A method and device for generating SAR scene target data set based on environment matching

Abstract

A method and device for generating a SAR scene target dataset based on environment matching. The method selects a first-category SAR target dataset and a second-category SAR target dataset based on target scene requirements, and downsamples their resolutions to achieve the same resolution. The method then processes the datasets using a CM image fusion strategy to obtain a fused target portion of the first-category SAR target dataset, which is then subjected to a rotation transformation to obtain a rotated fused target portion of the first-category SAR target dataset. The method then processes the datasets using an Anti-CM image fusion strategy to obtain a fused scene portion of the second-category SAR target dataset. Finally, the method generates a SAR scene target dataset that meets the target scene requirements using a DCM image fusion strategy. The present invention can generate a large number of high-quality SAR image datasets in a relatively short period of time, meeting the requirements of different application scenarios. It can also be expanded to generate other types of SAR image datasets, facilitating future research.

Description

Technical Field

[0001] The present invention relates to the technical field of image fusion and signal processing, and in particular to a method and device for generating a SAR scene target data set based on environment matching. Background Art

[0002] The scarcity of Synthetic Aperture Radar (SAR) image datasets and the inadequacy of their generation methods are currently a major challenge facing the remote sensing field. SAR image datasets are widely used in many fields, such as environmental monitoring and resource exploration.

[0003] Currently, due to the high cost of SAR image data acquisition, complex data processing, and limited data volume, existing SAR image datasets are unable to meet the needs of practical applications. In addition, traditional SAR target dataset generation methods have certain limitations, such as slow generation speed, single scene, and limited target types.

[0004] Therefore, studying the generation method of SAR scene target dataset based on environment matching has important practical significance and broad application prospects. Summary of the Invention

[0005] To this end, the present invention provides a method and apparatus for generating SAR scene target datasets based on environmental matching. This method, based on the DCM (Double Caster Matrix) image fusion principle, can fuse different types of SAR target datasets, thereby generating a large number of high-quality SAR image datasets in a relatively short period of time. Furthermore, it can generate SAR image datasets covering various terrains and landforms, meeting the needs of different application scenarios.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solution: a method for generating a SAR scene target dataset based on environment matching, comprising:

[0007] According to the target scene requirements, the first and second category SAR target datasets are selected;

[0008] Downsampling the resolutions of the first category SAR target dataset and the second category SAR target dataset to form the same resolution;

[0009] Processing the first type of SAR target data set through a CM image fusion strategy to obtain a fused target portion of the first type of SAR target data set; performing a rotation transformation on the fused target portion of the first type of SAR target data set to obtain a rotated fused target portion of the first type of SAR target data set;

[0010] Processing the second type of SAR target data set through the Anti-CM image fusion strategy to obtain a fused scene portion of the second type of SAR target data set;

[0011] Through the DCM image fusion strategy, the rotated fused target part of the first type of SAR target dataset is fused into the fused scene part of the second type of SAR target dataset to generate a SAR scene target dataset that meets the target scene requirements.

[0012] As a preferred solution of the method for generating a SAR scene target dataset based on environment matching, in the process of downsampling the resolutions of the first type of SAR target dataset and the second type of SAR target dataset, if the resolutions of the first type of SAR target dataset and the second type of SAR target dataset are the same, directly proceeding to the next step;

[0013] If the resolutions of the first category SAR target dataset and the second category SAR target dataset are different, the downsampling process is performed to reduce a pixel area in the SAR image to a pixel, so that the high-resolution SAR target dataset is converted into a low-resolution SAR image target dataset to form the same resolution.

[0014] As a preferred solution of the method for generating a SAR scene target dataset based on environment matching, in the process of obtaining the rotated fused target portion of the first-category SAR target dataset through the CM image fusion strategy, the target portion in the first-category SAR target dataset is cropped out and multiplied with the CM matrix to obtain the fused target portion of the first-category SAR target dataset; the fused target portion of the first-category SAR target dataset is subjected to a rotation transformation to obtain the rotated fused target portion of the first-category SAR target dataset, so that the shadow direction of the rotated fused target portion of the first-category SAR target dataset is consistent with the shadow direction of the fused scene portion of the second-category SAR target dataset.

[0015] As a preferred solution for a method for generating a SAR scene target dataset based on environment matching, in the process of obtaining the fused scene portion of the second-category SAR target dataset through the Anti-CM image fusion strategy, the scene portion of the second-category SAR target dataset is cropped out and multiplied by the Anti-CM matrix to obtain the fused scene portion of the second-category SAR target dataset.

[0016] As a preferred solution for a method for generating a SAR scene target dataset based on environment matching, the DCM image fusion strategy is as follows: a data matrix of the fused target portion of the first type of SAR target dataset is calculated and processed with a data matrix of the rotated fused target portion of the first type of SAR target dataset to obtain a new data matrix; and the new data matrix is ​​used to replace the data matrix of the scene portion of the second type of SAR target dataset to generate a SAR scene target dataset that meets the target scene requirements.

[0017] The present invention also provides a SAR scene target data set generation device based on environment matching, based on the above SAR scene target data set generation method based on environment matching, comprising:

[0018] A SAR target data set selection module is used to select the first type of SAR target data set and the second type of SAR target data set according to the target scene requirements;

[0019] an image resolution unification module, configured to downsample the resolutions of the first type of SAR target dataset and the second type of SAR target dataset to form the same resolution;

[0020] a CM image fusion module, configured to process the first type of SAR target dataset using a CM image fusion strategy to obtain a fused target portion of the first type of SAR target dataset; and perform a rotation transformation on the fused target portion of the first type of SAR target dataset to obtain a rotated fused target portion of the first type of SAR target dataset;

[0021] An Anti-CM image fusion module is used to process the second type of SAR target dataset through the Anti-CM image fusion strategy to obtain a fused scene part of the second type of SAR target dataset;

[0022] The SAR scene target dataset generation module is configured to fuse the rotated fused target portion of the first type of SAR target dataset into the fused scene portion of the second type of SAR target dataset through a DCM image fusion strategy, thereby generating a SAR scene target dataset that meets the target scene requirements.

[0023] As a preferred solution of the device for generating a SAR scene target dataset based on environment matching, in the image resolution unification module, during the process of downsampling the resolutions of the first type of SAR target dataset and the second type of SAR target dataset, if the resolutions of the first type of SAR target dataset and the second type of SAR target dataset are the same, then directly proceeding to the next step;

[0024] If the resolutions of the first category SAR target dataset and the second category SAR target dataset are different, the downsampling process is performed to reduce a pixel area in the SAR image to a pixel, so that the high-resolution SAR target dataset is converted into a low-resolution SAR image target dataset to form the same resolution.

[0025] As a preferred solution for a SAR scene target dataset generation device based on environment matching, in the CM image fusion module, in the process of obtaining the rotated fused target portion of the first-category SAR target dataset through the CM image fusion strategy, the target portion in the first-category SAR target dataset is cropped and multiplied by the CM matrix to obtain the fused target portion of the first-category SAR target dataset; and the fused target portion of the first-category SAR target dataset is subjected to a rotation transformation to obtain the rotated fused target portion of the first-category SAR target dataset, so that the shadow direction of the rotated fused target portion of the first-category SAR target dataset is consistent with the shadow direction of the fused scene portion of the second-category SAR target dataset.

[0026] As a preferred solution for a SAR scene target dataset generation device based on environment matching, in the Anti-CM image fusion module, during the process of obtaining the fused scene portion of the second-category SAR target dataset through the Anti-CM image fusion strategy, the scene portion of the second-category SAR target dataset is cropped and multiplied by the Anti-CM matrix to obtain the fused scene portion of the second-category SAR target dataset.

[0027] As a preferred solution for a SAR scene target dataset generation device based on environment matching, in the SAR scene target dataset generation module, the DCM image fusion strategy is: performing computational processing on a data matrix of a fused target portion of the first type of SAR target dataset and a rotated data matrix of the fused target portion of the first type of SAR target dataset to obtain a new data matrix; and replacing the data matrix of the scene portion of the second type of SAR target dataset with the new data matrix to generate a SAR scene target dataset that meets the target scene requirements.

[0028] The present invention has the following advantages: based on target scene requirements, a first-category SAR target dataset and a second-category SAR target dataset are selected; the resolutions of the first-category SAR target dataset and the second-category SAR target dataset are downsampled to the same resolution; the first-category SAR target dataset is processed using a CM image fusion strategy to obtain a fused target portion of the first-category SAR target dataset; the fused target portion of the first-category SAR target dataset is rotated to obtain a rotated fused target portion of the first-category SAR target dataset; the second-category SAR target dataset is processed using an Anti-CM image fusion strategy to obtain a fused scene portion of the second-category SAR target dataset; and the rotated fused target portion of the first-category SAR target dataset is fused into the fused scene portion of the second-category SAR target dataset using a DCM image fusion strategy, thereby generating a SAR scene target dataset that meets the target scene requirements. Based on the DCM (Double Caster Matrix) image fusion principle, the present invention can fuse different types of SAR target datasets, thereby generating a large number of high-quality SAR image datasets in a relatively short time. It can also generate SAR image datasets covering various terrains and landforms, meeting the requirements of different application scenarios. In addition, it is possible to generate SAR image targets of various types, including aircraft, ships, vehicles, and buildings, thus enhancing the practicality of the dataset. The present invention can also easily expand and generate other types of SAR image datasets based on actual needs, facilitating future research. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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 the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and those skilled in the art can, without inventive effort, derive other implementation drawings based on the provided drawings.

[0030] The structures, proportions, sizes, etc. illustrated in this specification are intended solely to complement the contents disclosed herein and to facilitate understanding and reading by persons skilled in the art. They are not intended to limit the conditions under which the present invention may be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportions, or adjustments in sizes, without affecting the efficacy and objectives of the present invention, shall remain within the scope of the technical contents disclosed herein.

[0031] Figure 1 This is a flow chart of a method for generating a SAR scene target dataset based on environment matching provided in Example 1 of the present invention;

[0032] Figure 2 This is a schematic diagram of a portion of images of a dataset used in a method for generating a SAR scene target dataset based on environment matching provided in Example 1 of the present invention;

[0033] Figure 3 This is a schematic diagram of a portion of images of a new dataset generated in a method for generating a SAR scene target dataset based on environment matching provided in Example 1 of the present invention;

[0034] Figure 4 This is a schematic diagram of detection results of a CFAR target detection algorithm in a method for generating a SAR scene target dataset based on environment matching provided in Example 1 of the present invention;

[0035] Figure 5 This is a schematic diagram of the architecture of a SAR scene target dataset generation device based on environment matching provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0036] The following describes the implementation of the present invention using specific embodiments. Those skilled in the art will readily understand the other advantages and benefits of the present invention from the disclosure herein. Obviously, the embodiments described are only a portion of the present invention, not all of it. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0037] Example 1

[0038] See also Figure 1 Embodiment 1 of the present invention provides a method for generating a SAR scene target dataset based on environment matching, comprising the following steps:

[0039] S1. Select the first and second category SAR target datasets according to the target scene requirements;

[0040] S2. downsampling the resolutions of the first category SAR target dataset and the second category SAR target dataset to have the same resolution;

[0041] S3. Processing the first-category SAR target dataset using a CM image fusion strategy to obtain a fused target portion of the first-category SAR target dataset; performing a rotation transformation on the fused target portion of the first-category SAR target dataset to obtain a rotated fused target portion of the first-category SAR target dataset;

[0042] S4. Processing the second type of SAR target dataset using an Anti-CM image fusion strategy to obtain a fused scene portion of the second type of SAR target dataset;

[0043] S5. Using a DCM image fusion strategy, fuse the rotated fused target portion of the first type of SAR target dataset into the fused scene portion of the second type of SAR target dataset to generate a SAR scene target dataset that meets the target scene requirements.

[0044] In this embodiment, in step S1, Figure 2 As shown in FIG, according to the target scene requirements, the first type of SAR target dataset and the second type of SAR target dataset are selected.

[0045] In this embodiment, in step S2, the resolutions of the first type SAR target dataset and the second type SAR target dataset are downsampled to form the same resolution;

[0046] In the process of downsampling the resolutions of the first-category SAR target dataset and the second-category SAR target dataset, if the resolutions of the first-category SAR target dataset and the second-category SAR target dataset are the same, directly proceeding to the next step;

[0047] If the resolutions of the first category SAR target dataset and the second category SAR target dataset are different, the downsampling process is performed to reduce a pixel area in the SAR image to a pixel, so that the high-resolution SAR target dataset is converted into a low-resolution SAR image target dataset to form the same resolution.

[0048] Specifically, the downsampling method reduces a pixel area in the SAR image to a pixel whose value is the average of the pixel values ​​in this pixel area; the size of the pixel area is determined by the multiple relationship of the resolutions of the two types of SAR target datasets. Downsampling converts the high-resolution SAR target dataset into a low-resolution SAR image target dataset, thereby unifying the resolutions of different SAR target datasets. Therefore, after processing, the resolutions of the two types of SAR target datasets are the same. The subsequent steps only require selecting the target parts and scene parts of the same size in the first and second types of SAR target datasets for processing and fusion.

[0049] In this embodiment, in step S3, the first type of SAR target dataset is processed using the CM image fusion strategy to obtain a fused target portion of the first type of SAR target dataset; the fused target portion of the first type of SAR target dataset is subjected to a rotation transformation to obtain a rotated fused target portion of the first type of SAR target dataset;

[0050] In the process of obtaining the rotated fused target portion of the first-category SAR target dataset through the CM image fusion strategy, the target portion in the first-category SAR target dataset is cropped and multiplied by the CM matrix to obtain the fused target portion of the first-category SAR target dataset; and the fused target portion of the first-category SAR target dataset is subjected to a rotation transformation to obtain the rotated fused target portion of the first-category SAR target dataset, so that the shadow direction of the rotated fused target portion of the first-category SAR target dataset is consistent with the shadow direction of the fused scene portion of the second-category SAR target dataset.

[0051] Specifically, an N×N matrix A containing targets in the first type of SAR target data set is selected;

[0052] Multiply matrix A and CM matrix (matrix C) to obtain matrix D;

[0053] In order to ensure that the shadow direction of the fused target part of the first type of SAR target dataset is consistent with the shadow direction of the fused scene part of the second type of SAR target dataset, it is necessary to multiply the matrix D by the rotation transformation T to obtain the matrix E.

[0054] The CM matrix is ​​shown in formula (1). The outermost circle of the matrix is ​​the first layer. The N×N matrix has layer, Indicates rounding up. CM matrix The layers have the same value, and the number of i layers is determined according to formula (2).

[0055]

[0056]

[0057] Where CM(i) represents the value of the CM matrix layer i. The value of the CM matrix layer i is similar to the tanh function, which weakens the edges of the target pixels and enhances the center, which is conducive to natural edge transition during image fusion.

[0058] Then, a pixel point N(x,y) in the matrix D is rotated to become N θ (x θ ,y θ ), which can be expressed as a matrix:

[0059]

[0060] Among them, the rotation matrix T can be expressed as:

[0061]

[0062] Finally, all pixels in matrix D are rotated to obtain matrix E.

[0063] In this embodiment, in step S4, the second type of SAR target dataset is processed by the Anti-CM image fusion strategy to obtain a fused scene portion of the second type of SAR target dataset;

[0064] In the process of obtaining the fused scene portion of the second type of SAR target data set through the Anti-CM image fusion strategy, the scene portion of the second type of SAR target data set is cropped out and multiplied by the Anti-CM matrix to obtain the fused scene portion of the second type of SAR target data set.

[0065] Specifically, an N×N matrix B (the size of matrix B is the same as that of matrix A) containing scenes in the second type of SAR target data set is selected;

[0066] Multiply the matrix B and the Anti-CM matrix (matrix C') to obtain the matrix E.

[0067] The Anti-CM matrix is ​​shown in formula (5), with the outermost circle of the matrix as the first layer, and the N×N matrix has layer, Indicates rounding up. Anti-CM matrix The layers have the same value, and the number of i layers is determined according to formula (6).

[0068]

[0069]

[0070] Where Anti-CM(i) represents the value of the Anti-CM matrix layer i. The value of the Anti-CM matrix layer i is similar to the tanh function, which enhances the edges of some pixels in the scene and weakens the center, which helps the target part to have a shadow when it is integrated into the scene.

[0071] In this embodiment, in step S5, the DCM image fusion strategy is used to fuse the rotated fused target portion of the first type of SAR target dataset into the fused scene portion of the second type of SAR target dataset to generate a SAR scene target dataset that meets the target scene requirements.

[0072] The DCM image fusion strategy is as follows: performing computational processing on the data matrix of the fused target portion of the first type of SAR target dataset and the rotated data matrix of the fused target portion of the first type of SAR target dataset to obtain a new data matrix; and replacing the data matrix of the scene portion of the second type of SAR target dataset with the new data matrix to generate a SAR scene target dataset that meets the target scene requirements.

[0073] Specifically, the rotated fusion target portion of the first type of SAR target data set is fused into the fusion scene portion of the second type of SAR target data set. The specific fusion method is:

[0074] F=αD+(1-α)E(7)

[0075] Where α is the adjustment factor, which makes the fused image fit naturally in the scene. Next, the data at the positions in the original matrix B in the second type of SAR target dataset needs to be replaced with the values ​​in the matrix F to generate a SAR scene target dataset that meets the requirements of the target scene.

[0076] The present invention uses the DCM (Double Caster Matrix) image fusion principle to fuse the target part of one type of SAR target data set into a medium-sized scene part of another type of SAR target data set, thereby generating a large number of high-quality SAR image data sets in a relatively short time, thereby solving the problem that existing SAR image data sets cannot meet the needs of different application scenarios.

[0077] It has been verified that the SAR target dataset generated by the present invention is very realistic. Not only is the transition at the edge of the image fusion natural, but the shadow part of the original target is also retained. Figure 3 As shown in Figure 2. The SAR targets generated by the proposed method can be detected by target detection algorithms such as CFAR, which verifies the correctness of the proposed method. Figure 4 shown.

[0078] In summary, the present invention selects a first-category SAR target dataset and a second-category SAR target dataset based on target scene requirements; downsamples the resolutions of the first-category SAR target dataset and the second-category SAR target dataset to the same resolution; processes the first-category SAR target dataset using a CM image fusion strategy to obtain a fused target portion of the first-category SAR target dataset; performs a rotation transformation on the fused target portion of the first-category SAR target dataset to obtain a rotated fused target portion of the first-category SAR target dataset; processes the second-category SAR target dataset using an Anti-CM image fusion strategy to obtain a fused scene portion of the second-category SAR target dataset; and fuses the rotated fused target portion of the first-category SAR target dataset into the fused scene portion of the second-category SAR target dataset using a DCM image fusion strategy, thereby generating a SAR scene target dataset that meets the target scene requirements. Based on the DCM (Double Caster Matrix) image fusion principle, the present invention can fuse different types of SAR target datasets, thereby generating a large number of high-quality SAR image datasets in a relatively short period of time. It can also generate SAR image datasets covering various terrains and landforms, meeting the requirements of different application scenarios. In addition, it is possible to generate SAR image targets of various types, including aircraft, ships, vehicles, and buildings, thus enhancing the practicality of the dataset. The present invention can also easily expand and generate other types of SAR image datasets based on actual needs, facilitating future research.

[0079] It should be noted that the method of the embodiments of the present disclosure can be performed by a single device, such as a computer or server. The method of the embodiments of the present disclosure can also be applied in a distributed scenario, where multiple devices cooperate to perform the method. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiments of the present disclosure, and the multiple devices will interact with each other to complete the method.

[0080] It should be noted that the above description is limited to some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] Example 2

[0082] See also Figure 5Embodiment 2 of the present invention further provides a device for generating a SAR scene target dataset based on environment matching, comprising:

[0083] SAR target data set selection module 001, used to select the first type of SAR target data set and the second type of SAR target data set according to the target scene requirements;

[0084] An image resolution unification module 002 is configured to downsample the resolutions of the first type SAR target dataset and the second type SAR target dataset to form the same resolution;

[0085] The CM image fusion module 003 is configured to process the first-category SAR target dataset using a CM image fusion strategy to obtain a fused target portion of the first-category SAR target dataset; and perform a rotation transformation on the fused target portion of the first-category SAR target dataset to obtain a rotated fused target portion of the first-category SAR target dataset.

[0086] An Anti-CM image fusion module 004 is configured to process the second type of SAR target dataset using an Anti-CM image fusion strategy to obtain a fused scene portion of the second type of SAR target dataset;

[0087] The SAR scene target dataset generation module 005 is configured to fuse the rotated fused target portion of the first type of SAR target dataset into the fused scene portion of the second type of SAR target dataset using a DCM image fusion strategy, thereby generating a SAR scene target dataset that meets the target scene requirements.

[0088] In this embodiment, in the image resolution unification module 002, in the process of performing the downsampling process on the resolutions of the first-category SAR target dataset and the second-category SAR target dataset, if the resolutions of the first-category SAR target dataset and the second-category SAR target dataset are the same, then directly proceed to the next step;

[0089] If the resolutions of the first category SAR target dataset and the second category SAR target dataset are different, the downsampling process is performed to reduce a pixel area in the SAR image to a pixel, so that the high-resolution SAR target dataset is converted into a low-resolution SAR image target dataset to form the same resolution.

[0090] In this embodiment, in the CM image fusion module 003, in the process of obtaining the rotated fused target portion of the first-category SAR target dataset through the CM image fusion strategy, the target portion in the first-category SAR target dataset is cropped and multiplied by the CM matrix to obtain the fused target portion of the first-category SAR target dataset; and the fused target portion of the first-category SAR target dataset is subjected to a rotation transformation to obtain the rotated fused target portion of the first-category SAR target dataset, so that the shadow direction of the rotated fused target portion of the first-category SAR target dataset is consistent with the shadow direction of the fused scene portion of the second-category SAR target dataset.

[0091] In this embodiment, in the Anti-CM image fusion module 004, in the process of obtaining the fused scene portion of the second type of SAR target dataset through the Anti-CM image fusion strategy, the scene portion of the second type of SAR target dataset is cropped and multiplied by the Anti-CM matrix to obtain the fused scene portion of the second type of SAR target dataset.

[0092] In this embodiment, in the SAR scene target dataset generation module 005, the DCM image fusion strategy is: performing computational processing on the data matrix of the fused target portion of the first type of SAR target dataset and the rotated data matrix of the fused target portion of the first type of SAR target dataset to obtain a new data matrix; and replacing the data matrix of the scene portion of the second type of SAR target dataset with the new data matrix to generate a SAR scene target dataset that meets the target scene requirements.

[0093] It should be noted that the information interaction, execution process, etc. between the modules of the above-mentioned system are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown above in the present application, and no further details will be given here.

[0094] Example 3

[0095] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a method for generating a SAR scene target dataset based on environment matching is stored. The program code includes instructions for executing the method for generating a SAR scene target dataset based on environment matching of embodiment 1 or any possible implementation thereof.

[0096] Computer-readable storage media can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available media 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)).

[0097] Example 4

[0098] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0099] The processor and the memory communicate with each other via a bus; the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute a SAR scene target dataset generation method based on environment matching according to embodiment 1 or any possible implementation thereof.

[0100] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor, which is implemented by reading software code stored in a memory. The memory can be integrated into the processor or located outside the processor and exist independently.

[0101] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of 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, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode.

[0102] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing system. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Alternatively, they can be implemented using program code executable by a computing system, and thus, they can be stored in a storage system and executed by the computing system. In some cases, the steps shown or described herein can be performed in a different order than that shown, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0103] Although the present invention has been described in detail above using general descriptions and specific embodiments, it will be apparent to those skilled in the art that modifications and improvements may be made thereto. Therefore, such modifications and improvements, without departing from the spirit of the present invention, are intended to be within the scope of protection claimed herein.

Claims

1. A method for generating a SAR scene target dataset based on environment matching, characterized in that: include: According to the target scene requirements, the first and second category SAR target datasets are selected; Downsampling the resolutions of the first category SAR target dataset and the second category SAR target dataset to form the same resolution; Processing the first type of SAR target data set through a CM image fusion strategy to obtain a fused target portion of the first type of SAR target data set; performing a rotation transformation on the fused target portion of the first-category SAR target data set to obtain a rotated fused target portion of the first-category SAR target data set; Processing the second type of SAR target data set through the Anti-CM image fusion strategy to obtain a fused scene portion of the second type of SAR target data set; By using a DCM image fusion strategy, the rotated fused target portion of the first type of SAR target dataset is fused into the fused scene portion of the second type of SAR target dataset to generate a SAR scene target dataset that meets the target scene requirements; In the process of downsampling the resolutions of the first-category SAR target dataset and the second-category SAR target dataset, if the resolutions of the first-category SAR target dataset and the second-category SAR target dataset are the same, directly proceeding to the next step; If the resolutions of the first category SAR target dataset and the second category SAR target dataset are different, reducing a pixel area in the SAR image to a pixel through the downsampling process, so as to convert the high-resolution SAR target dataset into a low-resolution SAR image target dataset to form the same resolution; In the process of obtaining the rotated fused target portion of the first-category SAR target dataset by processing the CM image fusion strategy, cropping the target portion from the first-category SAR target dataset and multiplying the target portion by the CM matrix to obtain the fused target portion of the first-category SAR target dataset; performing a rotation transformation on the fused target portion of the first-category SAR target dataset to obtain a rotated fused target portion of the first-category SAR target dataset, so that a shadow direction of the rotated fused target portion of the first-category SAR target dataset is consistent with a shadow direction of the fused scene portion of the second-category SAR target dataset; In the process of obtaining the fused scene portion of the second type of SAR target data set through the Anti-CM image fusion strategy, cropping the scene portion of the second type of SAR target data set and multiplying it with the Anti-CM matrix to obtain the fused scene portion of the second type of SAR target data set; The DCM image fusion strategy is: performing calculation processing on the data matrix of the fusion target part of the first type of SAR target data set and the data matrix of the fusion target part of the first type of SAR target data set after rotation to obtain a new data matrix; The new data matrix replaces the data matrix of the scene part of the second type of SAR target data set to generate a SAR scene target data set that meets the target scene requirements.

2. A SAR scene target dataset generation device based on environment matching, using the SAR scene target dataset generation method based on environment matching according to claim 1, characterized in that: include: A SAR target data set selection module is used to select the first type of SAR target data set and the second type of SAR target data set according to the target scene requirements; an image resolution unification module, configured to downsample the resolutions of the first type of SAR target dataset and the second type of SAR target dataset to form the same resolution; a CM image fusion module, configured to process the first type of SAR target data set using a CM image fusion strategy to obtain a fused target portion of the first type of SAR target data set; performing a rotation transformation on the fused target portion of the first-category SAR target data set to obtain a rotated fused target portion of the first-category SAR target data set; An Anti-CM image fusion module is used to process the second type of SAR target dataset through the Anti-CM image fusion strategy to obtain a fused scene part of the second type of SAR target dataset; The SAR scene target dataset generation module is configured to fuse the rotated fused target portion of the first type of SAR target dataset into the fused scene portion of the second type of SAR target dataset through a DCM image fusion strategy, thereby generating a SAR scene target dataset that meets the target scene requirements.

3. The device for generating a SAR scene target dataset based on environment matching according to claim 2, characterized in that: In the image resolution unification module, in the process of performing the downsampling processing on the resolutions of the first category SAR target dataset and the second category SAR target dataset, if the resolutions of the first category SAR target dataset and the second category SAR target dataset are the same, directly proceeding to the next step; If the resolutions of the first category SAR target dataset and the second category SAR target dataset are different, the downsampling process is performed to reduce a pixel area in the SAR image to a pixel, so that the high-resolution SAR target dataset is converted into a low-resolution SAR image target dataset to form the same resolution.

4. The device for generating a SAR scene target dataset based on environment matching according to claim 3, characterized in that: In the CM image fusion module, in the process of obtaining the fused target portion of the rotated first-category SAR target data set through the CM image fusion strategy, the target portion in the first-category SAR target data set is cropped and multiplied by the CM matrix to obtain the fused target portion of the first-category SAR target data set; Performing a rotation transformation on the fused target portion of the first-category SAR target dataset to obtain a rotated fused target portion of the first-category SAR target dataset, so that a shadow direction of the rotated fused target portion of the first-category SAR target dataset is consistent with a shadow direction of the fused scene portion of the second-category SAR target dataset.

5. The device for generating a SAR scene target dataset based on environment matching according to claim 4, characterized in that: In the Anti-CM image fusion module, in the process of obtaining the fused scene portion of the second type of SAR target data set through the Anti-CM image fusion strategy, the scene portion of the second type of SAR target data set is cropped and multiplied by the Anti-CM matrix to obtain the fused scene portion of the second type of SAR target data set.

6. The device for generating a SAR scene target dataset based on environment matching according to claim 5, characterized in that: In the SAR scene target data set generation module, the DCM image fusion strategy is: performing calculation processing on a data matrix of a fusion target portion of the first type of SAR target data set and a data matrix of a fusion target portion of the first type of SAR target data set after rotation to obtain a new data matrix; The new data matrix replaces the data matrix of the scene part of the second type of SAR target data set to generate a SAR scene target data set that meets the target scene requirements.

Images