Synthetic aperture radar image processing method and system

Abstract

The present invention relates to the field of radar image processing technology, and discloses a synthetic aperture radar image processing method and system. The method comprises: acquiring a synthetic aperture radar image, performing grayscale processing to obtain a radar grayscale image, and determining a grayscale value; counting the number of pixels corresponding to each grayscale value to obtain a pixel number set, sorting the pixels in descending order, and determining that the grayscale value corresponding to the number of pixels in a preset ranking is a target grayscale value; dividing the radar grayscale image according to the target grayscale value to obtain a plurality of divided regions and an undivided region; obtaining the center position of the divided region, determining the distance between the pixel points in the undivided region and the center position of the divided region, and classifying the pixel points in the undivided region into the divided region according to the distance, thereby processing the synthetic aperture radar image. The present invention can accurately divide different regions in a synthetic aperture radar image, thereby improving the accuracy and efficiency of image processing.

Description

Technical Field

[0001] The present invention relates to the technical field of radar image processing, and in particular to a synthetic aperture radar image processing method and system. Background Art

[0002] Synthetic Aperture Radar (SAR), an all-weather, all-day microwave remote sensing imaging technology, plays an irreplaceable role in military reconnaissance, terrain mapping, disaster monitoring, and other fields. However, SAR images are affected by factors such as coherent speckle noise, terrain undulation, and geometric imaging distortion, resulting in severe heterogeneity in scattering characteristics and uneven grayscale distribution. Traditional processing methods, such as constant false alarm rate (CFAR) detection or segmentation algorithms based on statistical models, often rely on fixed thresholds or prior knowledge and are difficult to adapt to the dynamic range of grayscale in complex terrain objects, easily leading to blurred target edges and loss of weak targets. Furthermore, existing clustering algorithms (such as K-means) suffer from high computational complexity and sensitivity to initial cluster centers when processing high-dimensional SAR data, which limits real-time processing capabilities.

[0003] The present invention addresses the pain points of the existing technology, such as weak adaptability, insufficient detail retention, and low processing efficiency, and proposes a synthetic aperture radar image processing method and system. Summary of the Invention

[0004] The purpose of the present invention is to provide a synthetic aperture radar image processing method and system to solve the above problems.

[0005] The present invention provides a synthetic aperture radar image processing method, comprising:

[0006] Acquire a synthetic aperture radar image, perform grayscale processing on the synthetic aperture radar image to obtain a radar grayscale image, and determine the grayscale values ​​of pixels in the radar grayscale image;

[0007] Counting the number of pixels corresponding to each grayscale value to obtain a pixel number set, sorting the pixel number set in descending order, determining the grayscale value corresponding to the number of pixels in a preset ranking, and setting it as the target grayscale value;

[0008] Dividing the radar grayscale image according to the target grayscale value to obtain a plurality of divided areas and undivided areas;

[0009] The center position of each divided area is obtained, and the distance between the pixel points in the undivided area and the center position of each divided area is determined. The pixels in the undivided area are classified into the divided areas according to the distance until all the pixels in the undivided area are classified, thereby realizing synthetic aperture radar image processing.

[0010] Preferably, sorting the pixel point number set in descending order, determining the grayscale value corresponding to the number of pixel points in a preset ranking, and setting it as the target grayscale value includes:

[0011] After sorting the pixel point set in descending order, determining a preset ranking according to the pixel point number;

[0012] The number of grayscale values ​​to be screened is determined based on the preset ranking, and the grayscale value corresponding to the number of pixels is determined according to the set of pixel numbers and grayscale values ​​sorted in descending order, and is set as the target grayscale value.

[0013] Preferably, after sorting the pixel point quantity set in descending order, determining a preset ranking according to the pixel point quantity includes:

[0014] Preset pixel number threshold;

[0015] Comparing each pixel number after descending sorting with the pixel number threshold; if the pixel number threshold is less than the pixel number, comparing the pixel number threshold with the next pixel number until the pixel number threshold is greater than or equal to the pixel number;

[0016] When the pixel number threshold is determined to be greater than or equal to the pixel number, the corresponding ranking is the preset ranking.

[0017] Preferably, the radar grayscale image is divided according to the target grayscale value to obtain a plurality of divided areas and undivided areas, including:

[0018] Determining a plurality of target grayscale value ranges according to the target grayscale value;

[0019] Divide the area with the same target grayscale value range into several initial divided areas;

[0020] Determine whether each initial divided area with the same target gray value range is connected. If so, set the corresponding initial divided area as the divided area;

[0021] If they are not connected, the disconnected initial partitioned areas are set as partitioned areas respectively;

[0022] The area whose grayscale value does not belong to the target grayscale value range is determined as an undivided area.

[0023] Preferably, several target grayscale value ranges are determined according to the target grayscale value, including:

[0024] Set the target grayscale change limit;

[0025] The target grayscale value range is determined according to the target grayscale value and the target grayscale change limit, wherein the left boundary of the target grayscale value range is: target grayscale value - target grayscale change limit, and the right boundary is: target grayscale value + target grayscale change limit.

[0026] Preferably, obtaining the center position of each divided area includes:

[0027] Get the pixel coordinates and grayscale values ​​of each divided area;

[0028] Determine the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01 of each divided area according to the pixel coordinates and grayscale values;

[0029] The center position of each divided area is determined according to the zero-order moment M00, the horizontal first-order moment M10 and the vertical first-order moment M01.

[0030] Preferably, determining the center position of each divided area according to the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01 includes:

[0031] The zero-order moment M00 is calculated as follows:

[0032] ;

[0033] The calculation method of the horizontal first-order moment M10 is:

[0034] ;

[0035] The calculation method of the vertical first-order moment M01 is:

[0036] ;

[0037] in, row i, represents the jth column, g ij Represents the grayscale value of the pixel in the i-th row and j-th column;

[0038] The calculation method of the center position of the divided area is:

[0039] ;

[0040] Among them, x z Indicates the row where the center is located, y z Indicates the column where the center position is located.

[0041] Preferably, determining the distance between a pixel point in the undivided area and the center position of each divided area, and classifying the pixel point in the undivided area into a divided area according to the distance includes:

[0042] Determine the distance between a pixel point in the undivided area and the center position of each adjacent divided area, compare the distances, and determine the minimum value therebetween;

[0043] Determine the divided area corresponding to the minimum value, and classify the pixels in the undivided area into the divided area corresponding to the minimum value;

[0044] The distance is determined according to the following formula:

[0045] ;

[0046] Among them, D wij represents the distance between the pixel point in row i and column j in the undivided area and the center of the divided area, (x wi ,y wj ) represents the coordinates of the pixel point in the i-th row and j-th column in the undivided area, (x z ,y z ) represents the coordinates of the center position of the divided area.

[0047] Preferably, classifying all pixels in the undivided area to achieve synthetic aperture radar image processing includes:

[0048] Classifying all the pixel points in the undivided area to determine the division trajectory of the divided area;

[0049] The synthetic aperture radar image is denoised and enhanced according to the division trajectory to achieve synthetic aperture radar image processing.

[0050] The present invention also discloses a synthetic aperture radar image processing system for applying the synthetic aperture radar image processing method, comprising:

[0051] An image acquisition module is configured to acquire a synthetic aperture radar image;

[0052] a grayscale processing module configured to perform grayscale processing on the synthetic aperture radar image to obtain a radar grayscale image, and determine the grayscale values ​​of pixels in the radar grayscale image;

[0053] a grayscale determination module configured to count the number of pixels corresponding to each grayscale value to obtain a pixel number set, sort the pixel number set in descending order, determine the grayscale value corresponding to the number of pixels in a preset ranking, and set the grayscale value as the target grayscale value;

[0054] a region division module configured to divide the radar grayscale image according to the target grayscale value to obtain a plurality of divided regions and undivided regions;

[0055] The position classification module is configured to obtain the center position of each divided area, determine the distance between the pixel points in the undivided area and the center position of each divided area, and classify the pixel points in the undivided area into the divided areas according to the distance until all the pixel points in the undivided area are classified, so as to realize the processing of the synthetic aperture radar image.

[0056] Compared with the existing technology, the beneficial effect of the present invention is that the present invention dynamically determines the target grayscale threshold by statistically sorting the set of pixel points in descending order, breaking through the limitations of traditional empirical thresholds or fixed segmentation modes, and improving the contrast of different texture areas.

[0057] Compared to single global threshold segmentation, this method employs a hierarchical segmentation strategy guided by target grayscale values ​​to decompose images into clusters of regions with consistent grayscale values. It determines attribution by calculating the spatial distance between unclassified pixels and the center of each region. Combined with an iterative update mechanism, this method suppresses speckle noise while preserving target contour details. Its dual-layer optimization architecture of grayscale statistical preprocessing and region center pre-extraction reduces single-frame processing time compared to deep learning-based segmentation methods and eliminates the need for extensive labeled sample training. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0059] Figure 1 It is a flow chart of a synthetic aperture radar image processing method of the present invention;

[0060] Figure 2 It is a functional block diagram of a synthetic aperture radar image processing system of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the 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 the embodiments. 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.

[0062] like Figure 1 As shown, the present invention provides a synthetic aperture radar image processing method, comprising:

[0063] A synthetic aperture radar image is acquired, grayscale processing is performed on the synthetic aperture radar image to obtain a radar grayscale image, and grayscale values ​​of pixels in the radar grayscale image are determined.

[0064] The number of pixels corresponding to each grayscale value is counted to obtain a pixel number set, and the pixel number set is sorted in descending order to determine the grayscale value corresponding to the number of pixels in a preset ranking and set as the target grayscale value.

[0065] The radar grayscale image is divided according to the target grayscale value to obtain a plurality of divided areas and undivided areas.

[0066] The center position of each divided area is obtained, and the distance between the pixel points in the undivided area and the center position of each divided area is determined. The pixels in the undivided area are classified into the divided areas according to the distance until all the pixels in the undivided area are classified, thereby realizing synthetic aperture radar image processing.

[0067] The present invention can more accurately delineate different regions within synthetic aperture radar images, improving the accuracy and efficiency of image processing. First, by grayscaling the radar image, image information can be simplified, facilitating subsequent processing. Second, by counting the number of pixels and determining the target grayscale value, image regions can be rationally divided, providing a basis for subsequent region classification. Finally, by calculating the distance between pixels in undivided regions and the center of divided regions, pixels are classified into the closest divided region, achieving precise image processing. This method not only improves image processing accuracy but also provides reliable data support for subsequent applications such as image analysis and target recognition.

[0068] In some embodiments of the present application, the set of pixel point numbers is sorted in descending order, and the grayscale value corresponding to the number of pixel points in a preset ranking is determined and set as the target grayscale value, including: after sorting the set of pixel point numbers in descending order, determining the preset ranking according to the number of pixel points; determining the number of filtered grayscale values ​​based on the preset ranking, determining the grayscale value corresponding to the corresponding number of pixel points according to the set of pixel point numbers in descending order and the number of grayscale values, and setting it as the target grayscale value.

[0069] It can be understood that the method provided by this embodiment can set the target grayscale value more flexibly, further improving the flexibility and accuracy of image processing. Specifically, by sorting the pixel number set in descending order, the distribution of pixels corresponding to each grayscale value can be clearly understood, and then the preset ranking can be determined according to actual needs to screen out the appropriate number of grayscale values. On this basis, according to the descending pixel number set and the number of grayscale values, the grayscale value corresponding to the corresponding number of pixels is determined as the target grayscale value, which can ensure that the setting of the target grayscale value is more reasonable, thereby better guiding the subsequent image division and pixel classification. This method not only improves the flexibility of image processing, but also can make targeted adjustments according to actual needs, so that the image processing results are more in line with actual needs.

[0070] In some embodiments of the present application, after the set of pixel point quantities is sorted in descending order, a preset ranking is determined based on the pixel point quantity, including: a preset pixel point quantity threshold; comparing each pixel point quantity after descending sorting with the pixel point quantity threshold, if the pixel point quantity threshold is less than the pixel point quantity, comparing the pixel point quantity threshold with the next pixel point quantity until the pixel point quantity threshold is greater than or equal to the pixel point quantity; determining that the ranking corresponding to when the pixel point quantity threshold is greater than or equal to the pixel point quantity is the preset ranking.

[0071] It is understandable that by presetting the pixel number threshold, it is possible to accurately screen the number of pixels, thereby more accurately determining the preset ranking. This method avoids the subjectivity of human settings, making the determination of the preset ranking more objective and scientific. At the same time, the pixel number threshold is compared one by one with the number of pixels in descending order until a ranking that meets the conditions is found, ensuring the accuracy of the preset ranking. This method of precise screening and determining the preset ranking further improves the flexibility and accuracy of the image processing method, making the image processing results more in line with actual needs and providing strong support for subsequent image segmentation and pixel classification.

[0072] In some embodiments of the present application, the radar grayscale image is divided according to the target grayscale value to obtain a number of divided areas and undivided areas, including: determining a number of target grayscale value ranges according to the target grayscale value; dividing areas with grayscale values ​​in the same target grayscale value range into a number of initial divided areas; determining whether each initial divided area with the same target grayscale value range is connected, and if so, setting the corresponding initial divided area as a divided area; if not, setting the unconnected initial divided areas as divided areas respectively; and determining areas with grayscale values ​​that do not fall within the target grayscale value range as undivided areas.

[0073] It can be understood that meticulously segmenting radar grayscale images by target grayscale values ​​not only improves image processing accuracy but also effectively distinguishes regions with different grayscale features. This method fully considers the complexity of radar grayscale images and, by setting a target grayscale value range, accurately captures key information in the image. At the same time, for initially segmented regions with the same grayscale value, the final segmentation region is determined by judging their connectivity. This step ensures the rationality and accuracy of the segmentation results. The setting of undivided regions further highlights the importance of segmentation regions, providing clear boundaries for subsequent image analysis and processing.

[0074] In some embodiments of the present application, several target grayscale value ranges are determined according to the target grayscale value, including: setting a target grayscale change limit; determining a target grayscale value range according to the target grayscale value and the target grayscale change limit, the left boundary of the target grayscale value range is: target grayscale value - target grayscale change limit, and the right boundary is: target grayscale value + target grayscale change limit, that is, the target grayscale value range is determined as [target grayscale value - target grayscale change limit, target grayscale value + target grayscale change limit].

[0075] As can be appreciated, by setting the target grayscale variation limit, the target grayscale value range can be flexibly adjusted to accommodate radar grayscale images of varying complexity. This approach not only improves image processing flexibility but also enhances its adaptability to diverse images. By setting the target grayscale value range to the interval obtained by adding or subtracting the target grayscale variation limit, centered around the target grayscale value, pixels within the target grayscale value range are ensured to have similar grayscale characteristics, which is crucial for subsequent image analysis and processing.

[0076] In some embodiments of the present application, obtaining the center position of each divided area includes: obtaining the pixel coordinates and grayscale values ​​of each divided area; determining the zero-order moment M00, horizontal first-order moment M10 and vertical first-order moment M01 of each divided area based on the pixel coordinates and grayscale values; and determining the center position of each divided area based on the zero-order moment M00, horizontal first-order moment M10 and vertical first-order moment M01.

[0077] It can be understood that by calculating the zero-order moment, horizontal first-order moment, and vertical first-order moment of each divided region, the center position of the region can be accurately determined. This step is crucial for subsequent tasks such as image registration, target detection, and tracking. By obtaining the pixel coordinates and grayscale values ​​of each divided region, we can not only understand the grayscale distribution characteristics of the region, but also further analyze its spatial location information. Using the zero-order moment M00, we can obtain the total number of pixels in the region, while the horizontal first-order moment M10 and the vertical first-order moment M01 reflect the grayscale center position of the region in the horizontal and vertical directions, respectively. By combining these three moments, we can accurately calculate the center position of each divided region, thereby improving the accuracy and reliability of image processing.

[0078] In some embodiments of the present application, the center position of each divided area is determined according to the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01, including: the zero-order moment M00 is calculated as follows:

[0079] ;

[0080] The calculation method of the horizontal first-order moment M10 is:

[0081] ;

[0082] The calculation method of the vertical first-order moment M01 is:

[0083] ;

[0084] in, row i, represents the jth column, g ij Represents the grayscale value of the pixel in the i-th row and j-th column;

[0085] The calculation method of the center position of the divided area is:

[0086] ;

[0087] Among them, x z Indicates the row where the center is located, y z Indicates the column where the center position is located.

[0088] It can be understood that the calculation of the zero-order moment M00, the horizontal first-order moment M10 and the vertical first-order moment M01 by specific mathematical formulas ensures the accuracy and repeatability of the calculation process. The calculation of the zero-order moment M00 takes into account the sum of the grayscale values ​​of all pixels in the area, reflecting the total grayscale amount of the area. The calculation of the horizontal first-order moment M10 is a weighted summation of the grayscale values ​​of each row of pixels, with the weight being the pixel coordinates of the row, thereby reflecting the grayscale center of gravity position of the area in the horizontal direction. The calculation of the vertical first-order moment M01 is similar, but the weight is the pixel coordinates of each column, reflecting the grayscale center of gravity position of the area in the vertical direction. Finally, by combining the values ​​of these three moments and using a specific formula to calculate the center position of the divided area, high-precision extraction of image features is achieved.

[0089] In some embodiments of the present application, determining the distance between a pixel point in an undivided area and the center position of each divided area, and classifying the pixel point in the undivided area into a divided area based on the distance includes: determining the distance between the pixel point in the undivided area and the center position of each adjacent divided area, comparing the distances to determine a minimum value; determining the divided area corresponding to the minimum value, and classifying the pixel point in the undivided area into the divided area corresponding to the minimum value;

[0090] The distance is determined according to the following formula:

[0091] ;

[0092] Among them, D wij represents the distance between the pixel point in row i and column j in the undivided area and the center of the divided area, (x wi ,y wj ) represents the coordinates of the pixel point in the i-th row and j-th column in the undivided area, (x z ,y z ) represents the coordinates of the center position of the divided area.

[0093] As can be understood, by calculating the distance between pixels in the undivided area and the center of each divided area and classifying pixels based on the minimum distance principle, the accuracy of pixel attribution is ensured. This method avoids the pixel misclassification problem that may occur in traditional image segmentation and further improves the accuracy of image processing. At the same time, this technical solution uses a clear mathematical formula to determine distance, ensuring the objectivity and consistency of the calculation process, providing more accurate data support for subsequent image processing tasks.

[0094] In some embodiments of the present application, all pixels in the undivided area are classified to implement synthetic aperture radar image processing, including: classifying all pixels in the undivided area to determine a division trajectory for dividing the area; and denoising and enhancing the synthetic aperture radar image according to the division trajectory to implement synthetic aperture radar image processing.

[0095] It's easy to see that by comprehensively classifying pixels in undivided areas and determining the segmentation trajectory based on the classification results, this method can more accurately identify and process feature information in the image. Noise reduction effectively reduces noise interference in the image, improving image clarity and readability; while enhancement highlights important features, making the image information more distinct and easier to analyze. This processing approach not only improves image processing efficiency but also further enhances image quality, providing a more reliable foundation for subsequent image analysis and applications.

[0096] like Figure 2 As shown, the present invention also discloses a synthetic aperture radar image processing system for applying the above synthetic aperture radar image processing method, comprising:

[0097] The image acquisition module is configured to acquire a synthetic aperture radar image.

[0098] The grayscale processing module is configured to perform grayscale processing on the synthetic aperture radar image to obtain a radar grayscale image, and determine the grayscale values ​​of pixels in the radar grayscale image.

[0099] The grayscale determination module is configured to count the number of pixels corresponding to each grayscale value to obtain a pixel number set, sort the pixel number set in descending order, determine the grayscale value corresponding to the number of pixels in a preset ranking, and set it as the target grayscale value.

[0100] The region division module is configured to divide the radar grayscale image according to the target grayscale value to obtain a plurality of divided regions and undivided regions.

[0101] The position classification module is configured to obtain the center position of each divided area, determine the distance between the pixel points in the undivided area and the center position of each divided area, and classify the pixel points in the undivided area into the divided areas according to the distance until all the pixel points in the undivided area are classified, so as to realize the processing of the synthetic aperture radar image.

[0102] The image acquisition module efficiently captures synthetic aperture radar (SAR) images, providing basic data for subsequent processing. The grayscale processing module converts images to grayscale, simplifying image information and facilitating subsequent processing and analysis. The grayscale determination module intelligently determines the target grayscale value by counting and analyzing the number of pixels, providing an accurate basis for region division. The region division module divides the image into several regions based on the target grayscale value, laying the foundation for subsequent classification processing. The position classification module effectively classifies pixels by accurately calculating the distance between pixels and the center of the divided regions, further improving the accuracy and efficiency of image processing. The modules of the entire system work together to achieve efficient and accurate processing of SAR images, providing strong technical support for research and application in related fields.

[0103] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A synthetic aperture radar image processing method, characterized in that: include: Acquire a synthetic aperture radar image, perform grayscale processing on the synthetic aperture radar image to obtain a radar grayscale image, and determine the grayscale values ​​of pixels in the radar grayscale image; Counting the number of pixels corresponding to each grayscale value to obtain a pixel number set, sorting the pixel number set in descending order, determining the grayscale value corresponding to the number of pixels in a preset ranking, and setting it as the target grayscale value; Dividing the radar grayscale image according to the target grayscale value to obtain a plurality of divided areas and undivided areas; Obtaining the center position of each divided region, determining the distance between a pixel point in an undivided region and the center position of each divided region, and classifying the pixel points in the undivided region into the divided regions according to the distance until all the pixel points in the undivided region are classified, thereby processing the synthetic aperture radar image; Sorting the pixel point set in descending order, determining the grayscale value corresponding to the pixel point number of a preset ranking, and setting it as the target grayscale value, including: After sorting the pixel point set in descending order, determining a preset ranking according to the pixel point number; Determining the number of grayscale values ​​to be screened based on the preset ranking, determining the grayscale value corresponding to the corresponding number of pixels according to the set of pixel numbers and grayscale values ​​sorted in descending order, and setting it as the target grayscale value; After sorting the pixel point set in descending order, determining a preset ranking according to the pixel point number includes: Preset pixel number threshold; Comparing each pixel number after descending sorting with the pixel number threshold; if the pixel number threshold is less than the pixel number, comparing the pixel number threshold with the next pixel number until the pixel number threshold is greater than or equal to the pixel number; Determine that the ranking corresponding to when the pixel number threshold is greater than or equal to the pixel number is the preset ranking; The radar grayscale image is divided according to the target grayscale value to obtain a plurality of divided areas and undivided areas, including: Determining several target grayscale value ranges according to the target grayscale value; Divide the area with the same target grayscale value range into several initial divided areas; Determine whether each initial divided area with the same target gray value range is connected. If so, set the corresponding initial divided area as the divided area; If they are not connected, the disconnected initial partitioned areas are set as partitioned areas respectively; The area whose grayscale value does not belong to the target grayscale value range is determined as an undivided area.

2. The synthetic aperture radar image processing method according to claim 1, characterized in that: According to the target grayscale value, several target grayscale value ranges are determined, including: Set the target grayscale change limit; The target grayscale value range is determined according to the target grayscale value and the target grayscale change limit, wherein the left boundary of the target grayscale value range is: target grayscale value - target grayscale change limit, and the right boundary is: target grayscale value + target grayscale change limit.

3. The synthetic aperture radar image processing method according to claim 1, characterized in that: Get the center position of each divided area, including: Get the pixel coordinates and grayscale values ​​of each divided area; Determine the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01 of each divided area according to the pixel coordinates and grayscale values; The center position of each divided area is determined according to the zero-order moment M00, the horizontal first-order moment M10 and the vertical first-order moment M01.

4. The synthetic aperture radar image processing method according to claim 1, characterized in that: Classifying all pixels in the undivided area to process the synthetic aperture radar image includes: Classifying all the pixel points in the undivided area to determine the division trajectory of the divided area; The synthetic aperture radar image is denoised and enhanced according to the division trajectory to achieve synthetic aperture radar image processing.

5. A synthetic aperture radar image processing system, adapted to apply the synthetic aperture radar image processing method according to any one of claims 1 to 4, characterized in that: include: An image acquisition module is configured to acquire a synthetic aperture radar image; a grayscale processing module configured to perform grayscale processing on the synthetic aperture radar image to obtain a radar grayscale image, and determine the grayscale values ​​of pixels in the radar grayscale image; a grayscale determination module configured to count the number of pixels corresponding to each grayscale value to obtain a pixel number set, sort the pixel number set in descending order, determine the grayscale value corresponding to the number of pixels in a preset ranking, and set the grayscale value as the target grayscale value; a region division module configured to divide the radar grayscale image according to the target grayscale value to obtain a plurality of divided regions and undivided regions; The position classification module is configured to obtain the center position of each divided area, determine the distance between the pixel points in the undivided area and the center position of each divided area, and classify the pixel points in the undivided area into the divided areas according to the distance until all the pixel points in the undivided area are classified, so as to realize the processing of the synthetic aperture radar image.

Images