Spatial situational awareness image compression method and system based on aggregated sparse coding

Abstract

A space situational awareness image compression method and system based on aggregated sparse coding. After background segmentation of the collected space situational awareness image, overlapping areas of the foreground are detected and assigned to adjacent satellites. Each satellite sequentially uses aggregated sparse coding based on images from adjacent satellites to obtain a dictionary tensor and coefficient tensor for the assigned overlapping or non-overlapping areas. The coefficient tensor is then further compressed into a transfer tensor and position tensor expressing the pixel relationships in the overlapping areas using an overlap-aware adaptive binary arithmetic coding algorithm. The tensor is then output to a ground station for image reconstruction. This method improves the compression rate of the corresponding image and ensures the quality of image reconstruction. It also utilizes distributed computing to reduce resource consumption during computation on a single satellite, ensuring that the system can still be effectively deployed in low-orbit satellite constellations with limited computing and transmission resources.

Description

Technical Field

[0001] The present invention relates to a technology in the field of image processing, specifically a spatial situational awareness image compression method and system based on aggregated sparse coding. Background Art

[0002] Satellite images are both sparse and temporally correlated, meaning that space situational awareness images contain low information entropy. Specifically, the foreground of such images consists of near-orbital targets, such as space debris, missiles, unusual aircraft, and other fast-moving objects, appearing as sparse white dots or lines, with pixel positions varying across successive images. The background is largely composed of deep space and stationary white dots, such as distant stars and the Milky Way. While capturing parameters (such as field of view and direction) remain consistent, low-orbit satellites undergo periodic motion according to their ephemeris, resulting in periodic repetition of the background in space situational awareness images. Spatially correlated images captured simultaneously by two adjacent low-orbit satellites contain regions with overlapping viewpoints. These overlapping regions represent the same region observed from different angles by adjacent satellites, containing consistent elements such as stars, planets, and aircraft. Existing image compression techniques based on sparse coding exploit the inherent sparsity of space situational awareness images by representing pixels with a reduced set of basic elements. These techniques include decomposition-based and convolution-based approaches. Decomposition-based approaches use a separable dictionary for each image dimension, while convolution-based approaches utilize multidimensional dictionaries to effectively handle high-order correlations. However, these methods have failed to effectively solve the multi-view redundancy problem, and there is no further processing of the overlapping area pixels captured by adjacent low-orbit satellites at the same time. Summary of the Invention

[0003] To address the shortcomings of existing technologies, such as insufficient compression rate, failure to consider the spatiotemporal correlation of images taken by adjacent low-orbit satellites, inability to resolve the spatiotemporal sparsity and redundancy of space situational awareness images, and high computational complexity, the present invention proposes a space situational awareness image compression method and system based on aggregated sparse coding, which improves the compression rate of corresponding images and ensures the quality of image reconstruction. At the same time, the present invention utilizes distributed computing methods to reduce resource consumption during single-satellite computing, ensuring that the system can still be effectively deployed in a low-orbit satellite constellation environment with limited computing and transmission resources.

[0004] The present invention is achieved through the following technical solutions:

[0005] The present invention relates to a space situation awareness image compression method based on aggregated sparse coding. After background segmentation is performed on the collected space situation awareness image, overlapping areas are detected on the foreground and allocated to adjacent satellites. Each satellite obtains a dictionary tensor and coefficient tensor of the allocated overlapping or non-overlapping areas through aggregated sparse coding in sequence based on images from adjacent satellites. The coefficient tensor is then further compressed into a transfer tensor and a position tensor that express the pixel relationship of the overlapping area through an overlap-aware adaptive binary arithmetic coding algorithm, and then output to a ground station for image reconstruction.

[0006] The background segmentation refers to: combining the advantages of sparse coding and local binary pattern, and using the SCS-LBP operator to perform background and foreground segmentation.

[0007] The background segmentation described above outputs the obtained background area to the ground station for image reconstruction.

[0008] The allocation means that N low-orbit satellites in the same layer are assigned serial numbers in the range of [0, N] in advance, with satellites with odd serial numbers assigned to pixels in overlapping areas transmitted by satellites within an adjacent one-hop range, and satellites with even serial numbers assigned to pixels in non-overlapping areas transmitted by satellites within an adjacent one-hop range. This allows the same space situational awareness image to be divided into overlapping and non-overlapping areas for distributed compression calculation.

[0009] Preferably, the inter-satellite transmission is performed by establishing a link through capture, tracking and aiming by an on-board laser communication payload, and then 1550nm wavelength communication is performed between adjacent satellites in the same orbital plane.

[0010] The overlapping area detection mentioned above is relatively fixed because the distance between two adjacent low-orbit satellites in the same layer is relatively fixed, and the imaging parameters on each satellite (such as focal length, sensor size, aperture and shooting direction) are fixed. Therefore, the overlapping area width of the space situational awareness images taken by adjacent satellites is relatively fixed, and the overlapping area length is consistent with the length of the captured photos. Therefore, it is only necessary to perform overlapping area detection after the space situational awareness image is captured at the first moment. The obtained overlapping width is applicable to image detection at subsequent moments. Specifically, it includes:

[0011] Step 1: Each satellite uses the SIFT operator to extract feature points and descriptors from the captured image, and exchanges the extracted feature points and descriptor results and the corresponding image shooting timestamps with adjacent satellites. Adjacent satellites use the BFMatcher operator to match the feature points in two images taken at the same time.

[0012] Step 2: Adjacent satellites use the RANSAC algorithm to calculate the homography matrix by matching feature points, which is used to transform the first image into the coordinate system of the second image to identify the overlapping area.

[0013] Step 3: Each satellite calculates the area of ​​the overlapping region using the area equivalence method, and then divides the area by the image length to determine the overlapping width, thereby obtaining the boundary coordinates of the overlapping region.

[0014] Step 4: The overlapping width of the two adjacent captured images is finally determined as the larger value of the two values, and then the larger width value is used to update the boundary coordinates of the overlapping area in the two images to finally determine the range of the overlapping area.

[0015] The group sparsity means that for a tensor of order 3 Its group sparsity ||X|| 1,1,2 For X ij The number of non-zero entries of , and relaxes to a convex version where:

[0016]

[0017] The aggregate sparse coding specifically includes:

[0018] Step a: Initialize dictionary tensor D mt and auxiliary tensor A.

[0019] Step b: Update the auxiliary tensor, specifically: in: D' mt is the dictionary tensor D mt The transpose of ||D' mt *D mt || is the binary norm result after convolution of two tensors.

[0020] Step c, repeat step b until the number of iterations i is reached, by Perform Fourier transform to obtain dictionary tensor D mt ,in: is the frequency domain representation obtained by Fourier transform of the auxiliary tensor A in the third dimension, For the conjugate transform of this representation, diag() produces a diagonal matrix whose diagonal elements are all λ.

[0021] Step d: Dictionary tensor D obtained from the overlapping areas captured by two adjacent satellites it and D jt Perform dictionary aggregation to obtain the aggregated dictionary

[0022] Step e: The aggregated dictionary tensor obtained from step d And the dictionary tensor D obtained in step c mt, with the goal of minimizing the loss between the reconstructed image obtained by performing tensor convolution calculation on the dictionary tensor and the coefficient tensor and the original image, the dictionary tensor D mt As the auxiliary tensor C mt , update using the method of step bc to obtain the dictionary tensor and coefficient tensor of the overlapping or non-overlapping area, specifically: The constraint is that the square root of the sum of the squares of all elements in the dictionary vector matrix of each channel does not exceed 1, which is used to limit the complexity of the dictionary solution, that is: Where: m is the satellite serial number, t is the shooting time, n3 is the number of channels of each space situational awareness image, is the tensor of the image captured by the mth satellite at the tth time on the jth channel, D mt is the dictionary tensor learned by sparse coding for the image, is the coefficient tensor on the corresponding channel, β is the balance coefficient, which is generally set to 0.1. 1,1,2 is group sparsity.

[0023] The overlap-aware adaptive binary arithmetic coding algorithm specifically includes:

[0024] Step i: transform the coefficient tensor C mt Each floating point value in is quantized to an integer value The coefficient value c i Round to the nearest integer a i ∈[0,9], and the quantization interval is Δ.

[0025] Step ii: rearrange the quantized coefficient tensor into an importance map p that records the position of the non-zero coefficients in the tensor t and the corresponding level map used to record its value

[0026] Step iii. For level mapping, first use fixed-length binarization to encode it into a sequence of 0 and 1. For non-overlapping area pictures, directly use context-aware binary arithmetic coding (CABAC). For two overlapping area pictures at the same moment, they are represented as the current view CurrView(x,y) and the reference view RefView(x',y'), respectively. Based on the pixel values ​​and context features in the two views, the context index ctxIdx=f(CurrView(x,y),RefView(x',y'),D(x,y,x',y')) is obtained, where: D(x,y,x',y') is the absolute difference between the pixels at the corresponding positions of the two pictures, and f(·) is the quantization function used to map continuous values ​​to a discrete context index space.

[0027] Step iv: Update the binary coded probability model P(b=0|ctx)=εP(b=0|ctx) according to the context index CurrView )+(1-ε)P(b=0|ctx RefView ), where: P(b=1|ctx)=1-P(b=1|ctx), P(b=0|ctx CurrView ) is the probability based on the current view context, P(b=0|ctx RefView ) is the probability of the reference view context after the transformation. ε is a weight factor that can be adjusted according to the size response of D(x,y,x',y'). The smaller D is, the larger the ε value is.

[0028] Step v: Perform arithmetic coding on the binary sequence of the level map according to the updated probability model.

[0029] The image reconstruction means that the ground station retrieves the corresponding background pixels according to the satellite sequence number m and the shooting time t And get the coefficient tensor C for decoding mt After that, the image is reconstructed using tensor convolution calculation Where: t = t mod T.

[0030] Technical Effects

[0031] The present invention, based on an aggregated sparse coding algorithm with overlapping region detection and an overlap-aware adaptive binary arithmetic coding algorithm, enables direct onboard computation of low-orbit satellite constellations, achieving a 93.78% compression rate for space situational awareness images. Furthermore, under the conditions of a 300Mbps satellite-to-ground transmission downlink bandwidth, a 10-minute satellite-to-ground communication connection, and 20 satellite-to-ground communication connections per day, this method can successfully transmit space situational awareness images captured at a 30Hz sampling rate over 24 hours to a ground station within one day at a data transmission rate of 93.04%. This performance significantly outperforms existing benchmark methods including ZIP, JPEG, multidimensional tensor sparse coding (MDTSC), and deep learning-based GAACNN. Furthermore, the image reconstructed by this method achieves an SSIM value of 0.73 and a PSNR value of 27.56dB, both of which are superior to multidimensional tensor sparse coding (MDTSC). Compared with centralized image sparse coding, the present invention can reduce CPU and RAM usage and processing time by approximately 20%, making it feasible to deploy this method in resource-constrained satellite networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0033] Figure 2 This is the flow chart of the aggregation sparse coding algorithm;

[0034] FIG3 is a schematic diagram of the embodiment architecture;

[0035] In the picture: Figure 3a To simulate the communication between ground station and satellite; Figure 3b A schematic diagram of the satellite computer and computing payload simulating a single satellite.

[0036] FIG4 is an effect analysis diagram of the image compression algorithm;

[0037] In the picture: Figure 4a This is a comparison chart of image compression rates. Figure 4b For the data transmission rate diagram, Figure 4c Compute delay graph for single image compression;

[0038] FIG5 is a visual diagram of a sparsely coded reconstructed image;

[0039] Figure 6 is a diagram showing the computing resource utilization analysis. DETAILED DESCRIPTION

[0040] like Figure 1 As shown, a space situational awareness image compression system based on aggregated sparse coding involved in this embodiment includes: an overlapping area segmentation and allocation module, a background segmentation module, a sparse coding module and an image reconstruction module, wherein: the background segmentation module performs foreground and background segmentation based on the captured space situational awareness image and outputs the background area to the ground station; the overlapping area segmentation and allocation module calculates the pixel area belonging to the same field of view based on the pixel relationship of the foreground area in the image captured by two adjacent satellites at the same time after segmentation, and allocates the corresponding area to the corresponding satellite for image compression; the sparse coding module performs aggregated sparse coding and overlap-aware adaptive binary arithmetic coefficient coding based on the received image area to further reduce the dictionary and coefficient size of the sparse coding output; the image reconstruction module performs the final image reconstruction in conjunction with the background part based on the encoded dictionary and coefficients.

[0041] The allocation means that the overlapping pixel areas under the same field of view are allocated to the odd-numbered satellites within the adjacent hop range for subsequent image compression, and the remaining non-overlapping pixel areas are allocated to the even-numbered satellites within the adjacent hop range for subsequent image compression. The corresponding areas are not additionally allocated according to whether the serial number of the local satellite is odd or even, and directly participate in subsequent calculations on the local satellite.

[0042] The sparse coding module includes: an aggregated sparse coding unit and an overlap-aware adaptive binary coefficient arithmetic coding unit, wherein: the dictionary aggregation unit aggregates dictionary tensors in overlapping areas to represent common basic elements in the image, further reducing the size of the dictionary obtained by sparse coding; the overlap-aware adaptive binary coefficient arithmetic coding unit utilizes the sparsity of the coefficient matrix obtained by sparse coding, applies geometric transformation on the overlapping area to predict the probability model, encodes the coefficient tensor into a more compact string, and further reduces the size of the coefficient obtained by sparse coding.

[0043] The background segmentation module includes a background segmentation unit and a background uploading unit, wherein the background segmentation unit uses the SCS-LBP operator to segment the background and foreground. The background uploading unit outputs the obtained background area to the ground station for image reconstruction.

[0044] The image reconstruction module includes: a background query unit and a reconstruction calculation unit, wherein: the background query unit retrieves the corresponding background pixels according to the satellite sequence number and the shooting time and obtains the coefficient tensor for decoding; the reconstruction calculation unit uses the background image, the dictionary tensor and the decoded coefficient tensor to perform tensor convolution calculation to reconstruct the image.

[0045] like Figure 2 As shown, this embodiment involves a spatial situational awareness image compression method based on aggregated sparse coding based on the above-mentioned system. The dictionary tensor and auxiliary tensor are initialized according to the image to be encoded, and the auxiliary tensor is iteratively updated according to the designed algorithm. The number of iterations will affect the computing resource consumption and computing delay. In this embodiment, 3 times is selected. After the auxiliary tensor is updated, the frequency domain representation of the dictionary tensor is calculated at the same time. The corresponding time domain representation dictionary tensor is obtained by performing Fourier transform, and the dictionary tensor is aggregated for the overlapping area. The aggregated dictionary will be used as input to enter the auxiliary tensor iterative update step. The updated auxiliary tensor is the coefficient tensor finally solved.

[0046] After specific actual experiments, the hardware simulation platform based on the low-orbit satellite shown in Figure 3 uses a Raspberry Pi as the satellite's on-orbit computer, which is used to control the satellite and manage information exchange respectively. However, the embodiment can be applied to other embedded development platforms, such as Arduino. Each Raspberry Pi is connected to a Jetson Orin OX, which is simulated as a computing load device. The Jetson device is equipped with an 8-core NVIDIA A78 CPU and 16GB LPDDR5 memory, and can provide a computing power of 100 INT8 TOPS. However, the embodiment can be applied to other types of lightweight embedded computing devices, such as Jetson Orin Nano. In addition, the ground station is simulated by a Linux server running the Ubuntu 16.04 LTS system. The server is equipped with a 12-core 3.2GHz Intel Core i7-8700 CPU and a GeForce GTX 1060 6GB GPU. However, the embodiment can be applied to other high-performance computing devices, such as HP DL20.

[0047] The space situational awareness image used in this embodiment is pre-divided into overlapping and non-overlapping areas and stored on two Raspberry Pis, simulating the input data received by odd-numbered and even-numbered satellites respectively. After receiving the image, the Jetson computing device will run the sparse coding module to compress the image. The compressed result is sent to the server via the Raspberry Pi's WiFi module. The maximum transmission bandwidth of the WiFi module is 300Mbps, which is equivalent to the satellite downlink bandwidth. The space situational awareness image used in this embodiment is obtained by taking pictures with two astronomical telescopes. The shooting equipment has a resolution of 1080×1920, an optical aperture of 50mm and a focal length of 250mm, and can take space images at a sampling rate of 30Hz.

[0048] like Figure 4a As shown in FIG, the present invention is compared with a variety of existing image compression algorithms. The compression ratio of the dictionary aggregation sparse coding algorithm involved in the present invention is about 93.78%;

[0049] like Figure 4b As shown in Figure 2, the data transmission ratio of the satellite downlink to the ground station is expressed by the transmission ratio of the original captured image data volume. It can be seen that the use of the aggregated sparse coding algorithm for image compression can transmit the largest amount of original image data;

[0050] like Figure 4c As shown in the figure, the delay of different compression algorithms running on orbit is shown for the compression delay of a single image. It can be seen that the delay of the dictionary aggregation sparse coding algorithm involved in the present invention is about 13.68s, which is much smaller than the interval between two adjacent satellite downlinks. At the same time, the delay is shorter than that of MDTSC, which verifies the feasibility of its on-orbit image compression operation.

[0051] like Figure 5a As shown in Figure 2, the visual comparison of the MDTSC reconstructed image is shown. The left side shows the reconstruction result of the entire image, and the right side shows the enlarged detail of the image with a 100*100 pixel block in the upper left corner. Figure 5b As shown in the figure, the visualization of the image reconstructed by the dictionary aggregation sparse coding algorithm involved in the present invention. Similarly, the left side is the reconstruction result of the entire image, and the right side is an enlarged detail image of the image with a 100*100 pixel block selected from the upper left corner. It can be seen from observation that the effect of the dictionary aggregation sparse coding algorithm involved in the present invention is that it uses a dictionary aggregated and learned from multiple perspectives, not a single perspective, and the final reconstructed image provides more details than MDTSC. Accordingly, the PSNR value of the image reconstructed by the dictionary aggregation sparse coding algorithm involved in the present invention is 27.56dB, and the SSIM value is 0.73, both higher than the PSNR value and SSIM value of the image reconstructed by MDTSC, which are 25.03dB and 0.65 respectively.

[0052] As shown in Figure 6, the computing resource usage of the space situational awareness image compression system during operation is: Figure 6a The time-dependent usage of CPU and RAM computing resources on a single computing device when using centralized image compression calculations is simulated. Figure 6b The CPU and RAM usage over time of distributed image compression calculations is simulated when overlapping area image compression processing is performed on a single odd-numbered satellite. Figure 6c The authors simulated the time-dependent CPU and RAM usage of distributed image compression for overlapping regions on a single even-numbered satellite. The results show that distributed computing significantly reduces CPU and RAM utilization, as well as processing time, compared to centralized encoding on a single satellite, especially when processing non-overlapping regions. Furthermore, the proposed sparse coding method utilizes approximately 40% of the CPU and 20%-30% of the RAM, demonstrating its feasibility on satellites with limited computing power, storage, and energy. Its modest resource consumption enables it to run in parallel with other satellite missions, such as attitude and orbit control and communications.

[0053] The above-mentioned specific implementation can be partially adjusted in different ways by those skilled in the art without departing from the principles and purpose of the present invention. The scope of protection of the present invention shall be based on the claims and shall not be limited by the above-mentioned specific implementation. All implementation schemes within its scope shall be subject to the constraints of the present invention.

Claims

1. A spatial situational awareness image compression method based on aggregated sparse coding, characterized in that: After background segmentation of the collected space situational awareness images, overlapping areas of the foreground are detected and assigned to adjacent satellites. Each satellite sequentially obtains the dictionary tensor and coefficient tensor of the assigned overlapping or non-overlapping areas through aggregate sparse coding based on the images from adjacent satellites. The coefficient tensor is then further compressed into a transfer tensor and position tensor that express the pixel relationship of the overlapping area through the overlap-aware adaptive binary arithmetic coding algorithm, and then output to the ground station for image reconstruction. The aggregate sparse coding specifically includes: Step a: Initialize the dictionary tensor and auxiliary tensor A; Step b: Update the auxiliary tensor, specifically: ,in: , Dictionary Tensor The transpose of The two-norm result after convolution of two tensors; Step c, repeat step b until the number of iterations i is reached, by Perform Fourier transform to obtain dictionary tensor ,in: , The frequency domain representation of the auxiliary tensor A obtained by Fourier transform in the third dimension, The conjugate transform of this representation, diag(), produces a diagonal whose elements are all The diagonal matrix of ; Step d: Dictionary tensor obtained from the overlapping areas captured by two adjacent satellites and Perform dictionary aggregation to obtain the aggregated dictionary ; Step e: The aggregated dictionary tensor obtained from step d And the dictionary tensor obtained in step c , with the goal of minimizing the loss between the reconstructed image obtained by performing tensor convolution calculation on the dictionary tensor and the original image, by As an auxiliary tensor , update using the method of step bc to obtain the dictionary tensor and coefficient tensor of the overlapping or non-overlapping area, specifically: , the constraint is that the square root of the sum of the squares of all elements in the dictionary vector matrix of each channel does not exceed 1, which is used to limit the complexity of the dictionary solution, that is: , where: m is the satellite number, t is the shooting time, is the number of channels of each space situational awareness image, is the tensor of the image captured by the m-th satellite at the t-th time on the j-th channel, is the dictionary tensor learned by sparse coding for the image, is the coefficient tensor on the corresponding channel, is the balance coefficient, generally taken as 0.1, is group sparsity; The group sparsity means that for a tensor of order 3 , its group sparsity The number of non-zero entries of , and relaxes to a convex version where: : .

2. The spatial situational awareness image compression method based on aggregated sparse coding according to claim 1 is characterized in that: The background segmentation refers to: combining the advantages of sparse coding and local binary pattern, using SCS-LBP operator to perform background and foreground segmentation; and outputting the obtained background area to the ground station for image reconstruction.

3. The spatial situational awareness image compression method based on aggregated sparse coding according to claim 1 is characterized in that: The allocation means that N low-orbit satellites in the same layer are assigned serial numbers in the range of [0, N] in advance, with satellites with odd serial numbers assigned to pixels in overlapping areas transmitted by satellites within an adjacent one-hop range, and satellites with even serial numbers assigned to pixels in non-overlapping areas transmitted by satellites within an adjacent one-hop range. This allows the same space situational awareness image to be divided into overlapping and non-overlapping areas for distributed compression calculation.

4. The spatial situational awareness image compression method based on aggregated sparse coding according to claim 1 is characterized in that: The overlapping area detection described above is relatively fixed because the distance between two adjacent low-orbit satellites in the same layer and the imaging parameters on each satellite are fixed. As a result, the overlapping area width of the space situational awareness images taken by adjacent satellites is relatively fixed, and the overlapping area length is consistent with the length of the taken photos. Therefore, it is only necessary to perform overlapping area detection after capturing the space situational awareness image at the first moment. The obtained overlapping width is applicable to image detection at subsequent moments.

5. The spatial situational awareness image compression method based on aggregated sparse coding according to claim 1 or 4, characterized in that: The overlapping area detection specifically includes: Step 1: Each satellite uses the SIFT operator to extract feature points and descriptors from the captured image, and exchanges the extracted feature points and descriptors and the corresponding image capture timestamps with the adjacent satellite. The adjacent satellite uses the BFMatcher operator to match the feature points in the two images captured at the same time. Step 2: Adjacent satellites use the RANSAC algorithm to calculate the homography matrix by matching feature points, which is used to transform the first image into the coordinate system of the second image to identify the overlapping area; Step 3: Each satellite calculates the area of ​​the overlapping region using the area equivalence method, and then divides the area by the image length to determine the overlap width, thereby obtaining the boundary coordinates of the overlapping region; Step 4: The overlapping width of the two adjacent captured images is finally determined as the larger value of the two values, and then the larger width value is used to update the boundary coordinates of the overlapping area in the two images to finally determine the range of the overlapping area.

6. The spatial situational awareness image compression method based on aggregated sparse coding according to claim 1 is characterized in that: The overlap-aware adaptive binary arithmetic coding algorithm specifically includes: Step i: transform the coefficient tensor Each floating point value in is quantized to an integer value , that is, the coefficient value Round to the nearest integer , the quantization interval is ; Step ii: Rearrange the quantized coefficient tensor into an importance map that records the position of non-zero coefficients in the tensor and the corresponding level map used to record its value ; Step iii: For the level map, first use fixed-length binarization to encode it into a sequence of 0 and 1. For non-overlapping area pictures, directly use context-aware binary arithmetic coding (CABAC). For two overlapping area pictures at the same time, they are represented as the current view CurrView(x,y) and the reference view RefView(x',y'), and the context index is obtained based on the pixel values ​​and context features in the two views. ,in: is the absolute difference between the pixels at corresponding positions in the two images, and f(·) is a quantization function used to map continuous values ​​to a discrete context index space; Step iv: Update the binary coded probability model based on the context index ,in: , is the probability based on the current view context, is the probability based on the transformed reference view context, is a weight factor, according to The size of the response adjustment; Step v: Perform arithmetic coding on the binary sequence of the level map according to the updated probability model.

7. The spatial situational awareness image compression method based on aggregated sparse coding according to claim 1 is characterized in that: The image reconstruction means that the ground station retrieves the corresponding background pixels according to the satellite sequence number m and the shooting time t And get the coefficient tensor for decoding After that, the image is reconstructed using tensor convolution calculation , where: t=tmod T.

8. A space situational awareness image compression system implementing the method according to any one of claims 1 to 7, characterized in that: include: The overlapping area segmentation and allocation module, the background segmentation module, the sparse coding module and the image reconstruction module are as follows: the background segmentation module performs foreground and background segmentation based on the captured space situational awareness image and outputs the background area to the ground station; the overlapping area segmentation and allocation module calculates the pixel area belonging to the same field of view based on the pixel relationship of the foreground area in the images captured by two adjacent satellites at the same time after segmentation, and allocates the corresponding area to the corresponding satellite for image compression; The sparse coding module performs aggregated sparse coding and overlap-aware adaptive binary arithmetic coefficient coding based on the received image area to further reduce the dictionary and coefficient size of the sparse coding output; the image reconstruction module performs the final image reconstruction based on the encoded dictionary and coefficients combined with the background part; The allocation means that the overlapping pixel areas under the same field of view are allocated to the odd-numbered satellites within the adjacent hop range for subsequent image compression, and the remaining non-overlapping pixel areas are allocated to the even-numbered satellites within the adjacent hop range for subsequent image compression. The corresponding areas are not additionally allocated according to whether the serial number of the local satellite is odd or even, and directly participate in subsequent calculations on the local satellite.

9. The space situational awareness image compression system according to claim 8, characterized in that: The sparse coding module includes: an aggregation sparse coding unit and an overlap-aware adaptive binary coefficient arithmetic coding unit, wherein: the dictionary aggregation unit aggregates dictionary tensors in overlapping areas to represent common basic elements in the image, further reducing the size of the dictionary obtained by sparse coding; the overlap-aware adaptive binary coefficient arithmetic coding unit utilizes the sparsity of the coefficient matrix obtained by sparse coding, applies geometric transformation on the overlapping areas to predict the probability model, and encodes the coefficient tensor into a more compact string, further reducing the size of the coefficient obtained by sparse coding; The background segmentation module includes: a background segmentation unit and a background uploading unit, wherein: the background segmentation unit uses the SCS-LBP operator to perform background and foreground segmentation, and the background uploading unit outputs the obtained background area to the ground station for image reconstruction; The image reconstruction module includes: a background query unit and a reconstruction calculation unit, wherein: the background query unit retrieves the corresponding background pixels according to the satellite sequence number and the shooting time and obtains the coefficient tensor for decoding; the reconstruction calculation unit uses the background image, the dictionary tensor and the decoded coefficient tensor to perform tensor convolution calculation to reconstruct the image.

Images