A method and apparatus for generating SAR scene targets based on space calibration

Abstract

This invention discloses a method and apparatus for generating SAR scene targets based on space calibration. The method involves using sensors to detect SAR signals and obtain the flight direction of the SAR carrier; selecting a SAR target dataset by establishing a database; rotating and flipping the SAR target dataset according to the flight direction of the SAR carrier to obtain a processed SAR target dataset; performing unified resolution processing on the processed SAR target dataset and the SAR scene to obtain a unified resolution SAR target dataset and the SAR scene; and fusing the unified resolution SAR target dataset and the SAR scene by setting a fusion strategy to generate SAR scene targets. This invention can generate a large number of SAR scene target datasets that conform to the actual imaging geometry in a relatively short time, improving data generation efficiency.

Description

Technical Field

[0001] This invention specifically relates to a method and apparatus for generating SAR scene targets based on spatial calibration. It pertains to the fields of scene target generation and signal processing technology. Background Technology

[0002] Synthetic Aperture Radar (SAR) image datasets are particularly important for expanding the training set of neural networks. By increasing the size of the SAR image dataset, we can significantly improve the training effect of neural networks, thereby enhancing their robustness. This improved robustness helps the network maintain good performance when facing complex and changing environments. Simultaneously, a richer dataset can effectively reduce underfitting during neural network training, enabling the network to more accurately learn and simulate the characteristics of SAR images, thus improving prediction accuracy and reliability in practical applications. Therefore, increasing research on methods for collecting and generating SAR image datasets is of great significance for promoting the development of the remote sensing field.

[0003] However, current SAR image datasets face challenges such as high acquisition costs, complex processing procedures, and limited data volume, which undoubtedly restricts their widespread application and effectiveness in practice. To overcome this problem, researchers have proposed many methods for generating SAR data. However, traditional SAR target dataset generation methods, such as slicing existing SAR target datasets or using generative adversarial networks to generate datasets, are mainly limited to slice sets or ignore the spatial geometry of SAR images, resulting in generated datasets that do not closely match actual imaging.

[0004] Therefore, how to invent a SAR scene target generation method based on spatial calibration to improve the efficiency of data generation has become an urgent problem to be solved. Summary of the Invention

[0005] To this end, the present invention provides a SAR scene target generation method and apparatus based on spatial calibration, which can generate a large number of SAR scene target datasets that conform to the actual imaging geometric features in a relatively short time, thereby improving the efficiency of data generation.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a SAR scene target generation method based on space calibration, comprising:

[0007] The flight direction of the SAR carrier is obtained by detecting SAR signals through sensors;

[0008] By setting up a database, a SAR target dataset is selected;

[0009] The SAR target dataset is rotated and flipped according to the flight direction of the SAR carrier to obtain the processed SAR target dataset;

[0010] The processed SAR target dataset and SAR scene are subjected to unified resolution processing to obtain the SAR target dataset and SAR scene with unified resolution;

[0011] By setting a fusion strategy, the SAR target dataset and the SAR scene with the same resolution are fused to generate SAR scene targets.

[0012] As a preferred embodiment of a SAR scene target generation method based on spatial calibration, the rotation matrix expression is as follows during the rotation processing of the SAR target dataset:

[0013]

[0014] In the formula, θ is the set rotation angle.

[0015] As a preferred embodiment of a SAR scene target generation method based on spatial calibration, the expression for the folding process in the SAR target dataset is:

[0016] C(i,j)=B(i,N+1-j)

[0017] In the formula, C is the matrix after folding; B is the matrix before folding; i and j are matrix coordinates; and N is the matrix size.

[0018] As a preferred embodiment of a SAR scene target generation method based on spatial calibration, during the process of unifying the resolution of the processed SAR target dataset and the SAR scene, a downsampling strategy is used to convert the high-resolution SAR target dataset into a low-resolution SAR target dataset, thereby unifying the resolution of the SAR target dataset and the SAR scene.

[0019] As a preferred embodiment of a SAR scene target generation method based on spatial calibration, during the process of fusing the SAR target dataset and the SAR scene with uniform resolution through the set fusion strategy, the SAR target dataset and the SAR scene with uniform resolution are respectively subjected to inverse imaging processing; after the inverse imaging processing, fusion is performed in the echo domain; the fusion processing expression is:

[0020]

[0021] In the formula, γ is the adjustment factor; B' is the echo matrix corresponding to the SAR target after rotation; C' is the echo matrix corresponding to the SAR target after folding; D is the echo corresponding to the N×N scene portion in the SAR scene; L represents the left view; R represents the right view.

[0022] This invention also provides a SAR scene target generation device based on space calibration, which, based on the above-mentioned SAR scene target generation method based on space calibration, includes:

[0023] The SAR carrier flight direction acquisition module is used to detect SAR signals through sensors and obtain the flight direction of the SAR carrier.

[0024] The SAR target dataset selection module is used to select SAR target datasets by setting a database.

[0025] The SAR target dataset processing module is used to rotate and fold the SAR target dataset according to the flight direction of the SAR carrier to obtain the processed SAR target dataset.

[0026] The resolution unification module is used to perform resolution unification processing on the processed SAR target dataset and SAR scene to obtain the SAR target dataset and SAR scene with unified resolution;

[0027] The fusion processing module is used to fuse the SAR target dataset and the SAR scene with a uniform resolution by setting a fusion strategy to generate SAR scene targets.

[0028] As a preferred embodiment of a SAR scene target generation device based on spatial calibration, in the SAR target dataset processing module, during the rotation processing of the SAR target dataset, the rotation matrix expression is:

[0029]

[0030] In the formula, θ is the set rotation angle.

[0031] As a preferred embodiment of a SAR scene target generation device based on spatial calibration, in the SAR target dataset processing module, during the folding process of the SAR target dataset, the expression for the folding process is:

[0032] C(i,j)=B(i,N+1-j)

[0033] In the formula, C is the matrix after folding; B is the matrix before folding; i and j are matrix coordinates; and N is the matrix size.

[0034] As a preferred embodiment of a SAR scene target generation device based on spatial calibration, in the resolution unification module, during the process of unifying the resolution of the processed SAR target dataset and the SAR scene, a downsampling strategy is used to convert the high-resolution SAR target dataset into a low-resolution SAR target dataset, thereby unifying the resolution of the SAR target dataset and the SAR scene.

[0035] As a preferred embodiment of a SAR scene target generation device based on spatial calibration, in the fusion processing module, during the process of fusing the SAR target dataset and the SAR scene with uniform resolution through the set fusion strategy, the SAR target dataset and the SAR scene with uniform resolution are respectively subjected to inverse imaging processing; after the inverse imaging processing, fusion is performed in the echo domain; the fusion processing expression is:

[0036]

[0037] In the formula, γ is the adjustment factor; B' is the echo matrix corresponding to the SAR target after rotation; C' is the echo matrix corresponding to the SAR target after folding; D is the echo corresponding to the N×N scene portion in the SAR scene; L represents the left view; R represents the right view.

[0038] This invention offers the following advantages: It obtains the flight direction of the SAR carrier by detecting SAR signals using sensors; it selects a SAR target dataset by establishing a database; it rotates and flips the SAR target dataset according to the flight direction of the SAR carrier to obtain a processed SAR target dataset; it performs unified resolution processing on the processed SAR target dataset and the SAR scene to obtain a unified resolution SAR target dataset and the SAR scene; and it fuses the unified resolution SAR target dataset and the SAR scene using a fusion strategy to generate SAR scene targets. Based on the principle of spatial calibration, this invention effectively transforms multiple SAR target datasets through precise rotation and flipping operations, and then fuses them with the SAR scene. This process can generate a large number of SAR image datasets that conform to the actual imaging geometry in a relatively short time, thus solving the problem of existing SAR image datasets neglecting SAR imaging geometry. This breakthrough not only significantly improves the efficiency of data generation but also ensures that the dataset can adapt to diverse application scenarios and meet the needs of different fields. More importantly, this invention has excellent scalability and can be flexibly expanded to generate more types of SAR scene target datasets according to specific research or application needs, thus providing great convenience and broad possibilities for the continuous development of remote sensing technology and future research. Attached Figure Description

[0039] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0040] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0041] Figure 1 This is a schematic diagram of a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention;

[0042] Figure 2 This is a schematic diagram of the SAR scene result in the standard spatial coordinate system in a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention;

[0043] Figure 3 This is a schematic diagram of the SAR scene imaging result in a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention;

[0044] Figure 4 This is a schematic diagram of SAR target results in a standard spatial coordinate system in a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention;

[0045] Figure 5 This is a schematic diagram of the SAR target and scene fusion result in a standard spatial coordinate system in a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention;

[0046] Figure 6 This is a schematic diagram of the SAR target and scene fusion result without transformation in the SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention;

[0047] Figure 7 This is a schematic diagram of the SAR target and scene fusion result in a standard spatial coordinate system without transformation in a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention.

[0048] Figure 8 This is a schematic diagram of the transformed SAR target and scene fusion result in a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention;

[0049] Figure 9 This is a schematic diagram of the SAR target and scene fusion result after transformation in the standard spatial coordinate system in a SAR scene target generation method based on spatial calibration provided in Embodiment 1 of the present invention.

[0050] Figure 10 This is a schematic diagram of SAR scene results in a standard spatial coordinate system in one possible embodiment of Embodiment 1 of the present invention;

[0051] Figure 11 This is a schematic diagram of SAR scene imaging results in one possible embodiment provided in Embodiment 1 of the present invention;

[0052] Figure 12 This is a schematic diagram of SAR target results in a standard spatial coordinate system in one possible embodiment of Embodiment 1 of the present invention;

[0053] Figure 13 This is a schematic diagram of SAR target imaging results in one possible embodiment provided in Embodiment 1 of the present invention;

[0054] Figure 14 This is a schematic diagram of the imaging result after fusion of SAR target and SAR scene in one possible embodiment provided in Embodiment 1 of the present invention;

[0055] Figure 15 This is a schematic diagram of the fusion result of SAR target and SAR scene in a standard spatial coordinate system in one possible embodiment of Embodiment 1 of the present invention;

[0056] Figure 16 This is a schematic diagram of the detection result after fusion of SAR target and SAR scene in one possible embodiment provided in Embodiment 1 of the present invention;

[0057] Figure 17 This is a schematic diagram of the architecture of a SAR scene target generation device based on space calibration provided in Embodiment 2 of the present invention. Detailed Implementation

[0058] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Example 1

[0060] See Figure 1 Embodiment 1 of the present invention provides a SAR scene target generation method based on space calibration, comprising the following steps:

[0061] S1. Detect SAR signals using sensors to obtain the flight direction of the SAR carrier;

[0062] S2. Select the SAR target dataset by setting up the database;

[0063] S3. Rotate and fold the SAR target dataset according to the flight direction of the SAR carrier to obtain the processed SAR target dataset;

[0064] S4. Perform unified resolution processing on the processed SAR target dataset and SAR scene to obtain the SAR target dataset and SAR scene with unified resolution;

[0065] S5. By setting a fusion strategy, the SAR target dataset and the SAR scene with the same resolution are fused to generate SAR scene targets.

[0066] In this embodiment, in step S1, the SAR signal is detected by a sensor to obtain the flight direction of the SAR carrier;

[0067] Specifically, by using sensors to detect and measure SAR signals, the flight direction of the SAR carrier corresponding to the SAR scene can be obtained.

[0068] In this embodiment, in step S2, a SAR target dataset is selected by setting up a database.

[0069] Specifically, by setting up a database, the required SAR target dataset is selected.

[0070] In this embodiment, in step S3, the SAR target dataset is rotated and flipped according to the flight direction of the SAR carrier to obtain the processed SAR target dataset;

[0071] Specifically, such as Figure 2As shown, the SAR carrier flies from south to north at a 45° east-northeast angle, and is viewed from the right. Therefore, from the perspective of the SAR carrier, its flight direction is the azimuth direction after imaging, and the vertical direction is the range direction. The corresponding imaging results are as follows: Figure 3 As shown. At this point, I want to... Figure 4 The SAR targets shown are fused into the SAR scene to form a shape like... Figure 5 The results are shown. If we take Figure 4 If the fusion is performed directly without any transformation, the resulting range-azimuth image will be as follows: Figure 6 As shown, this Figure 6 The results in the corresponding standard spatial coordinate system are as follows Figure 7 As shown, this is clearly not what is required. Therefore, it is necessary to... Figure 4 Perform a rotation transformation, and then fuse it into the range-azimuth imaging map, such as... Figure 8 As shown, the result of the fused imaging in this way meets the requirements in the corresponding spatial coordinate system. Figure 9 As shown.

[0072] The rotation angle is related to the flight direction and the left and right side views. This invention rotates counterclockwise, and the flight angle is the angle between the chosen flight direction and the due south and due north directions. Specifically:

[0073] If the flight direction is from south to north, and the angle of west of north is α, then the rotation angle β is:

[0074]

[0075] If the flight direction is from south to north, and the angle of north by east is α, then the rotation angle β is:

[0076]

[0077] If the flight direction is from north to south, and the angle of south by west is α, then the rotation angle β is:

[0078]

[0079] If the flight direction is from north to south, and the angle of south by east is α, then the rotation angle β is:

[0080]

[0081] In the above formula, R represents the right-side view and L represents the left-side view. In order to achieve spatial calibration, if the SAR carrier is the left-side view, it needs to be folded on the basis of rotation.

[0082] In this embodiment, the rotation angle operation is specifically as follows:

[0083] In an N×N matrix A, an element A(i,j) is rotated to become A θ (i θ ,j θ Represented as a matrix:

[0084]

[0085] The rotation matrix T can be expressed as:

[0086]

[0087] In the formula, θ is the set rotation angle.

[0088] Finally, all pixels in matrix A are rotated to obtain matrix B.

[0089] In this embodiment, the folding operation is specifically as follows:

[0090] For each row of the rotated N×N matrix B, the elements are flipped to obtain the flipped matrix C, where:

[0091] C(i,j)=B(i,N+1-j)

[0092] In the formula, C is the matrix after folding; B is the matrix before folding; i and j are matrix coordinates; and N is the matrix size.

[0093] In this embodiment, in step S4, the processed SAR target dataset and SAR scene are subjected to unified resolution processing to obtain the SAR target dataset and SAR scene with unified resolution;

[0094] Specifically, because the resolution of the SAR target dataset and the SAR scene are different, downsampling is required. The downsampling method reduces a pixel region in the SAR image to a single pixel, the value of which is the average of the pixel values ​​in that region. The size of the pixel region is determined by the ratio of the resolution of the SAR target dataset and the SAR scene. Downsampling converts the high-resolution SAR target dataset output by the spatial calibration module into a low-resolution SAR image target dataset, thereby unifying the resolution of the SAR target dataset and the SAR scene. Therefore, after processing, the SAR target dataset and the SAR scene have the same resolution. Subsequent steps only require selecting target portions of the same size from both the SAR target dataset and the SAR scene, processing them, and fusing them.

[0095] In this embodiment, in step S5, by setting a fusion strategy, the SAR target dataset and the SAR scene with the same resolution are fused to generate SAR scene targets.

[0096] Specifically, firstly, inverse imaging is performed on both the SAR scene and SAR target data after unifying the resolution, and then they are fused in the echo domain. The fusion processing expression is as follows:

[0097]

[0098] In the formula, γ is an adjustment factor, which makes the fused image fit the scene naturally; B' is the echo matrix corresponding to the SAR target after rotation; C' is the echo matrix corresponding to the SAR target after folding; and D is the echo corresponding to the N×N scene portion in the SAR scene.

[0099] In one possible embodiment, a specific simulation experiment example is provided as follows:

[0100] like Figure 10 As shown, the corresponding SAR carrier's flight direction, as determined by reconnaissance, is from south to north, 63.5° east of north, and is a right-side view. Therefore, from the perspective of the SAR carrier, its imaging range-azimuth map is as follows. Figure 11 As shown. So, if we want to... Figure 12 The SAR target shown should be fused with the SAR scene. Figure 12 Calibration was performed to obtain Figure 13 The results are shown below. Then, the resolution of these results is unified, and finally, the SAR target and SAR scene images with unified resolution are fused to obtain the results shown below. Figure 14 The results shown correspond to the results in the spatial coordinate system as follows: Figure 15 As shown. Furthermore, the SAR targets generated by the method proposed in this invention can be detected by target detection algorithms such as CFAR, verifying the correctness of the proposed method, as shown. Figure 16 As shown.

[0101] In summary, this invention uses sensors to detect SAR signals and obtain the flight direction of the SAR carrier; it selects a SAR target dataset by establishing a database; it rotates and flips the SAR target dataset according to the flight direction of the SAR carrier to obtain a processed SAR target dataset; it then performs unified resolution processing on the processed SAR target dataset and the SAR scene to obtain a unified resolution SAR target dataset and the SAR scene; finally, it fuses the unified resolution SAR target dataset and the SAR scene by setting a fusion strategy to generate SAR scene targets. Based on the principle of spatial calibration, this invention effectively transforms multiple SAR target datasets through precise rotation and flipping operations, and then fuses them with the SAR scene. This process can generate a large number of SAR image datasets that conform to the actual imaging geometry in a relatively short time, thus solving the problem of existing SAR image datasets neglecting SAR imaging geometry. This breakthrough not only significantly improves the efficiency of data generation but also ensures that the dataset can adapt to diverse application scenarios and meet the needs of different fields. More importantly, this invention has excellent scalability and can be flexibly expanded to generate more types of SAR scene target datasets according to specific research or application needs, thus providing great convenience and broad possibilities for the continuous development of remote sensing technology and future research.

[0102] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0103] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0104] Example 2

[0105] See Figure 17 Embodiment 2 of the present invention also provides a SAR scene target generation device based on space calibration, comprising:

[0106] The SAR carrier flight direction acquisition module 001 is used to detect SAR signals through sensors and obtain the flight direction of the SAR carrier.

[0107] SAR target dataset selection module 002 is used to select SAR target datasets by setting a database;

[0108] SAR target dataset processing module 003 is used to rotate and fold the SAR target dataset according to the flight direction of the SAR carrier to obtain the processed SAR target dataset;

[0109] The resolution unification module 004 is used to perform resolution unification processing on the processed SAR target dataset and SAR scene to obtain the SAR target dataset and SAR scene with unified resolution;

[0110] The fusion processing module 005 is used to fuse the SAR target dataset and the SAR scene with a uniform resolution by setting a fusion strategy to generate SAR scene targets.

[0111] In this embodiment, in the SAR target dataset processing module 003, during the rotation processing of the SAR target dataset, the rotation matrix expression is:

[0112]

[0113] In the formula, θ is the set rotation angle.

[0114] In this embodiment, in the SAR target dataset processing module 003, during the folding process of the SAR target dataset, the expression for the folding process is:

[0115] C(i,j)=B(i,N+1-j)

[0116] In the formula, C is the matrix after folding; B is the matrix before folding; i and j are matrix coordinates; and N is the matrix size.

[0117] In this embodiment, in the resolution unification module 004, during the process of unifying the resolution of the processed SAR target dataset and the SAR scene, a downsampling strategy is used to convert the high-resolution SAR target dataset into a low-resolution SAR target dataset, thereby unifying the resolution of the SAR target dataset and the SAR scene.

[0118] In this embodiment, in the fusion processing module 005, during the process of fusing the SAR target dataset and the SAR scene with the same resolution through the set fusion strategy, the SAR target dataset and the SAR scene with the same resolution are respectively subjected to inverse imaging processing; after the inverse imaging processing, fusion is performed in the echo domain; the fusion processing expression is:

[0119]

[0120] In the formula, γ is the adjustment factor; B' is the echo matrix corresponding to the SAR target after rotation; C' is the echo matrix corresponding to the SAR target after folding; D is the echo corresponding to the N×N scene portion in the SAR scene; L represents the left view; R represents the right view.

[0121] It should be noted that the information interaction and execution process between the modules of the above system are based on the same concept as the method embodiment in Embodiment 1 of this application, and the resulting technical effects are the same as those in the method embodiment of this application. For details, please refer to the description in the method embodiment shown above in this application, and it will not be repeated here.

[0122] Example 3

[0123] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium storing program code for a SAR scene target generation method based on spatial calibration. The program code includes instructions for executing the SAR scene target generation method based on spatial calibration of Embodiment 1 or any possible implementation thereof.

[0124] Computer-readable storage media can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives, SSDs).

[0125] Example 4

[0126] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0127] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor can execute a SAR scene target generation method based on space calibration according to Embodiment 1 or any possible implementation thereof by calling the program instructions.

[0128] Specifically, a processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0129] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0130] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing systems. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Optionally, they can be implemented using program code executable by a computing system, thereby storing them in a storage system for execution by the computing system. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0131] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A SAR scene target generation method based on space calibration, characterized in that, include: The flight direction of the SAR carrier is obtained by detecting SAR signals through sensors; By setting up a database, a SAR target dataset is selected; The SAR target dataset is rotated and flipped according to the flight direction of the SAR carrier to obtain the processed SAR target dataset; The processed SAR target dataset and SAR scene are subjected to unified resolution processing to obtain the SAR target dataset and SAR scene with unified resolution; By setting a fusion strategy, the SAR target dataset and the SAR scene with the same resolution are fused to generate SAR scene targets; In the process of fusing the SAR target dataset and the SAR scene with uniform resolution using the defined fusion strategy, the SAR target dataset and the SAR scene with uniform resolution are respectively subjected to inverse imaging processing; after the inverse imaging processing, fusion is performed in the echo domain; the fusion processing expression is: In the formula, γ is the adjustment factor; B' is the echo matrix corresponding to the SAR target after rotation; C' is the echo matrix corresponding to the SAR target after folding; D is the echo corresponding to the N×N scene portion in the SAR scene; L represents the left view; R represents the right view.

2. The SAR scene target generation method based on space calibration according to claim 1, characterized in that, During the rotation process of the SAR target dataset, the rotation matrix expression is as follows: In the formula, θ is the set rotation angle.

3. The SAR scene target generation method based on space calibration according to claim 2, characterized in that, During the folding process of the SAR target dataset, the folding expression is: C(i,j)=B(i,N+1-j) In the formula, C is the matrix after folding; B is the matrix before folding; i and j are matrix coordinates; and N is the matrix size.

4. The SAR scene target generation method based on space calibration according to claim 3, characterized in that, In the process of unifying the resolution of the processed SAR target dataset and the SAR scene, a downsampling strategy is used to convert the high-resolution SAR target dataset into a low-resolution SAR target dataset, thereby unifying the resolution of the SAR target dataset and the SAR scene.

5. A SAR scene target generation device based on space calibration, employing the SAR scene target generation method based on space calibration as described in any one of claims 1-4, characterized in that, include: The SAR carrier flight direction acquisition module is used to detect SAR signals through sensors and obtain the flight direction of the SAR carrier. The SAR target dataset selection module is used to select SAR target datasets by setting a database. The SAR target dataset processing module is used to rotate and fold the SAR target dataset according to the flight direction of the SAR carrier to obtain the processed SAR target dataset. The resolution unification module is used to perform resolution unification processing on the processed SAR target dataset and SAR scene to obtain the SAR target dataset and SAR scene with unified resolution; The fusion processing module is used to fuse the SAR target dataset and the SAR scene with a uniform resolution by setting a fusion strategy to generate SAR scene targets; In the fusion processing module, during the process of fusing the SAR target dataset and the SAR scene with uniform resolution using the set fusion strategy, the SAR target dataset and the SAR scene with uniform resolution are respectively subjected to inverse imaging processing; after the inverse imaging processing, fusion is performed in the echo domain; the fusion processing expression is: In the formula, γ is the adjustment factor; B' is the echo matrix corresponding to the SAR target after rotation; C' is the echo matrix corresponding to the SAR target after folding; D is the echo corresponding to the N×N scene portion in the SAR scene; L represents the left view; R represents the right view.

6. The SAR scene target generation device based on space calibration according to claim 5, characterized in that, In the SAR target dataset processing module, during the rotation process of the SAR target dataset, the rotation matrix expression is: In the formula, θ is the set rotation angle.

7. The SAR scene target generation device based on space calibration according to claim 6, characterized in that, In the SAR target dataset processing module, during the folding process of the SAR target dataset, the expression for the folding process is: C(i,j)=B(i,N+1-j) In the formula, C is the matrix after folding; B is the matrix before folding; i and j are matrix coordinates; and N is the matrix size.

8. The SAR scene target generation device based on space calibration according to claim 7, characterized in that, In the resolution unification module, during the process of unifying the resolution of the processed SAR target dataset and the SAR scene, a downsampling strategy is used to convert the high-resolution SAR target dataset into a low-resolution SAR target dataset, thereby unifying the resolution of the SAR target dataset and the SAR scene.

Images