A moving target detection method in satellite video based on low-rank sparse matrix decomposition

Abstract

This application discloses a method for detecting moving targets in satellite videos based on low-rank sparse matrix decomposition, relating to the field of data processing technology. This solution considers the impact of dynamically changing backgrounds in videos on moving target detection, using singular value components and a minimized norm to characterize the low-rank nature of the dynamically changing background, thereby more accurately restoring the background image under dynamic changes. Furthermore, a non-convex #imgabs0# norm is used to constrain sparse foreground targets to enhance robustness to noise, while a total variation regularization term is used to suppress dynamic background pixels. This allows for the construction of a moving target detection model that can better distinguish between background and target, thereby improving the accuracy of target image detection in satellite video image data.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for detecting moving targets in satellite videos based on low-rank sparse matrix decomposition. Background Art

[0002] Moving object detection in video satellite data aims to separate targets from complex backgrounds. Background changes in satellite video data are typically slow. Background regions typically exhibit a certain degree of autocorrelation and continuity, and are therefore considered low-rank. Moving targets occupy a very small portion of satellite video images, and are therefore considered sparse.

[0003] Therefore, the problem of detecting moving targets in satellite videos can be transformed into a low-rank sparse reconstruction problem. Although many current satellite video moving target detection methods based on the classic principal component analysis method have achieved good detection performance, they cannot guarantee high detection accuracy in dynamically changing backgrounds, because the dynamic changing background has similarities with the target changes in the temporal domain.

[0004] In view of the above, how to solve the problem that the current satellite video moving target detection cannot guarantee high detection accuracy in a dynamically changing background is an urgent problem to be solved by technicians in this field. Summary of the Invention

[0005] The purpose of this application is to provide a satellite video moving target detection method based on low-rank sparse matrix decomposition to solve the problem that the current satellite video moving target detection cannot guarantee high detection accuracy in a dynamically changing background.

[0006] To solve the above technical problems, the present application provides a method for satellite video moving target detection based on low-rank sparse matrix decomposition, comprising:

[0007] Acquire satellite video image data, and construct a satellite video matrix data model based on the satellite video image data;

[0008] Constructing a total variation regularization term model based on the satellite video image data;

[0009] According to the satellite video matrix data model, a background model based on the singular value part and the minimized norm and a background model based on the non-convex Norm foreground model;

[0010] According to the background model based on the singular value part and the minimized norm, the non-convex norm foreground model and the total variation regularization term model to construct a moving target detection algorithm model;

[0011] Solve the moving target detection algorithm model to obtain the target image of the satellite video image data.

[0012] On the one hand, constructing a satellite video matrix data model based on the satellite video image data includes:

[0013] Vectorizing the satellite video image data;

[0014] The vectorized satellite video image data is decomposed into a background matrix and a foreground matrix to obtain the satellite video matrix data model.

[0015] On the other hand, a total variation regularization term model is constructed based on the satellite video image data, including:

[0016] Obtaining differential values ​​of pixel values ​​in the satellite video image data in the horizontal direction, the vertical direction, and the time direction;

[0017] Vectorizing the difference values ​​to obtain a spatial image long-dimension difference matrix, a spatial image wide-dimension difference matrix, and a time-dimension difference matrix;

[0018] The total variation regularization term model is constructed according to the spatial image long dimension difference matrix, the spatial image wide dimension difference matrix and the time dimension difference matrix.

[0019] On the other hand, the formula of the moving target detection algorithm model includes:

[0020] ;

[0021] in, is the background model based on the singular value part and the minimization norm, For the non-convex norm foreground model, is the total variation regularization model, is the satellite video matrix data model, is the background matrix, is the foreground matrix, is the moving background and dynamically changing background matrix caused by local misalignment and illumination changes, is the number of singular values, and are the hyperparameters of the constrained foreground regularization term and the total variation regularization term, respectively.

[0022] On the other hand, solving the moving target detection algorithm model to obtain the target image of the satellite video image data includes:

[0023] Constructing a Lagrangian function according to the moving target detection algorithm model;

[0024] The Lagrangian function is decomposed by an alternating direction multiplier method to obtain the target image.

[0025] On the other hand, the decomposition of the Lagrangian function by the alternating direction multiplier method includes:

[0026] updating the background matrix based on the Lagrangian function;

[0027] updating the foreground matrix based on the Lagrangian function;

[0028] Update the motion background and dynamically changing background matrices based on the Lagrangian function;

[0029] updating the Lagrangian operator of the Lagrangian function according to the updated background matrix, the updated foreground matrix, and the updated moving background and dynamically changing background matrices;

[0030] Determine whether the preset number of iterations has been reached or the preset conditions have been met;

[0031] If yes, output the updated background matrix, the updated foreground matrix, and the updated moving background and dynamically changing background matrices;

[0032] If not, the process returns to the step of updating the background matrix based on the Lagrangian function.

[0033] On the other hand, after obtaining the target image, the method further includes:

[0034] When there is a single moving target in the target image, continuously tracking the moving target and recording the corresponding motion trajectory and state changes;

[0035] When there are multiple moving targets in the target image, each of the moving targets is tracked simultaneously, and the relative positions and movement relationships between the moving targets are analyzed.

[0036] On the other hand, after obtaining the target image, the method further includes:

[0037] When there is a moving target in the target image, continuously tracking the moving target;

[0038] Determine whether the motion trajectory and state of the moving target have changed according to a preset period;

[0039] If so, output an alarm message indicating that the moving target is abnormal.

[0040] On the other hand, after obtaining the target image, the method further includes:

[0041] When there is a moving target in the target image, obtaining the appearance features of the moving target;

[0042] The type and attributes of the moving object are determined according to the appearance features.

[0043] On the other hand, after determining the type and attributes of the moving object according to the appearance features,

[0044] The information of each type of sports target is stored in a database in the form of reports and / or charts.

[0045] The satellite video moving target detection method based on low-rank sparse matrix decomposition provided in this application obtains satellite video image data and constructs a satellite video matrix data model based on the satellite video image data; constructs a total variation regularization term model based on the satellite video image data; constructs a background model based on the singular value part and the minimization norm and a non-convex matrix model based on the satellite video matrix data model. norm foreground model; based on the background model based on the singular value part and the minimized norm, based on the non-convex The foreground model of the norm and the total variation regularization term model are used to construct the moving target detection algorithm model; the moving target detection algorithm model is solved to obtain the target image of the satellite video image data. It can be seen that this scheme takes into account the influence of the dynamic background in the video on the moving target detection, and uses the singular value part and the minimized norm to represent the low rank of the dynamic background, so as to more accurately restore the background image under dynamic changes; on this basis, the non-convex Norm constraints are used to sparse foreground targets to enhance robustness to noise. At the same time, the total variation regularization term is used to suppress dynamic background pixels, thereby constructing a moving target detection model that can better distinguish between background and target, thereby improving the accuracy of target image detection in satellite video image data. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 A flowchart of a method for satellite video moving target detection based on low-rank sparse matrix decomposition provided in an embodiment of the present application;

[0048] Figure 2 A first schematic diagram of minimizing the nuclear norm provided in an embodiment of the present application;

[0049] Figure 3A second schematic diagram of minimizing the nuclear norm provided in an embodiment of the present application;

[0050] Figure 4 Provided in the embodiments of this application 、 and One-dimensional diagram of the norm. DETAILED DESCRIPTION

[0051] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0052] The core of this application is to provide a satellite video moving target detection method based on low-rank sparse matrix decomposition to solve the problem that the current satellite video moving target detection cannot guarantee high detection accuracy in a dynamically changing background.

[0053] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0054] Currently, many satellite video moving target detection methods based on low-rank sparse matrix decomposition, which are based on the classic principal component analysis method, have achieved good detection performance. However, they cannot guarantee high detection accuracy in dynamically changing backgrounds, because the dynamic changing background has similarities with the target changes in the time domain. Therefore, to address the above problems, this application provides a satellite video moving target detection method based on low-rank sparse matrix decomposition.

[0055] Figure 1 The flowchart of a method for detecting moving targets in satellite video based on low-rank sparse matrix decomposition is provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0056] S10: Acquire satellite video image data, and construct a satellite video matrix data model based on the satellite video image data.

[0057] To achieve moving target recognition in satellite images, satellite video image data must first be acquired. It should be noted that the satellite video image data is a video sequence. Simultaneously, a satellite video matrix data model is constructed based on the satellite video image data. The satellite video matrix data model converts the satellite video image data into matrix data. The process of constructing the satellite video matrix data model is not limited in this embodiment.

[0058] S11: Construct a total variation regularization model based on satellite video image data.

[0059] Furthermore, a total variation regularization model is constructed based on the satellite video image data. The total variation (TV) regularization term is a common regularization method used in image processing and optimization problems. Its primary function is to maintain image smoothness by minimizing the sum of differences between adjacent pixels in the image, thereby suppressing noise and preserving edge information. This embodiment does not impose any restrictions on the construction process of the total variation regularization model.

[0060] S12: Based on the satellite video matrix data model, a background model based on the singular value part and the minimized norm is constructed and a non-convex Norm foreground model.

[0061] When there is a large amount of measurement noise interference in the image, the recovery performance of the Nuclear Norm (NN) convex relaxation algorithm will drop sharply, and the recovered solution will seriously deviate from the original solution of the rank minimization optimization problem, and the estimated rank will be over-shrink. Figure 2 This is the first schematic diagram of minimizing the nuclear norm provided by the embodiment of the present application. Figure 2 As shown, the horizontal axis X1 represents the ground truth value, and the vertical axis X2 represents the estimated value. The green represents the true value, and the true value subspace (green) is a one-dimensional straight line with sparse outliers and noise. Figure 2 , the estimated subspace is biased towards the estimated axis which has a smaller nuclear norm but the second singular value is larger than the ground truth coordinate. Figure 3 This is a second schematic diagram of minimizing the nuclear norm provided in an embodiment of the present application. Figure 3 In , the horizontal axis X1 represents the ground truth value, and the vertical axis X2 represents the estimated value. Some inliers located on the true subspace are regarded as outliers to obtain smaller singular values.

[0062] In order to more reasonably utilize the prior knowledge represented by different singular values ​​and treat each rank component differently to improve the low-rank recovery accuracy, instead of using the same weights as in Nuclear Norm Minimization (NNM), this scheme adopts Partial Sum Minimization of Singular Values ​​(PSSV), which discards the smallest - singular values, keep the largest unchanged, among which is the number of singular values, is the rank of the matrix. The PSSV norm is defined as:

[0063] ;

[0064] in, Background matrix The target rank, It is before indivual The singular values ​​of Background matrix of The largest singular value, for and The upper limit of the ratio is also the rank of the matrix, and The background matrix The number of rows and columns.

[0065] The PSSV norm minimizes the variance of the residual rank while maintaining large singular values, thereby preserving the principal components of the data and improving the accuracy of background image restoration in dynamic satellite video. Compared with traditional nuclear norm minimization methods, the PSSV norm minimizes some singular values, making the soft threshold more reasonable. As a result, the difference between target and background motion becomes clear and measurable, making it easier for detection models to remove the background.

[0066] On the other hand, although Norm replacement norm can better solve sparse terms, however The norm may cause the result to fall into the local minimum instead of the global minimum, which will affect the effect of sparse constraints. In addition, it does not consider the spatial correlation of foreground pixels. In order to improve the foreground smoothness caused by the constraint, the performance is better than of norm to enforce the sparsity constraint. Figure 4 Provided in the embodiments of this application 、 and One-dimensional diagram of the norm. Figure 4 As shown, the horizontal axis X represents the absolute value of the one-dimensional variable, and the vertical axis Y represents the norm value. Norm and One-dimensional example of the norm, as can be seen from the figure Norm Ratio The curve of the norm is closer to norm. The norm has been proven to not only fully utilize spatial correlation and feature similarity to restore sparse targets and obtain a sparser solution, but also use fewer iterations to reach convergence while reducing the amount of computation. Therefore, the foreground matrix is ​​defined as:

[0067] ;

[0068] in, is the foreground matrix, For the Rank The pixel value of the column.

[0069] In summary, this application specifically constructs a background model based on the singular value part and the minimized norm and a background model based on the non-convex The foreground model based on the norm can more accurately restore the background image under dynamic changes, and can also constrain sparse foreground targets to enhance robustness to noise.

[0070] S13: Based on the background model based on the singular value part and the minimized norm, based on the non-convex The norm foreground model and total variation regularization term model are used to build a moving target detection algorithm model.

[0071] S14: Solve the moving target detection algorithm model to obtain the target image of the satellite video image data.

[0072] Furthermore, by integrating the background model, the foreground model and the total variation regularization term model, a moving target detection algorithm model is constructed. In this embodiment, there is no restriction on the expression of the moving target detection algorithm model, which depends on the specific implementation situation.

[0073] Finally, the moving target detection algorithm model is solved to obtain the target image of the satellite video image data, realizing the moving target recognition of satellite images.

[0074] In this embodiment, satellite video image data is obtained and a satellite video matrix data model is constructed based on the satellite video image data; a total variation regularization term model is constructed based on the satellite video image data; a background model based on the singular value part and the minimization norm and a background model based on the non-convex matrix are constructed based on the satellite video matrix data model. norm foreground model; based on the background model based on the singular value part and the minimized norm, based on the non-convex The foreground model of the norm and the total variation regularization term model are used to construct the moving target detection algorithm model; the moving target detection algorithm model is solved to obtain the target image of the satellite video image data. It can be seen that this scheme takes into account the influence of the dynamic background in the video on the moving target detection, and uses the singular value part and the minimized norm to represent the low rank of the dynamic background, so as to more accurately restore the background image under dynamic changes; on this basis, the non-convex Norm constraints are used to sparse foreground targets to enhance robustness to noise. At the same time, the total variation regularization term is used to suppress dynamic background pixels, thereby constructing a moving target detection model that can better distinguish between background and target, thereby improving the accuracy of target image detection in satellite video image data.

[0075] Based on the above embodiments, in some embodiments, constructing a satellite video matrix data model based on satellite video image data includes:

[0076] S101: performing vectorization processing on satellite video image data;

[0077] S102: Decomposing the vectorized satellite video image data into a background matrix and a foreground matrix to obtain a satellite video matrix data model.

[0078] Specifically, assuming that the given satellite image video sequence is , which is vectorized into .in, 、 and are the height, width, and number of frames of the video image. Generally, the vectorized video sequence can be decomposed into foreground and background. Therefore, the satellite video matrix data model is as follows:

[0079] ;

[0080] in, is the satellite video matrix data model, is the background matrix; is the foreground matrix, which contains the moving target.

[0081] In this way, the construction of the satellite video matrix data model is realized.

[0082] Based on the above embodiments, in some embodiments, a total variation regularization term model is constructed based on satellite video image data, including:

[0083] S111: Obtaining differential values ​​of pixel values ​​in the satellite video image data in the horizontal direction, the vertical direction, and the time direction;

[0084] S112: performing vectorization processing on each difference value to obtain a spatial image long dimension difference matrix, a spatial image wide dimension difference matrix, and a time dimension difference matrix;

[0085] S113: Construct a total variation regularization term model based on the spatial image long dimension difference matrix, the spatial image wide dimension difference matrix, and the time dimension difference matrix.

[0086] It is understandable that derivatives can be used to measure the sensitivity of a function to changes. For discrete functions, the differential operator is an approximation of the derivative. Therefore, in order to construct the total variation regularization term model, it is necessary to calculate the differential values ​​of the pixel values ​​in the video sequence image in the horizontal, vertical, and temporal directions. Specifically, the differential values ​​of the pixel values ​​in the satellite video image data in the horizontal, vertical, and temporal directions are obtained:

[0087] ;

[0088] in, are the length, width and time frames of the video data image respectively.

[0089] Then these results are matrix-vectorized to obtain the long-dimensional difference matrix of the spatial image , spatial image wide dimension difference matrix and the time dimension difference matrix .Will , and Merge into one matrix to get the total difference matrix , the total variation regularization model is as follows:

[0090] ;

[0091] in, , and Represents the intensity changes on the horizontal, vertical and time axes respectively.

[0092] In this way, the construction of the total variation regularization term model is realized.

[0093] Based on the above embodiment, in this embodiment, the formula of the moving target detection algorithm model includes:

[0094] ;

[0095] in, is a background model based on the singular value part and the minimization norm, Based on non-convex norm foreground model, is the total variation regularization model, is the satellite video matrix data model, is the background matrix, is the foreground matrix, is the moving background and dynamically changing background matrix caused by local misalignment and illumination changes, is the number of singular values, and are the hyperparameters of the constrained foreground regularization term and the total variation regularization term, respectively. It should be noted that when The value is fixed When it becomes small enough, the model will degenerate into a special case, namely, moving target detection in a static background.

[0096] Based on the above embodiments, in some embodiments, solving a moving target detection algorithm model to obtain a target image of satellite video image data includes:

[0097] S141: Constructing Lagrangian function based on the moving target detection algorithm model;

[0098] S142: Decomposing the Lagrangian function by an alternating direction multiplier method to obtain a target image.

[0099] In order to solve the moving target detection algorithm model, we first need to establish the Lagrangian function:

[0100] ;

[0101] in, is the Lagrange multiplier matrix, is a positive penalty scalar, represents the inner product of matrices, is the Frobenius norm.

[0102] Since it is difficult to optimize all the above variables simultaneously, in this embodiment, the Lagrangian function is decomposed by the Alternating Direction Method of Multipliers (ADMM), which is specifically decomposed into the following sub-problems:

[0103] (1) Background matrix Updates;

[0104] Specifically, the background matrix is ​​updated based on the Lagrangian function. It should be noted that the update , while keeping other variables unchanged.

[0105] ;

[0106] therefore, The solution formula is:

[0107] ;

[0108] in, is the Partial Singular Value Thresholding Operator (PSVT), and k is the number of iterations. According to the relevant public theories, we can get:

[0109] ;

[0110] ;

[0111] in, is a soft threshold operator. It can be solved using Singular Value Decomposition (SVD), and can be considered as the sum of two matrices, namely:

[0112] ;

[0113] in, 、 、 、 、 、 、 、 and are all singular vector matrices.

[0114] (2) Foreground Matrix Updates;

[0115] Specifically, the foreground matrix is ​​updated based on the Lagrangian function. It should be noted that the update , but also keep other variables unchanged.

[0116] ;

[0117] It can be understood that the above formula is a typical Regularization term constraint problem. Therefore, the optimal solution can be obtained by element-wise contraction operation:

[0118] ;

[0119] in, is the element-wise contraction operator.

[0120] (3) Motion background and dynamic change background matrix Updates;

[0121] Specifically, the motion background and dynamic change background matrices are updated based on the Lagrangian function. During the optimization process, The update can be done through the following steps:

[0122] ;

[0123] Using TV norm regularization, we can get the solution:

[0124] ;

[0125] in, It is the TV operator.

[0126] Furthermore, the Lagrangian operator of the Lagrangian function is updated according to the updated background matrix, the updated foreground matrix, and the updated motion background and dynamically changing background matrices:

[0127] ;

[0128] During the optimization process, all variables are iteratively updated, and it is determined whether the preset number of iterations is reached or the preset conditions are met; if so, the updated background matrix, updated foreground matrix, and updated motion background and dynamically changing background matrices are output; if not, the process returns to the step of updating the background matrix based on the Lagrangian function.

[0129] It should be noted that the preconditions are:

[0130] ;

[0131] in, .

[0132] In summary, the moving target detection algorithm model is solved and the target image is obtained.

[0133] Based on the above embodiment, in some embodiments, after obtaining the target image, the method further includes:

[0134] S15: When there is a single moving target in the target image, the moving target is continuously tracked and the corresponding motion trajectory and state changes are recorded;

[0135] S16: When there are multiple moving targets in the target image, each moving target is tracked simultaneously, and the relative position and movement relationship between the moving targets are analyzed.

[0136] After detecting a target image in satellite video image data, target tracking can be further performed, which can provide in-depth insights into the target's motion patterns and behavioral characteristics. Target tracking can be categorized into two main forms: single-target tracking and multi-target tracking.

[0137] Single target tracking focuses on the continuous monitoring of a single detected moving target. By recording the target's trajectory and state changes, such as position, velocity, and acceleration, single target tracking can reveal the target's individual behavioral characteristics. The advantage of this tracking method lies in its precise focus on a specific target, enabling detailed analysis of the target's short- and long-term movement trends. For example, in wildlife conservation, single target tracking can help researchers understand animal migration routes and living habits.

[0138] Multi-target tracking involves simultaneously tracking multiple moving targets in a video and analyzing their relative positions and motion relationships. This tracking method provides a broader perspective, revealing the behavioral patterns and interaction mechanisms of target groups. The advantage of multi-target tracking lies in its adaptability to complex scenarios and its ability to handle occlusion, intersection, and separation between targets. In traffic monitoring, multi-target tracking can be used to calculate traffic flow, detect traffic incidents, and provide data support for traffic planning and management. Furthermore, in military and security applications, multi-target tracking can help monitoring personnel promptly detect and address potential threats.

[0139] In this embodiment, target tracking, as a follow-up to moving target detection, provides strong support for research and practice in various fields by recording and analyzing the target's motion trajectory and state changes. Whether focusing on a single target or analyzing multiple targets in groups, target tracking can reveal the target's behavioral characteristics and interaction mechanisms, providing decision support and scientific basis for related applications.

[0140] Based on the above embodiment, in some embodiments, after obtaining the target image, the method further includes:

[0141] S17: When there is a moving target in the target image, the moving target is continuously tracked.

[0142] S18: Determine whether the motion trajectory and state of the moving target have changed according to a preset period; if so, proceed to step S19.

[0143] S19: Outputting alarm information indicating that there is an abnormality in the moving target.

[0144] After detecting moving targets in satellite video imagery, anomaly detection and early warning are important applications in moving target tracking and analysis. Specifically, when a moving target is present in the target image, it is continuously tracked. By monitoring the target's motion trajectory and behavior patterns, deviations from normal patterns, such as sudden acceleration or deviation from the planned route, can be identified. These abnormal behaviors may indicate potential problems or threats, requiring further attention and action. Anomaly detection algorithms, typically based on statistical methods or machine learning techniques, can automatically identify unusual patterns from large amounts of data.

[0145] Furthermore, the system determines whether the target's trajectory and state have changed based on a preset period. If so, the security warning system can issue a timely alert based on the anomaly detection results, alerting personnel to take appropriate action or taking necessary measures. This early warning mechanism is crucial in many areas, including traffic safety, border surveillance, and environmental protection. Combining anomaly detection with real-time warnings can significantly improve the speed and efficiency of responding to potential risks.

[0146] Based on the above embodiment, in some embodiments, after obtaining the target image, the method further includes:

[0147] S20: When there is a moving target in the target image, obtain the appearance features of the moving target.

[0148] S21: Determine the type and attributes of the moving target based on the appearance features.

[0149] After detecting moving targets in satellite video imagery, target classification and recognition are critical follow-up steps. Target type recognition analyzes the target's appearance, motion patterns, and other information to classify the target into different categories, such as airplanes, cars, and ships. This recognition not only relies on static features such as shape and color but also considers dynamic behavior, such as speed and trajectory. Accurate target type recognition is crucial for many applications.

[0150] Furthermore, target attribute analysis delves deeper into the details of the target, including attributes such as size, shape, and color. These attributes provide additional information about the target, enabling more refined analysis and decision-making. For example, in environmental monitoring, analyzing the size and shape of wildlife can help determine species, while color information can be used to identify specific individuals. Target attribute analysis enriches our understanding of the target and provides more comprehensive support for subsequent data mining and applications.

[0151] In addition, after determining the type of moving target based on appearance characteristics, the information of each type of moving target can be stored in the database in the form of reports and / or charts. This can not only more comprehensively display the trends and patterns behind the data, but also be stored as historical data to facilitate subsequent possible data analysis.

[0152] The above is a detailed introduction to a satellite video moving target detection method based on low-rank sparse matrix decomposition provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the scope of protection of this application.

[0153] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

Claims

1. A method for satellite video moving target detection based on low-rank sparse matrix decomposition, characterized in that: include: Acquire satellite video image data, and construct a satellite video matrix data model based on the satellite video image data; Constructing a total variation regularization term model based on the satellite video image data; According to the satellite video matrix data model, a background model based on the singular value part and the minimized norm and a background model based on the non-convex norm foreground model; where ; According to the background model based on the singular value part and the minimized norm, the non-convex norm foreground model and the total variation regularization term model to construct a moving target detection algorithm model; Solving the moving target detection algorithm model to obtain a target image of the satellite video image data; A total variation regularization term model is constructed based on the satellite video image data, including: Obtain the differential values ​​of the pixel values ​​in the satellite video image data in the horizontal direction, vertical direction, and time direction; the specific formula is as follows: ； in, are the length, width and time frame number of the video data image respectively; Each of the differential values ​​is vectorized to obtain the long-dimensional difference matrix of the spatial image , spatial image wide dimension difference matrix and the time dimension difference matrix ; The total variation regularization term model is constructed according to the spatial image long-dimensional difference matrix, the spatial image wide-dimensional difference matrix, and the time-dimensional difference matrix. The specific formula is as follows: ； in, , and Represents the intensity changes on the horizontal, vertical and time axes respectively; The formula of the moving target detection algorithm model includes: ； in, is the background model based on the singular value part and the minimization norm, For the non-convex norm foreground model, is the total variation regularization model, is the satellite video matrix data model, is the background matrix, is the foreground matrix, is the moving background and dynamically changing background matrix caused by local misalignment and illumination changes, is the number of singular values, and are the hyperparameters of the constrained foreground regularization term and the total variation regularization term, respectively.

2. The method for satellite video moving target detection based on low-rank sparse matrix decomposition according to claim 1, characterized in that: Constructing a satellite video matrix data model according to the satellite video image data, including: Vectorizing the satellite video image data; The vectorized satellite video image data is decomposed into a background matrix and a foreground matrix to obtain the satellite video matrix data model.

3. The method for satellite video moving target detection based on low-rank sparse matrix decomposition according to claim 1, characterized in that: Solving the moving target detection algorithm model to obtain the target image of the satellite video image data includes: Constructing a Lagrangian function according to the moving target detection algorithm model; The Lagrangian function is decomposed by an alternating direction multiplier method to obtain the target image.

4. The method for satellite video moving target detection based on low-rank sparse matrix decomposition according to claim 3, characterized in that: The decomposition of the Lagrangian function by the alternating direction multiplier method includes: updating the background matrix based on the Lagrangian function; updating the foreground matrix based on the Lagrangian function; Update the motion background and dynamically changing background matrices based on the Lagrangian function; updating the Lagrangian operator of the Lagrangian function according to the updated background matrix, the updated foreground matrix, and the updated moving background and dynamically changing background matrices; Determine whether the preset number of iterations has been reached; If yes, output the updated background matrix, the updated foreground matrix, and the updated moving background and dynamically changing background matrices; If not, the process returns to the step of updating the background matrix based on the Lagrangian function.

5. The method for satellite video moving target detection based on low-rank sparse matrix decomposition according to any one of claims 1 to 4, characterized in that: After obtaining the target image, the method further includes: When there is a single moving target in the target image, continuously tracking the moving target and recording the corresponding motion trajectory and state changes; When there are multiple moving targets in the target image, each of the moving targets is tracked simultaneously, and the relative positions and movement relationships between the moving targets are analyzed.

6. The method for satellite video moving target detection based on low-rank sparse matrix decomposition according to any one of claims 1 to 4, characterized in that: After obtaining the target image, the method further includes: When there is a moving target in the target image, continuously tracking the moving target; Determine whether the motion trajectory and state of the moving target have changed according to a preset period; If so, output an alarm message indicating that the moving target is abnormal.

7. The method for satellite video moving target detection based on low-rank sparse matrix decomposition according to any one of claims 1 to 4, characterized in that: After obtaining the target image, the method further includes: When there is a moving target in the target image, obtaining the appearance features of the moving target; The type and attributes of the moving object are determined according to the appearance features.

8. The method for satellite video moving target detection based on low-rank sparse matrix decomposition according to claim 7, characterized in that: After determining the type and attributes of the moving object according to the appearance features, The information of each type of sports target is stored in a database in the form of reports and / or charts.

Images