuals h: (17) According to the correction , update the initial vector of the orbital initial state orbit: (18) Updated state vector It will be closer to the true value. If higher accuracy is required, it can be updated iteratively until the observed residual h meets the preset accuracy requirements.

[0067] In this embodiment, by utilizing the position vectors of the space target and the observation platform, a geometric relationship between them and the center of the earth is established, and the geocentric distance equation is constructed by the Laplace method. The initial orbital parameters are obtained based on the geocentric distance equation and the geometric relationship, thereby realizing the conversion of observation data to orbital parameters, obtaining the orbital characteristics of the space target to be identified, and describing the dynamic characteristics of the space target to be identified based on the orbital characteristics.

[0068] Step 103: Acquire fusion features based on the image features and the orbital features, and identify the space target to be identified based on the fusion features and the historical catalog database to obtain a space target identification result.

[0069] In this embodiment, the acquiring of fusion features based on the image features and the orbital features, and identifying the space target to be identified based on the fusion features and a historical catalog database to obtain a space target identification result includes: Performing standardization processing on the image features and the track features to obtain standard image features and standard track features; Perform stitching based on the standard image features and the standard track features to obtain fusion features; Inputting the fusion features into a pre-trained target recognition model, identifying the spatial target to be identified, and obtaining a preliminary recognition result; The preliminary recognition result is verified based on the historical cataloging data to obtain a space target recognition result.

[0070] In this embodiment, the eigenvalues ​​of different dimensions can be converted to the same scale through standardization processing, and the standardized image features and orbital features can be spliced ​​together to form a comprehensive feature vector containing multiple aspects of information. The image characteristics and kinematic characteristics of the space target to be identified can be fully described by fusion features, so as to identify the space target to be identified and improve the recognition accuracy.

[0071] In this embodiment, space target recognition based solely on image features faces many challenges, especially under complex observation conditions and target attitude changes. The photosensitive angle under different attitudes will significantly affect the image features of the target. In addition, when the target is in the reentry or maneuvering ignition stage, the strong correlation between its image brightness and the flight stage (such as the active stage, boost stage, glide stage and cruise stage) makes it possible to rely solely on optical image processing methods for target type identification, resulting in a high false alarm rate. In addition, for targets in ultra-short arc segments, the determination of the initial dynamic orbit is often constrained by the singularity of the observation equation, which may cause the orbit to not converge or have a trivial solution, which further affects the reliability of orbit determination. At the same time, for short arc orbit improvement, due to the small amount of data redundancy and the small change in the constructed spatial geometry, the orbit improvement accuracy is reduced, which has little help in improving the success rate of space target recognition. Therefore, by fusing image features and orbit features to comprehensively describe the image characteristics and orbit characteristics of space targets, the space target recognition method that integrates the image and orbit determination results fuses image features and orbit features, and can make full use of the complementary information of the two. Image features provide the appearance and morphological characteristics of the target, while orbit features provide key parameters for the dynamic behavior and motion state of the target. By combining them with each other, the target recognition capability can be significantly enhanced, the recognition accuracy can be improved, and the false alarm rate can be effectively reduced.

[0072] In this embodiment, since the dimensions of the image features and the track features are different, all features are standardized using the Min-Max scaling principle, and the standardized image features and track features are directly spliced ​​to form a new fusion feature.

[0073] In this embodiment, a recognition model is pre-trained based on a large model technology, and a spatial target is recognized based on the trained recognition model and fusion features to obtain a preliminary recognition result.

[0074] In this embodiment, for the space target with cataloged data, the preliminary recognition result needs to be verified based on the historical cataloged data to obtain the space target recognition result.

[0075] In this embodiment, the preliminary recognition result includes basic information of the space target to be recognized, and the verification of the preliminary recognition result based on the historical cataloging data to obtain the space target recognition result includes: matching a verification target in the historical catalog database based on the basic information; The orbit error is calculated based on the basic information and the verification target, the preliminary recognition result is verified based on a preset orbit error, and the space target recognition result is obtained based on the verification result.

[0076] In this embodiment, before the identification of a space target, for the identification of a space target with cataloged data, before the identification of a space target, the historical catalog database should be updated to the time node closest to the epoch time according to the orbital epoch time of the space target to be identified, so as to ensure the timeliness and accuracy of the orbital data used in the subsequent identification; In this embodiment, based on the given forecast start time, forecast end time, and forecast step, orbit forecasts are performed for all satellites and other carriers and space targets to be identified in the historical catalog database to obtain their position and velocity information in the J2000 coordinate system.

[0077] In this embodiment, the orbital errors between the space target and all satellite carriers in the catalog database are calculated respectively; and all orbital errors are sorted. The orbital errors are specifically: (18) (19) in, is the position error between the space target to be identified and the carrier numbered p in the catalog library, It is the position error between the space target to be identified and the carrier numbered p in the catalog library.

[0078] In this embodiment, the calculated orbit error is compared with the set target recognition threshold. If the orbit error is within the target recognition threshold, the space target to be identified is matched with the target name and ID in the catalog database to confirm its identity. After the target is identified, the identification result is further verified. The identification result can be cross-verified by other external measurement data (such as real-time tracking system, radar monitoring, etc.) to ensure the accuracy and reliability of the identification.

[0079] In this embodiment, based on the verification feedback of the recognition results, the error sources and potential problems in the recognition process are analyzed. Based on the feedback information, the algorithm and threshold setting of target recognition are optimized to improve the accuracy and efficiency of recognition. As new track data is continuously acquired, the catalog database is regularly updated to maintain the timeliness and accuracy of the data.

[0080] In this embodiment, by utilizing the basic information in the preliminary recognition result, matching targets are searched in the historical catalog database, and the difference between the orbital parameters of the preliminary recognition result and the target in the historical catalog database is quantified based on the orbital error, so as to verify the preliminary recognition result, and based on the preset orbital error threshold, it is determined whether the preliminary recognition result meets the requirements, thereby determining the space target recognition result to improve the recognition accuracy and avoid misjudgment.

[0081] In this embodiment, the images taken by the observation payload are analyzed by combining image processing methods such as image filtering, binarization, edge extraction, and centroid calculation. The space target type recognition based on image characteristics is to analyze the grayscale characteristics of the target, such as grayscale maximum value, diffusion area, grayscale gradient, grayscale average value, etc. and combine them with dynamic observation data, which can effectively improve the accuracy of distinguishing the type of space target. At the same time, the space target orbit calculation results and image recognition results are integrated to associate and match the space target with the prior cataloging information, which helps to improve the accuracy of the target orbit initial value estimation, and finally improve the efficiency and accuracy of space target recognition.

[0082] The embodiment of the present invention also provides a near-Earth space target recognition device, including: an image feature extraction module, a track feature extraction module and a fusion recognition module; The image feature extraction module is used to obtain a space-based measurement picture, obtain morphological information of a space target to be identified and a centroid position of the space target to be identified based on the space-based measurement picture, and obtain image features based on the morphological information and the centroid position; The orbit feature extraction module is used to obtain observation data based on the observation platform, build a geometric relationship model based on the observation data, and determine the target orbit of the space target to be identified based on the geometric relationship model and the Laplace method to obtain orbit features; the geometric relationship model is a geometric relationship model between the space target to be identified, the observation platform and the center of the earth; The fusion recognition module is used to obtain fusion features based on the image features and the orbital features, and to identify the space target to be identified based on the fusion features and the historical catalog database to obtain a space target identification result.

[0083] In this embodiment, the image feature extraction module is used to: Generate a filter operator matrix based on a preset filter, and perform filtering processing on the space-based measurement image based on the filter operator matrix to obtain a filtered image; Binarize the filtered image based on a preset grayscale threshold to generate a grayscale image; Extracting edges of the grayscale image based on a preset first edge detection algorithm to obtain morphological information of the space target; The target contour of the grayscale image is identified based on a preset second edge detection algorithm, and the center of mass position of the space target is acquired based on the target contour.

[0084] In this embodiment, the observation data includes a space target position vector and an observation platform position vector, wherein the space target position vector is a position vector of the space target relative to the center of the earth, and the observation platform position vector is a position vector of the observation platform relative to the center of the earth; the orbit feature extraction module is used to: Constructing the geometric relationship based on the space target position vector and the observation platform position vector; Constructing a geocentric distance equation of the space target based on the Laplace method, and obtaining initial orbit parameters based on the geometric relationship and the geocentric distance equation; An observation model and an error model are constructed based on the initial orbit parameters, and the initial orbit parameters are optimized based on the observation model and the error model to determine the target orbit and obtain orbit characteristics.

[0085] In this embodiment, the fusion identification module is used to: Performing standardization processing on the image features and the track features to obtain standard image features and standard track features; Perform stitching based on the standard image features and the standard track features to obtain fusion features; Inputting the fusion features into a pre-trained target recognition model, identifying the spatial target to be identified, and obtaining a preliminary recognition result; The preliminary recognition result is verified based on the historical cataloging data to obtain a space target recognition result.

[0086] In this embodiment, the fusion identification module is used to: matching a verification target in the historical catalog database based on the basic information; The orbit error is calculated based on the basic information and the verification target, the preliminary recognition result is verified based on a preset orbit error, and the space target recognition result is obtained based on the verification result.

[0087] In an embodiment of the present invention, a terminal device is also provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the above-mentioned near-Earth space target identification method when executing the computer program.

[0088] In an embodiment of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored computer program. When the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned near-Earth space target identification method.

[0089] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0090] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor, a memory, and a display. Those skilled in the art will appreciate that the above components are merely examples of the terminal device and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0091] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0092] The memory can be used to store computer programs and / or modules. The processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0093] Among them, if the module based on the identification of near-Earth space targets is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0094] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A near-Earth space target recognition method, characterized in that: include: Acquire a space-based measurement picture, acquire morphological information of a space target to be identified and a centroid position of the space target to be identified based on the space-based measurement picture, and acquire image features based on the morphological information and the centroid position; Acquire observation data based on the observation platform, construct a geometric relationship model based on the observation data, and determine the target orbit of the space target to be identified based on the geometric relationship model and the Laplace method to obtain orbital characteristics; the geometric relationship model is a geometric relationship model between the space target to be identified, the observation platform and the center of the earth; A fusion feature is obtained based on the image feature and the orbit feature, and the space target to be identified is identified based on the fusion feature and a historical catalog database to obtain a space target identification result.

2. A near-Earth space target recognition method according to claim 1, characterized in that: The acquiring the morphological information of the space target and the center of mass position of the space target based on the space-based measurement picture includes: Generate a filter operator matrix based on a preset filter, and perform filtering processing on the space-based measurement image based on the filter operator matrix to obtain a filtered image; Binarize the filtered image based on a preset grayscale threshold to generate a grayscale image; Performing edge extraction on the grayscale image based on a preset first edge detection algorithm to obtain morphological information of the space target to be identified; The target contour of the grayscale image is identified based on a preset second edge detection algorithm, and the center of mass position of the space target is acquired based on the target contour.

3. A near-Earth space target recognition method as claimed in claim 2, characterized in that: The observation data includes a space target position vector and an observation platform position vector, wherein the space target position vector is a position vector of the space target relative to the center of the earth, and the observation platform position vector is a position vector of the observation platform relative to the center of the earth; The step of constructing a geometric relationship model based on the observation data comprises: Constructing the geometric relationship based on the space target position vector and the observation platform position vector; Constructing a geocentric distance equation of the space target based on the Laplace method, and obtaining initial orbit parameters based on the geometric relationship and the geocentric distance equation; An observation model and an error model are constructed based on the initial orbit parameters, and the initial orbit parameters are optimized based on the observation model and the error model to determine the target orbit and obtain orbit characteristics.

4. A near-Earth space target recognition method as claimed in claim 3, characterized in that: The acquiring of fusion features based on the image features and the orbital features, and identifying the space target to be identified based on the fusion features and a historical catalog database to obtain a space target identification result includes: Performing standardization processing on the image features and the track features to obtain standard image features and standard track features; Perform stitching based on the standard image features and the standard track features to obtain fusion features; Inputting the fusion features into a pre-trained target recognition model, identifying the spatial target to be identified, and obtaining a preliminary recognition result; The preliminary recognition result is verified based on the historical cataloging data to obtain a space target recognition result.

5. A near-Earth space target recognition method as claimed in claim 4, characterized in that: The preliminary recognition result includes basic information of the space target to be recognized, and the verification of the preliminary recognition result based on the historical cataloging data to obtain the space target recognition result includes: matching a verification target in the historical catalog database based on the basic information; The orbit error is calculated based on the basic information and the verification target, the preliminary recognition result is verified based on a preset orbit error, and the space target recognition result is obtained based on the verification result.

6. A near-Earth space target recognition device, characterized in that: include: Image feature extraction module, track feature extraction module and fusion recognition module; The image feature extraction module is used to obtain a space-based measurement picture, obtain morphological information of a space target to be identified and a centroid position of the space target to be identified based on the space-based measurement picture, and obtain image features based on the morphological information and the centroid position; The orbit feature extraction module is used to obtain observation data based on an observation platform, build a geometric relationship model based on the observation data, and determine the target orbit of the space target to be identified based on the geometric relationship model and the Laplace method to obtain orbit features; The geometric relationship model is a geometric relationship model between the space target to be identified, the observation platform and the center of the earth; The fusion recognition module is used to obtain fusion features based on the image features and the orbital features, and to identify the space target to be identified based on the fusion features and the historical catalog database to obtain a space target identification result.

7. A near-Earth space target identification device as claimed in claim 6, characterized in that: The image feature extraction module is used to: Generate a filter operator matrix based on a preset filter, and perform filtering processing on the space-based measurement image based on the filter operator matrix to obtain a filtered image; Binarize the filtered image based on a preset grayscale threshold to generate a grayscale image; Extracting edges of the grayscale image based on a preset first edge detection algorithm to obtain morphological information of the space target; The target contour of the grayscale image is identified based on a preset second edge detection algorithm, and the center of mass position of the space target is acquired based on the target contour.

8. A near-Earth space target identification device as claimed in claim 7, characterized in that: The observation data includes a space target position vector and an observation platform position vector, wherein the space target position vector is a position vector of the space target relative to the center of the earth, and the observation platform position vector is a position vector of the observation platform relative to the center of the earth; the orbit feature extraction module is used to: Constructing the geometric relationship based on the space target position vector and the observation platform position vector; Constructing a geocentric distance equation of the space target based on the Laplace method, and obtaining initial orbit parameters based on the geometric relationship and the geocentric distance equation; An observation model and an error model are constructed based on the initial orbit parameters, and the initial orbit parameters are optimized based on the observation model and the error model to determine the target orbit and obtain orbit characteristics.

9. A near-Earth space target identification device as claimed in claim 8, characterized in that: The fusion recognition module is used to: Performing standardization processing on the image features and the track features to obtain standard image features and standard track features; Perform stitching based on the standard image features and the standard track features to obtain fusion features; Inputting the fusion features into a pre-trained target recognition model, identifying the spatial target to be identified, and obtaining a preliminary recognition result; The preliminary recognition result is verified based on the historical cataloging data to obtain a space target recognition result.

10. A near-Earth space target recognition device as claimed in claim 9, characterized in that: The preliminary recognition result includes basic information of the space target to be recognized, and the fusion recognition module is used to: matching a verification target in the historical catalog database based on the basic information; The orbit error is calculated based on the basic information and the verification target, the preliminary recognition result is verified based on a preset orbit error, and the space target recognition result is obtained based on the verification result.

Images