Space target edge detection method and device, equipment and medium

Abstract

The invention relates to a space target edge detection method and device, equipment and a medium. The method comprises the steps of obtaining a space target image; constructing a space target edge detection model, inputting the space target image into the space target edge detection model for processing, and outputting an edge prediction map; carrying out adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map; processing the edge prediction map and the segmentation prediction map through morphology and operation to obtain a space target edge map; and performing closing operation on the small holes and fractures of the space target edge image to obtain a complete edge image. According to the method, the accuracy of space target edge detection is improved, the interference of background noise and a complex environment on edge detection is reduced, the continuity and integrity of an edge detection result are optimized, and a final edge image is clearer and more accurate.

Description

Technical Field

[0001] The present invention relates to the field of target detection technology, and in particular to a method, device, equipment and medium for detecting an edge of a space target. Background Art

[0002] Space targets refer to various flying objects in the outer space of the earth, such as communication and observation satellites, abandoned satellites and space debris. In recent years, with the rapid development of aerospace technology, more and more space targets have been sent into space. Many spacecraft in orbit are unable to continue to perform their assigned tasks due to fuel exhaustion, malfunctions and other reasons, which threaten space exploration activities at all times and cause serious damage to space assets. In order to ensure space order, various aerospace agencies have conducted a series of related studies, among which on-orbit service technologies such as parts replacement, fuel filling, and high-value parts recycling have become research hotspots. In order to obtain reliable guidance information, accurate identification and stable tracking of space targets are key issues that need to be solved urgently.

[0003] For space targets, the main challenges faced by edge detection are: the noise and complex background in the space target image will interfere with edge detection, leading to misjudgment of edge points, causing edges to break or deviate. Traditional edge detection algorithms are based on gradient operations to identify and locate the locations where mutations occur in images, such as Roberts operator, Sobel operator, Prewitt operator, Laplacian operator and Canny operator. These methods are simple in principle and have good real-time performance, but are not robust and are easily affected by factors such as noise. In practical applications, they are prone to cause more false alarm points and discontinuous edges. At the same time, the actual effect depends on the manual adjustment of parameters, and the edge detection effects presented at different thresholds are often very different. Edge detection methods based on convolutional neural networks, such as the Holostically-Nested Edge Detection (HED) algorithm, have high model complexity and are not accurate enough in processing detailed edges. Summary of the invention

[0004] Based on this, it is necessary to provide a space target edge detection method, device, equipment and medium with higher robustness and accuracy to address the above technical problems.

[0005] A space target edge detection method, the method comprising: Acquire space target images; Constructing a space target edge detection model, inputting the space target image into the space target edge detection model for processing, and outputting an edge prediction map; Performing adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map; Processing the edge prediction map and the segmentation prediction map through morphological operations to obtain a spatial target edge map; Small holes and breaks in the edge image of the space object are closed to obtain a complete edge image.

[0006] A space target edge detection device, the device comprising: A data acquisition module, used for acquiring space target images; An edge prediction map output module is used to construct a space target edge detection model, input the space target image into the space target edge detection model for processing, and output an edge prediction map; A segmentation prediction map output module is used to perform adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map; A spatial target edge map output module is used to process the edge prediction map and the segmentation prediction map through morphological operations to obtain a spatial target edge map; The complete edge image output module is used to close the small holes and breaks in the edge image of the space target to obtain a complete edge image.

[0007] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the space target edge detection method when executing the computer program.

[0008] A computer-readable storage medium stores a computer program, which implements the steps of the space target edge detection method when executed by a processor.

[0009] The above-mentioned space target edge detection method, device, equipment and medium first obtain a space target image; then build a space target edge detection model, input the space target image into the space target edge detection model for processing, and output an edge prediction map; at the same time, perform adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map; then process the edge prediction map and the segmentation prediction map through morphology and operation to obtain a space target edge map; finally, close the small holes and breaks in the space target edge map to obtain a complete edge image.

[0010] The present invention can more accurately extract the contour edge of the space target through the space target edge detection model, thereby improving the accuracy of edge detection; through adaptive dynamic threshold segmentation, it can effectively distinguish the background area and the space target area in the image, reduce the interference of background noise and complex environment on edge detection, enhance the accuracy of edge detection results, and reduce errors. Through morphological refinement processing and adaptive filling methods, small holes and breaks in the image are effectively processed. This post-processing technology optimizes the continuity and integrity of the edge detection results, making the final edge image clearer and more accurate, and providing a more reliable basis for subsequent image analysis and target recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0012] Figure 1 Schematic diagram of the process of edge detection of space objects in Example 1; Figure 2 Schematic diagram of the structure of the space target edge detection model in Example 1; Figure 3 is a structural block diagram of the space target edge detection device in Example 2; Figure 4 This is a diagram of the internal structure of the computer device in Example 3.

[0013] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] It can be understood that the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0016] The following will describe the implementation of the present invention in detail with reference to the accompanying drawings in the embodiment diagram of the present invention.

[0017] Example 1 This embodiment discloses a space target edge detection method. By constructing a space target edge detection model, the contour edge of the space target can be extracted more accurately, improving the accuracy of edge detection; through adaptive dynamic threshold segmentation, the background area and the space target area in the image can be effectively distinguished, reducing the interference of background noise and complex environment on edge detection, enhancing the accuracy of edge detection results, and reducing errors. Morphological refinement processing and adaptive filling methods are used to effectively process small holes and breaks in the image. This post-processing technology optimizes the continuity and integrity of the edge detection results, making the final edge image clearer and more accurate, providing a more reliable foundation for subsequent image analysis and target recognition.

[0018] like Figure 1 As shown, the space target edge detection method provided by this embodiment includes the following steps: Step 201, acquiring a space target image.

[0019] Step 202, constructing a space target edge detection model, inputting the space target image into the space target edge detection model for processing, and outputting an edge prediction map.

[0020] Step 203, performing adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map.

[0021] Step 204, the edge prediction map and the segmentation prediction map are processed by morphological operations to obtain a spatial object edge map.

[0022] Step 205 , closing the small holes and breaks in the edge image of the space object to obtain a complete edge image.

[0023] In the specific implementation process of step 201, the acquired space target image is the space target image to be detected. Since the imaging environment of the space target is complex and changeable, the acquired space target image to be detected includes not only the space target but also the noise interference in the space environment and the complexity of the background. The purpose of the present invention is to eliminate the interference factors in the space target image to be detected and extract the space target accurately and completely.

[0024] In the specific implementation process of step 202, a data set is first obtained, which includes a space target image for training. By marking the edge of the space target in the space target image, edge annotation data corresponding to the space target image is obtained. The space target image and the edge annotation data corresponding to the space target image are used as a set of training data; multiple sets of training data constitute a data set. Then the data set is divided into a training set, a validation set, and a test set. The division ratio is determined according to the requirements. In this embodiment, the division is performed according to the ratio of 3:1:1.

[0025] A space target edge detection model is constructed. The space target edge detection model includes several feature extraction modules of different scales. Feature extraction is performed on the space target image through each feature extraction module to obtain feature maps at different scales. Feature maps at different scales are concatenated in a cascade manner to obtain multi-scale information feature maps. Feature extraction and fusion are performed on the multi-scale information feature maps to obtain an edge prediction map.

[0026] See also Figure 2 , which is the space object edge detection model provided in this embodiment, includes 6 feature extraction modules. Among them, the first feature extraction module stage0 is a The convolution layer has 32 output channels; the second feature extraction module stage1 is a bottleneck module, the expansion factor is 1, and the output channel number is 16; the third feature extraction module stage2 is two bottleneck modules, the expansion factor is 6, and the output channel number is 24; the fourth feature extraction module stage3 is three bottleneck modules, the expansion factor is 6, and the output channel number is 32; the fifth feature extraction module stage4 is four bottleneck modules, the expansion factor is 6, and the output channel number is 64; the sixth feature extraction module stage5 is three bottleneck modules, the expansion factor is 6, and the output channel number is 96. In each bottleneck module, it contains Point-wise convolution expansion layer, The deep convolution layer and the projection convolution layer are divided into three parts.

[0027] When the spatial object edge detection model is processing data, the input of the next feature extraction module is the output of the previous feature extraction module. After the feature map output by each feature extraction module is convolved and deconvolved, it is spliced ​​in a cascade manner. The obtained multi-scale information feature map is then extracted and fused through additional convolution layers to obtain higher-level features. The higher-level features are binarized to generate edge prediction maps.

[0028] In this embodiment, based on the pre-constructed loss function, the space target edge detection model is trained through the training set to obtain a trained space target edge detection model. The space target image to be detected is input into the trained space target edge detection model for processing, and an edge prediction map is output.

[0029] The pre-built loss functions include the total side output loss function and the fusion layer loss function, which are expressed as: ; In the formula, Represents the fusion weight coefficient of a single side output layer; Represents a set of network parameters; Represents the side output layer parameters.

[0030] Total side output loss function The expression is: ; In the formula, Represents the weight of the loss function of a single side output layer; represents the loss function of a single side output layer.

[0031] in, ; In the formula, , , and Respectively represent the number of non-edge pixels and edge pixels in the label; Indicates the parameter for balancing positive and negative samples, with a value between 0 and 1; Indicates the true label j The value of each pixel; express Side output layer parameters for the layer.

[0032] Fusion layer loss function The expression is: ; In the formula, represents the fusion layer of the network, which is The result of weighted fusion of the side output layers, where express Side output of the layer; Indicates the total number of pixels; represents the true label.

[0033] It can be understood that the space target edge detection model structure constructed in this embodiment uses a lightweight network module as the backbone network, which reduces the number of model parameters and computing resource consumption, reduces model complexity, saves computing resources, and is particularly suitable for application in resource-constrained environments; at the same time, it avoids the problems of blurred prediction edges and inaccurate positioning that are easily caused by deep convolution, and can more accurately extract the contour edges of space targets. The pre-constructed loss function can predict the degree of overlap between the result and the true label, can better capture local edge information, solve the problem of training instability caused by the imbalance of positive and negative samples in edge detection tasks, and can effectively improve the accuracy of edge detection.

[0034] In the specific implementation process of step 203, the space target image is divided into multiple local areas, and the grayscale histogram is calculated for each local area; based on the grayscale histogram, the optimal threshold of each local area is calculated; the optimal threshold of each local area is weighted averaged and fused to obtain a global threshold; based on the global threshold, the space target image is segmented to obtain a segmentation result; the segmentation result is evaluated by a pixel accuracy index to obtain an evaluation result; the global threshold is adaptively and dynamically adjusted according to the evaluation result, and the space target image is re-segmented to obtain a final segmentation prediction map.

[0035] Specifically, the global threshold is adaptively and dynamically adjusted according to the evaluation results, including: (1) If the pixel accuracy is lower than the preset threshold, the global threshold is adjusted: if the background area is over-segmented, the global threshold can be appropriately increased; if the target area is over-segmented, the global threshold can be appropriately reduced.

[0036] (2) Determine the adjustment range of the global threshold based on the difference between the current pixel accuracy and the preset threshold. For example, when the pixel accuracy differs from the preset threshold by 0.1, adjust the global threshold by 5%; when the pixel accuracy differs from the preset threshold by 0.01, adjust the global threshold by 0.5%.

[0037] It can be understood that by introducing an adaptive threshold dynamic adjustment method in the edge detection task, the background area and the spatial target area in the image are effectively distinguished, the interference of background noise and complex environment on edge detection is reduced, the accuracy of edge detection results is enhanced, and errors are reduced.

[0038] In this embodiment, the optimal threshold of each local area can be calculated according to different lighting and noise conditions by using the OTSU threshold segmentation method, the local variance-based threshold segmentation method, or the adaptive threshold segmentation method. In this embodiment, the OTSU threshold segmentation method is preferably used.

[0039] In the specific implementation process of step 204, the segmentation prediction map and the edge prediction map are combined to obtain the space object edge map by using morphology and operation. In this step, by combining the advantages of the two methods, a more complete space object edge contour is obtained.

[0040] Specifically, the morphological operation function in the image processing software or library (such as OpenCV) is used for implementation, which will not be described in detail here.

[0041] In the specific implementation process of step 205, the edge map of the space object is improved, and small holes and breaks in the edge contour are closed to obtain a complete edge image.

[0042] Specifically, the space target edge map is firstly subjected to morphological refinement processing to obtain a refined edge image; then the breakpoints of the refined edge image are marked, and the edge closing processing is performed based on the marked breakpoint positions to obtain a complete edge image.

[0043] Among them, the spatial target edge map is subjected to morphological thinning processing to obtain a thinned edge image, that is, the size of the object in the image is reduced by iterative erosion operation, and then the original size of the object is restored by dilation operation. More specifically, the spatial target edge map is first converted into a binary edge image, and a structural element is determined. In this embodiment, the structural element is a small square, which is mainly used to determine the range of erosion and dilation operations, and the image is processed pixel by pixel. Then, an erosion operation is performed, that is, the minimum value of the value in the rectangular neighborhood of each position is taken as the output gray value of the position, and the binary edge image is eroded using the structural element to obtain an eroded image. Then, an expansion operation is performed, which is equivalent to the reverse operation of erosion. The size of the brighter objects in the image will become larger, and the size of the darker objects will decrease; the eroded image is expanded using the structural element to obtain an expanded image. Through iterative erosion and dilation operations, the edge width of the binary edge image is reduced to one pixel to obtain a thinned edge image.

[0044] In the spatial object edge map, the refinement operation can remove redundant pixels in the edge width and leave only the most core edge pixels, which helps to clearly distinguish edge and non-edge areas and provide more accurate edge information for subsequent processing.

[0045] After obtaining the refined edge image, the next step is to mark the breakpoints and perform edge closure processing based on the marked breakpoint positions to obtain a complete edge image. It can be understood that breakpoints refer to places where the edges are discontinuous, that is, there are gaps between edge pixels. The purpose of marking these breakpoints is to identify areas that need further processing. This is achieved by detecting the intervals between edge pixels. If the distance between two edge pixels exceeds a certain threshold, it can be considered that there is a breakpoint here, and these breakpoints will serve as the starting point for subsequent closure processing.

[0046] Specifically, the refined edge image is traversed to mark all edge pixels; for each edge pixel, the distance between it and the nearest edge pixel is calculated, which can be achieved by scanning the neighborhood of the edge pixel.

[0047] Set a threshold , threshold Determine based on the expected width of the edge and the resolution of the image; determine whether the distance between two edge pixels is greater than the threshold If yes, a breakpoint is marked between the two edge pixels; if no, it is considered that there is no breakpoint between the two edge pixels and no marking is required.

[0048] All breakpoint positions are recorded, and edge closing processing is performed based on the breakpoint positions to obtain a complete edge image.

[0049] Further specifically, according to the position of the breakpoint and the direction information of the edge, small holes and breaks in the edge contour are adaptively filled to obtain a complete edge image. The key to this step is to determine how to fill these gaps to ensure that the filled edge is visually consistent with the original edge. In this embodiment, an interpolation method based on edge direction is used to ensure that the filled edge is consistent with the original edge in direction, thereby achieving natural and accurate closure. For example, if the edge is horizontal at the breakpoint, the filling operation may add pixels horizontally above and below the breakpoint.

[0050] The steps are: First, the filling direction is determined. For each breakpoint, the filling direction is determined based on the direction information of the edges on both sides of the breakpoint. If the directions of the edges on both sides of the breakpoint are consistent, filling is performed along that direction; if the directions are inconsistent, the most likely filling direction is selected based on the continuity of the edges.

[0051] Then, adaptive filling is performed. According to the determined filling direction, edge pixels are adaptively added at the breakpoint until the hole or break is completely filled. The length and width of the filling can be determined according to the spacing and direction of the edges on both sides of the breakpoint.

[0052] Finally, after the filling process, some post-processing steps are required to further improve the edge image quality, including removing too small fragments, smoothing edges, and enhancing edge contrast. Among them, too small fragments may be caused by noise or excessive processing during the thinning process; smoothing the edge can reduce the discontinuity introduced by the thinning and filling operations; enhancing the edge contrast can make the edge more obvious and easier to identify. These operations are achieved through morphological operations (such as opening and closing operations) and Gaussian filtering (such as Gaussian filtering) techniques.

[0053] It can be understood that in this step, the small holes and breaks in the edge map of the space target are effectively processed through morphological refinement and adaptive filling methods. This post-processing technology optimizes the continuity and integrity of the edge detection results, making the final edge image clearer and more accurate, providing a more reliable basis for subsequent image analysis and target recognition.

[0054] Although this embodiment Figure 1 The steps in the process are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of the steps, and the steps can be executed in other orders. Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0055] Example 2 Based on the space target edge detection method in Example 1, this embodiment discloses a space target edge detection device, such as Figure 3 As shown, the space target edge detection device includes: a data acquisition module 401, an edge prediction map output module 402, a segmentation prediction map output module 403, a space target edge map output module 404 and a complete edge image output module 405, wherein: The data acquisition module 401 is used to acquire space target images.

[0056] The edge prediction map output module 402 is used to construct a space target edge detection model, input the space target image into the space target edge detection model, and output an edge prediction map.

[0057] The segmentation prediction map output module 403 is used to perform adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map.

[0058] The spatial object edge map output module 404 is used to process the edge prediction map and the segmentation prediction map through morphological operations to obtain the spatial object edge map.

[0059] The complete edge image output module 405 is used to close small holes and breaks in the edge image of the space object to obtain a complete edge image.

[0060] In this embodiment, the specific working process and working principle of the data acquisition module 401, the edge prediction map output module 402, the segmentation prediction map output module 403, the space target edge map output module 404 and the complete edge image output module 405 are the same as those in the method of Embodiment 1, so they are not described in detail in this embodiment. Each unit module can be implemented in whole or in part by software, hardware and a combination thereof, and each unit module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above unit modules.

[0061] Example 3 like Figure 4 The terminal device disclosed in this embodiment includes a transmitter, a receiver, a memory, and a processor. The transmitter is used to send instructions and data, the receiver is used to receive instructions and data, the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions stored in the memory to implement the method in the above-mentioned embodiment 1.

[0062] It should be noted that the above memory can be independent or integrated with the processor. When the memory is independently provided, the terminal device further includes a bus for connecting the memory and the processor.

[0063] Example 4 This embodiment discloses a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method in the above-mentioned embodiment 1 is implemented.

[0064] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0065] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0066] The above-mentioned embodiments only express several implementation modes of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A space target edge detection method, characterized in that: The method comprises: Acquire space target images; Constructing a space target edge detection model, inputting the space target image into the space target edge detection model for processing, and outputting an edge prediction map; Performing adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map; Processing the edge prediction map and the segmentation prediction map through morphological operations to obtain a spatial target edge map; Small holes and breaks in the edge image of the space object are closed to obtain a complete edge image.

2. The space target edge detection method according to claim 1, characterized in that: The spatial object edge detection model is trained based on a pre-built loss function, which includes a total side output loss function and a fusion layer loss function, and the expression is: ； Among them, the total side output loss function The expression is: ； Fusion layer loss function The expression is: ； In the formula, Represents a set of network parameters; Represents the side output layer parameters; Represents the fusion weight coefficient of a single side output layer; Represents the weight of the loss function of a single side output layer; represents the loss function of a single side output layer; represents the fusion layer of the network; Indicates the total number of pixels; represents the true label.

3. The space target edge detection method according to claim 1, characterized in that: The space target edge detection model includes a plurality of feature extraction modules of different scales, and each feature extraction module is used to extract features of the space target image to obtain feature maps of different scales; The feature maps at different scales are concatenated to obtain a multi-scale information feature map; Feature extraction and fusion are performed on the multi-scale information feature map to obtain an edge prediction map.

4. The space target edge detection method according to claim 3, characterized in that: The space target image is subjected to adaptive dynamic threshold segmentation to obtain a segmentation prediction map, including: Dividing the space target image into a plurality of local areas, and calculating a grayscale histogram for each local area; Based on the grayscale histogram, the optimal threshold of each local area is calculated; the optimal threshold of each local area is weighted averaged and fused to obtain a global threshold; Segmenting the space target image based on the global threshold to obtain a segmentation result; Evaluate the segmentation result by using a pixel accuracy index to obtain an evaluation result; The global threshold is adaptively and dynamically adjusted according to the evaluation result, and the spatial target image is re-segmented to obtain a final segmentation prediction map.

5. The space target edge detection method according to any one of claims 1 to 4, characterized in that: The small holes and breaks in the edge image of the space target are closed to obtain a complete edge image, including: The space target edge map is subjected to morphological refinement processing to obtain a refined edge image; breakpoints are marked on the refined edge image, and edge closing processing is performed based on the marked breakpoint positions to obtain a complete edge image.

6. The space target edge detection method according to claim 5, characterized in that: Performing morphological thinning processing on the space target edge map to obtain a thinned edge image includes: Converting the spatial target edge map into a binary edge image; Using a structural element to perform an erosion operation on the binary edge image to obtain an eroded image; Performing a dilation operation on the eroded image to obtain a dilated image; By iteratively performing erosion and dilation operations, the edge width of the binary edge image is reduced to one pixel, thereby obtaining a refined edge image.

7. The space target edge detection method according to claim 6, characterized in that: The thinned edge image is marked with breakpoints, and edge closing processing is performed based on the marked breakpoint positions to obtain a complete edge image, including: Traversing the refined edge image, marking all edge pixels; for each edge pixel, calculating the distance between it and the nearest edge pixel; Set a threshold and determine whether the distance between two edge pixels is greater than the threshold. If so, mark a breakpoint between the two edge pixels. All breakpoint positions are recorded, and edge closing processing is performed based on the breakpoint positions to obtain a complete edge image.

8. A space target edge detection device, characterized in that: The device comprises: A data acquisition module, used for acquiring space target images; An edge prediction map output module is used to construct a space target edge detection model, input the space target image into the space target edge detection model for processing, and output an edge prediction map; A segmentation prediction map output module is used to perform adaptive dynamic threshold segmentation on the space target image to obtain a segmentation prediction map; A spatial target edge map output module is used to process the edge prediction map and the segmentation prediction map through morphological operations to obtain a spatial target edge map; The complete edge image output module is used to close the small holes and breaks in the edge image of the space target to obtain a complete edge image.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the space object edge detection method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the space object edge detection method described in any one of claims 1 to 7 are implemented.

Images