Wide polarimetric SAR image ship target detection method, system, device, medium and product

Abstract

The invention discloses a wide-range polarized SAR image ship target detection method, system and device, a medium and a product, and relates to the field of image target detection, and the method comprises the steps: obtaining wide-range SAR data; preprocessing the wide SAR data to obtain preprocessed data; performing scattering feature extraction on the preprocessed data to obtain a plurality of SAR images with different scattering features; selecting the SAR image with one scattering characteristic to carry out self-adaptive cutting, and obtaining position information and cutting grids of each cut picture; cutting the SAR images with other scattering characteristics by using the cutting grid to obtain a cut picture; ship target detection is carried out based on the multiple cut pictures, and ship target detection information is obtained; and based on the position information of each cut picture, ship target detection information is mapped to the wide SAR image. According to the method, the image can be adaptively cut on the premise that the ship target is not damaged, and the real-time performance and the accuracy of SAR image ship target detection are improved.

Description

Technical Field

[0001] The present application relates to the field of image target detection, and in particular to a method, system, equipment, medium and product for detecting ship targets in wide-band polarimetric SAR images. Background Art

[0002] Synthetic Aperture Radar (SAR) is an active microwave imaging sensor that has the ability to work all day and all weather, and has good adaptability to monitoring the ocean with unpredictable climate. Fully polarized SAR can simultaneously receive and transmit electromagnetic waves in multiple polarization states, so that the measured data is no longer just the radar cross section (RCS) of the radar target, but a 2×2 scattering matrix, and the target scattering information obtained is richer. How to effectively use different scattering information for real-time detection of ship targets is one of the hot topics in current ship target research. In addition, since the pixels of wide-band SAR images are too large to input the entire image into the network for detection, how to adaptively crop the image without destroying the ship target is also a difficulty and focus of wide-band polarized SAR image detection target detection. Summary of the invention

[0003] The purpose of this application is to provide a wide-band polarimetric SAR image ship target detection method, system, equipment, medium and product, which can adaptively crop images without destroying the ship target, thereby improving the real-time and accuracy of SAR image ship target detection.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for detecting ship targets in wide-band polarimetric SAR images, comprising:

[0006] Acquire wide-band SAR data;

[0007] Preprocessing the wide-width SAR data to obtain preprocessed data;

[0008] Extracting scattering features from the preprocessed data to obtain a plurality of SAR images with different scattering features;

[0009] Select one of the SAR images with scattering characteristics for adaptive cropping, and obtain the position information of each cropped image and the SAR image cropping grid;

[0010] SAR images of other scattering features are cropped based on the cropping grid to obtain multiple cropped images of SAR data with different scattering features at the same location;

[0011] Perform ship target detection based on the plurality of cropped images to obtain ship target detection information; the ship target detection information includes ship target category, ship target border and ship target location information;

[0012] The ship target detection information is mapped onto the wide-width SAR image based on the position information of each of the cropped images.

[0013] Optionally, a SAR image with one of the scattering characteristics is selected for adaptive cropping, and position information of each cropped image and a SAR image cropping grid are obtained, specifically including:

[0014] Using a clustering algorithm to perform clustering processing on one of the SAR images with scattering characteristics to obtain a clustered image; the clustered image includes a plurality of clustered targets;

[0015] Determining the border position information of each cluster target in the cluster image;

[0016] Generating a cropping grid according to the original size of the wide-width SAR image and a set cropping size;

[0017] Taking a boundary point in the cluster image as an origin, setting a boundary line of the cropping grid with the origin as a vertex to 0, and taking a line in the cropping grid that is parallel to and adjacent to the boundary line as a cropping line;

[0018] Using the cropping grid to crop the cluster image, and during the cropping process, determining whether there is a cluster target on the cropping line;

[0019] If there is a cluster target on the clipping line, traverse all cluster targets on the clipping line, and determine the position information of the cluster target closest to the boundary line of the clipping grid among the cluster targets;

[0020] Determine an offset based on position information of a cluster target closest to a boundary line of the clipping grid;

[0021] After offsetting the clipping grid along the clipping line toward the boundary line of the clipping grid by the offset amount, updating the clipping grid and completing clipping;

[0022] If there is no cluster target on the clipping line, the clipping grid is directly used to complete the clipping.

[0023] Optionally, performing ship target detection based on the plurality of cropped images to obtain ship target detection information specifically includes:

[0024] Constructing a ship target detection network; the ship target detection network includes: a multi-channel convolutional attention network module, a multi-scale convolutional attention network module and a hybrid encoder module;

[0025] Inputting the plurality of cropped images and the position information of each cropped image into the ship target detection network to obtain initial information for ship target detection; the initial information for ship target detection includes a plurality of prediction frame encoding information; the prediction frame encoding information includes: predicted target category, predicted frame and predicted target position information;

[0026] Adopting an uncertain minimization query and selection method, selecting the first j prediction box encoding information from the prediction box encoding information of the initial information of the ship target detection;

[0027] The first j prediction frame encoding information is decoded to obtain the ship target detection information.

[0028] Optionally, inputting the plurality of cropped images and the position information of each cropped image into the ship target detection network to obtain initial information of ship target detection specifically includes:

[0029] Inputting the plurality of cropped images and the position information of each of the cropped images into the multi-channel convolutional attention network module to obtain a first feature;

[0030] Inputting the first feature into the multi-scale convolutional attention network module to obtain a second feature; the second feature includes a first sub-feature, a second sub-feature and a third sub-feature;

[0031] The second feature is input into the hybrid encoder module to obtain the initial information of the ship target detection.

[0032] Optionally, inputting the second feature into the hybrid encoder module to obtain the initial information of the ship target detection specifically includes:

[0033] In the hybrid encoder module, flattening the third sub-feature into a one-dimensional feature vector;

[0034] The one-dimensional feature vector is encoded by a multi-head attention mechanism to achieve intra-scale feature interaction;

[0035] Convert the one-dimensional feature vector encoded by the multi-head attention mechanism into a two-dimensional vector;

[0036] The first sub-feature, the second sub-feature and the two-dimensional vector are bidirectionally fused and spliced ​​to output, so as to obtain the initial information of the ship target detection.

[0037] Optionally, a multi-branch convolution structure RepBlock module is set in the hybrid encoder module; the multi-branch convolution structure RepBlock module is used to perform bidirectional feature fusion on the first sub-feature, the second sub-feature and the two-dimensional vector.

[0038] In a second aspect, the present application provides a wide-band polarimetric SAR image ship target detection system, which is used to implement the wide-band polarimetric SAR image ship target detection method provided above; the wide-band polarimetric SAR image ship target detection system includes:

[0039] Polarimetric SAR data acquisition module, used to acquire wide-band SAR data;

[0040] A wide-width SAR image ship target adaptive cropping module is connected to the polarization SAR data acquisition module and is used to preprocess the wide-width SAR data to obtain preprocessed data, extract scattering features from the preprocessed data to obtain a plurality of SAR images with different scattering features, obtain cropped images, and obtain position information of the cropped images;

[0041] The SAR ship target real-time detection module is connected to the wide-width SAR image ship target adaptive cropping module, and is used to perform ship target detection based on the cropped image to obtain ship target detection information, and is used to map the ship target detection information to the wide-width SAR image based on the position information of each cropped image; the ship target detection information includes the ship target category, the ship target border and the position information of the ship target.

[0042] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for ship target detection in wide-band polarization SAR images provided above.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for detecting ship targets in wide-band polarization SAR images.

[0044] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for detecting ship targets in wide-band polarization SAR images.

[0045] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0046] The present application provides a method, system, device, medium and product for ship target detection in wide-width polarimetric SAR images. By extracting scattering features from SAR data, SAR images with different scattering features can be obtained, thereby obtaining richer scattering information, and adaptively cropping SAR images with different scattering features, the image can be adaptively cropped without destroying the ship target. Ship target detection is performed based on multiple cropped images with different scattering features and the position information of each cropped image, and ship target detection information is obtained, and the ship target detection information is mapped to a wide-width SAR image, which can improve the real-time and accuracy of SAR image ship target detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 This is an application environment diagram of a wide-band polarimetric SAR image ship target detection method in one embodiment of the present application;

[0049] Figure 2 A schematic diagram of a flow chart of a method for detecting ship targets in wide-band polarimetric SAR images provided in one embodiment of the present application;

[0050] Figure 3 A schematic diagram of the preprocessing and adaptive cropping process provided in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of a ship target detection process provided by another embodiment of the present application;

[0052] Figure 5 A schematic diagram of the structure of a multi-channel convolutional attention network module provided in one embodiment of the present application;

[0053] Figure 6 A schematic diagram of the structure of a multi-scale attention network module provided in an embodiment of the present application;

[0054] Figure 7 A schematic diagram of the structure of a hybrid encoder module provided in one embodiment of the present application;

[0055] Figure 8 A schematic diagram of the module functions of a wide-band polarimetric SAR image ship target detection system provided in one embodiment of the present application;

[0056] Fig. 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0059] The wide-band polarimetric SAR image ship target detection method provided in the embodiment of the present application can be applied to the following applications: Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send wide-width SAR data to the server 104. After receiving the wide-width SAR data, the server 104 pre-processes the wide-width SAR data to obtain pre-processed data. The pre-processed data is subjected to scattering feature extraction to obtain multiple SAR images with different scattering features; a SAR image with one scattering feature is selected for adaptive cropping, and the position information of each cropped image and the SAR image cropping grid are obtained; the SAR images with other scattering features are cropped based on the cropping grid to obtain multiple cropped images with different scattering features of the SAR data at the same position. Ship target detection is performed based on the cropped images with multiple different scattering features to obtain ship target detection information. The ship target detection information is mapped to the wide-width SAR image based on the position information of each cropped image. The server 104 can feed back the obtained wide-width SAR image mapped with ship target detection information to the terminal 102. In addition, in some embodiments, the wide-width polarization SAR image ship target detection method provided in the present application can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly perform ship target detection on the wide-width SAR image, or the server 104 can obtain the wide-width SAR image from the data storage system and perform ship target detection on the wide-width SAR image.

[0060] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0061] In an exemplary embodiment, Figure 2 As shown, a method for detecting ship targets in wide-band polarimetric SAR images is provided. The method is executed by a computer device, and specifically can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 200 to 206.

[0062] in:

[0063] Step 200: Acquire wide-band SAR data.

[0064] Step 201: preprocess the wide-band SAR data to obtain preprocessed data.

[0065] Step 202: extract scattering features from the preprocessed data to obtain a plurality of SAR images with different scattering features.

[0066] Step 203: adaptively cropping the SAR image of one of the scattering characteristics, and obtaining the position information of each cropped image and the SAR image cropping grid;

[0067] Step 204: cropping SAR images of other scattering features based on the cropping grid to obtain a plurality of cropped images of SAR data of the same position with different scattering features.

[0068] Step 205: Perform ship target detection based on the multiple cropped images to obtain ship target detection information. The ship target detection information includes ship target category, ship target border and ship target position information.

[0069] Step 206: Mapping the ship target detection information onto the wide-width SAR image based on the position information of each cropped image.

[0070] By implementing the above steps 200 to 206, the image can be adaptively cropped without destroying the ship target, thereby improving the real-time and accuracy of ship target detection in SAR images.

[0071] In another exemplary embodiment of the present application, since the image data (i.e., wide-width SAR image) generated by wide-width SAR imaging data is usually very large and cannot be directly input into the detection network for target detection, image cropping is required before target detection. Most of the existing cropping methods are cropped by fixed size, such as 512*512, but these existing cropping methods will destroy the detection target, resulting in missed detection or false detection. In order to solve this problem, the present application performs adaptive cropping on the SAR image in step 203 to avoid damaging the detection target. In actual application, the implementation process of step 203 can be described as:

[0072] Step 2031: clustering the SAR image with one scattering feature using a clustering algorithm to obtain a cluster image. The cluster image includes multiple cluster targets.

[0073] Step 2032: Determine the border position information of each cluster target in the cluster image.

[0074] Step 2033: Generate a cropping grid according to the original size of the wide-width SAR image and the set cropping size.

[0075] Step 2034: Taking a boundary point in the cluster image as the origin, setting the boundary line of the cropping grid with the origin as the vertex to 0, and taking the lines in the cropping grid that are parallel to and adjacent to the boundary line as the cropping lines.

[0076] Step 2035: Use a cropping grid to crop the cluster image, and during the cropping process, determine whether there is a cluster target on the cropping line.

[0077] Step 2036: If there is a cluster target on the cutting line, traverse all cluster targets on the cutting line and determine the position information of the cluster target closest to the boundary line of the cutting grid among these cluster targets.

[0078] Step 2037: Determine the offset based on the position information of the cluster target closest to the boundary line of the clipping grid.

[0079] Step 2038: After the clipping grid is offset along the clipping line toward the boundary line of the clipping grid by the offset amount, the clipping grid is updated and clipping is completed.

[0080] Step 2039: If there is no cluster target on the clipping line, clipping is completed directly using the clipping grid.

[0081] In another exemplary embodiment of the present application, since the collected wide-width SAR image has certain sea clutter and other noise, in order to minimize the impact of noise on target detection, preprocessing is required to improve image quality. Taking adaptive cropping along the x-axis and y-axis of the position information as an example, Figure 3As shown, the specific implementation process of step 202 and step 203 can be described as:

[0082] The collected wide-band SAR images are complex data. In order to segment the images, the complex data are converted into intensity data to generate grayscale images. The target area is white with a pixel value of 255, and the background area is black with a pixel value of 0. The size of the grayscale image is (n, m), where n represents length and m represents width.

[0083] After the grayscale image is generated, there may still be Gaussian noise in the grayscale image. For example, if the target area is interspersed with individual background pixels 0, or the background area is interspersed with individual target pixels 255, the area will be continuous. Therefore, morphological opening and closing operations are used to process the image to remove noise and interference in the grayscale image and improve the image quality.

[0084] Using the clustering algorithm, the border position of each cluster target in the denoised grayscale image is obtained, such as (P x1 ,P y1 ,P x2 ,P y2 ). For example, clustering algorithms such as k-means are used to cluster the target area and calculate the border position information of each cluster target. x1 ,P y1 ) is the coordinate of the upper left point of the grayscale image after denoising, (P x2 ,P y2 ) is the coordinate of the lower right point of the grayscale image after denoising.

[0085] Generate a cropping grid based on the original wide-width SAR image size and the preset cropping size. In the process of generating the cropping grid, if there are decimals, they are rounded down.

[0086] With the denoised grayscale image as the origin, define the coordinates of the cropping grid. The cropping grid coordinates can be defined as: The purpose of this processing is to adjust the clipping coordinates later to achieve adaptive clipping.

[0087] Define the leftmost and topmost boundary lines of the clipping grid as 0, then set i, j = 1 and start clipping from the second line of the grid.

[0088] When using the clipping grid for vertical clipping, the judgment is made from left to right. For example, if there are cluster targets on the second vertical clipping line of the clipping grid, all cluster targets on the clipping line are found, and the leftmost coordinate x of these cluster targets is calculated. min , then the second coordinate point x in the clipping grid a , a∈[i,n / S] to the last coordinate point are offset to the left by xa -x min , that is, subtract x from the clipping grid coordinates one by one a -x min This cycle is repeated until there is no cropping of clustering targets in the vertical direction. Where n represents the original image size and S represents the cropped image size.

[0089] Furthermore, the horizontal cropping idea is the same as the vertical cropping idea. The horizontal cropping is performed from top to bottom to ensure that the cluster targets are not cropped in the horizontal direction. For the specific process, see Figure 3 As shown, no further description is given here.

[0090] In another exemplary embodiment of the present application, by using different decomposition features (i.e., the cropped images obtained by the above cropping), more abundant scattering information can be obtained. By analyzing a variety of scattering information, it is helpful to improve the accuracy and robustness of ship target detection. Based on this, in the above step 205 of the present application, the inference network can be used to detect ship targets on multiple cropped images. Specifically, Figure 4 As shown, the implementation process of step 204 can be described as:

[0091] (1) Construct a ship target detection network (i.e., inference network). The ship target detection network includes: a multi-channel convolutional attention network module, a multi-scale convolutional attention network module, and a hybrid encoder module.

[0092] (2) Input multiple cropped images and the position information of each cropped image into the ship target detection network to obtain the initial information of ship target detection. The initial information of ship target detection includes multiple prediction box information. The prediction box information includes: predicted target category, predicted frame and predicted target position information. Among them:

[0093] (2-1) Input multiple cropped images and the position information of each cropped image into the multi-channel convolutional attention network module to obtain the first feature. For example, Figure 5 As shown, each decomposed feature (i.e., cropped image) is processed by the CBS1 module, and then the channel attention mechanism is used to perform attention mechanism modeling on different scattered features of the input. Figure 5 In the figure, the processing flow of the CBS1 module is: Conv1×1s1-->BN-->Silu. Conv1×1 is a 1×1 convolution. s1 is the step size 1. BN stands for BatchNormalization, which means batch normalization. Silu is the Silu activation function.

[0094] (2-2) Input the first feature into the multi-scale convolutional attention network module to obtain the second feature. The second feature includes the first sub-feature, the second sub-feature and the third sub-feature.

[0095] In actual application, due to the large difference in the size of the detection target, such as the size of an aircraft carrier is more than ten times or even hundreds of times larger than that of a fishing boat, a multi-scale attention network module is used to extract features of different scales. In this embodiment, a three-layer multi-scale convolutional attention network module (MSANet1, MSANet2 and MSANet3) is used to extract features of different depths, respectively. The features of different depths are the first sub-feature, the second sub-feature and the third sub-feature, which are respectively recorded as S5, S4 and S3.

[0096] like Figure 6 As shown in the figure, in MSANet, a large-scale feature convolution kernel K1 is first used to capture large target features. Large-scale feature convolution kernel K1 represents a large convolution kernel, such as 7*7, with a large receptive field. Small-scale feature convolution kernel K2 is used to capture small target features. Small-scale feature convolution kernel K2, such as 3*3, has a relatively small receptive field. Then, through the spatial attention mechanism, MSANet adaptively adjusts the spatial attention according to the detection target needs.

[0097] (2-3) Input the second feature into the hybrid encoder module to obtain the initial information of ship target detection. Figure 7 In the hybrid encoder module structure shown, first, the third sub-feature S5 is flattened into a one-dimensional feature vector using formula (1). Then, the one-dimensional feature vector is encoded using a multi-head attention mechanism using formula (2) to achieve intra-scale feature interaction. Subsequently, the one-dimensional feature vector encoded by the multi-head attention mechanism is converted into a two-dimensional vector F. Finally, the first sub-feature S3, the second sub-feature S4 and the two-dimensional feature vector F are bidirectionally fused using formula (3) and then spliced ​​and output. For example, a multi-branch convolutional structure RepBlock module is used to deeply fuse features of different layers.

[0098] Among them, the relevant processing formula of the hybrid encoder module is expressed as:

[0099] Q=K=V=Flatten(S5) (1)

[0100] F = Reshape(Attn(Q,K,V)) (2)

[0101] Output=Fusion({S3,S4,F}) (3)

[0102] In the formula, Flatten represents flattening, Q, K, V all represent one-dimensional feature vectors, Reshape(Attn()) represents multi-head attention mechanism encoding, Fusion represents bidirectional feature fusion and splicing, and Output represents output.

[0103] (3) The uncertain minimization query and selection method is used to select the first j prediction box encoding information from the prediction box encoding information of the initial information of ship target detection.

[0104] (4) Decode the encoded information of the first j prediction boxes to obtain the ship target detection information.

[0105] In another exemplary embodiment of the present application, in the above step 204, a certain number of coding prediction frames can be generated according to the result of the hybrid encoder module. In order to improve the pertinence of the coding prediction frame, Figure 4 As shown, the uncertainty minimization query and selection method can be used to select the first j coding prediction boxes from the i coding prediction boxes, thereby improving the detection speed.

[0106] Decode the encoded prediction box and obtain the detected target category, bounding box, and location information.

[0107] Based on the same inventive concept, the embodiment of the present application also provides a wide-width polarimetric SAR image ship target detection system for implementing the wide-width polarimetric SAR image ship target detection method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more wide-width polarimetric SAR image ship target detection system embodiments provided below can refer to the limitations of the wide-width polarimetric SAR image ship target detection method above, and will not be repeated here.

[0108] In an exemplary embodiment, Figure 8 As shown, a wide-band polarimetric SAR image ship target detection system is provided, comprising:

[0109] Polarimetric SAR data acquisition module, used to acquire wide-band SAR data;

[0110] The wide-width SAR image ship target adaptive cropping module is connected to the polarimetric SAR data acquisition module, and is used to preprocess the wide-width SAR data to obtain preprocessed data, extract scattering features from the preprocessed data, obtain multiple SAR images with different scattering features, obtain cropped images, and obtain position information of the cropped images.

[0111] The SAR ship target real-time detection module is connected to the wide-width SAR image ship target adaptive cropping module, and is used to detect ship targets based on the cropped images, obtain ship target detection information, and map the ship target detection information to the wide-width SAR image based on the position information of each cropped image. The ship target detection information includes the ship target category, the ship target border, and the ship target position information.

[0112] As an optional implementation, the polarimetric SAR data acquisition module acquires polarimetric SAR data from the SAR sensor, thereby obtaining a wide-width SAR image.

[0113] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store ship target detection data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a ship target detection method for a wide-band polarization SAR image is implemented.

[0114] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0115] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0116] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0117] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0118] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0119] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0120] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A ship target detection method for wide-band polarimetric SAR images, characterized in that: The wide-band polarimetric SAR image ship target detection method comprises: Acquire wide-band SAR data; Preprocessing the wide-width SAR data to obtain preprocessed data; Extracting scattering features from the preprocessed data to obtain a plurality of SAR images with different scattering features; Select one of the SAR images with scattering characteristics for adaptive cropping, and obtain the position information of each cropped image and the SAR image cropping grid; SAR images of other scattering features are cropped based on the cropping grid to obtain multiple cropped images of SAR data with different scattering features at the same location; Perform ship target detection based on the plurality of cropped images to obtain ship target detection information; the ship target detection information includes ship target category, ship target border and ship target location information; The ship target detection information is mapped onto the wide-width SAR image based on the position information of each of the cropped images.

2. The ship target detection method of wide-band polarimetric SAR image according to claim 1, characterized in that: Select one of the SAR images with scattering characteristics for adaptive cropping, and obtain the location information of each cropped image and the SAR image cropping grid, specifically including: Using a clustering algorithm to perform clustering processing on one of the SAR images with scattering characteristics to obtain a clustered image; the clustered image includes a plurality of clustered targets; Determining the border position information of each cluster target in the cluster image; Generating a cropping grid according to the original size of the wide-width SAR image and a set cropping size; Taking a boundary point in the cluster image as an origin, setting a boundary line of the cropping grid with the origin as a vertex to 0, and taking a line in the cropping grid that is parallel to and adjacent to the boundary line as a cropping line; Using the cropping grid to crop the cluster image, and during the cropping process, determining whether there is a cluster target on the cropping line; If there is a cluster target on the clipping line, traverse all cluster targets on the clipping line, and determine the position information of the cluster target closest to the boundary line of the clipping grid among the cluster targets; Determine an offset based on position information of a cluster target closest to a boundary line of the clipping grid; After offsetting the clipping grid along the clipping line toward the boundary line of the clipping grid by the offset amount, updating the clipping grid and completing clipping; If there is no cluster target on the clipping line, the clipping grid is directly used to complete the clipping.

3. The ship target detection method of wide-band polarimetric SAR image according to claim 1, characterized in that: Ship target detection is performed based on the plurality of cropped images to obtain ship target detection information, specifically including: Constructing a ship target detection network; the ship target detection network includes: a multi-channel convolutional attention network module, a multi-scale convolutional attention network module and a hybrid encoder module; Inputting the plurality of cropped images and the position information of each cropped image into the ship target detection network to obtain initial information for ship target detection; the initial information for ship target detection includes a plurality of prediction frame encoding information; the prediction frame encoding information includes: predicted target category, predicted frame and predicted target position information; Adopting an uncertain minimization query and selection method, selecting the first j prediction box encoding information from the prediction box encoding information of the initial information of the ship target detection; The first j prediction frame encoding information is decoded to obtain the ship target detection information.

4. The ship target detection method of wide-band polarimetric SAR image according to claim 3 is characterized in that: Inputting the plurality of cropped images and the position information of each cropped image into the ship target detection network to obtain initial information of ship target detection specifically includes: Inputting the plurality of cropped images and the position information of each of the cropped images into the multi-channel convolutional attention network module to obtain a first feature; Inputting the first feature into the multi-scale convolutional attention network module to obtain a second feature; the second feature includes a first sub-feature, a second sub-feature and a third sub-feature; The second feature is input into the hybrid encoder module to obtain the initial information of the ship target detection.

5. The ship target detection method of wide-band polarimetric SAR image according to claim 4, characterized in that: Inputting the second feature into the hybrid encoder module to obtain the initial information of ship target detection specifically includes: In the hybrid encoder module, flattening the third sub-feature into a one-dimensional feature vector; The one-dimensional feature vector is encoded by a multi-head attention mechanism to achieve intra-scale feature interaction; Convert the one-dimensional feature vector encoded by the multi-head attention mechanism into a two-dimensional vector; The first sub-feature, the second sub-feature and the two-dimensional vector are bidirectionally fused and spliced ​​to output, so as to obtain the initial information of the ship target detection.

6. The ship target detection method of wide-band polarimetric SAR image according to claim 5, characterized in that: A multi-branch convolution structure RepBlock module is set in the hybrid encoder module; A multi-branch convolution structure RepBlock module is used to perform bidirectional feature fusion on the first sub-feature, the second sub-feature and the two-dimensional vector.

7. A wide-band polarimetric SAR image ship target detection system, characterized in that: The wide-band polarimetric SAR image ship target detection system is used to implement the wide-band polarimetric SAR image ship target detection method according to any one of claims 1 to 6; The wide-band polarimetric SAR image ship target detection system comprises: Polarimetric SAR data acquisition module, used to acquire wide-band SAR data; A wide-width SAR image ship target adaptive cropping module is connected to the polarization SAR data acquisition module and is used to preprocess the wide-width SAR data to obtain preprocessed data, extract scattering features from the preprocessed data to obtain a plurality of SAR images with different scattering features, adaptively crop the wide-width SAR image to obtain a cropped image, and obtain position information of the cropped image; The SAR ship target real-time detection module is connected to the wide-width SAR image ship target adaptive cropping module, and is used to perform ship target detection based on the cropped image to obtain ship target detection information, and is used to map the ship target detection information to the wide-width SAR image based on the position information of each cropped image; the ship target detection information includes the ship target category, the ship target border and the position information of the ship target.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the wide-band polarimetric SAR image ship target detection method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting ship targets in wide-band polarimetric SAR images according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for detecting ship targets in wide-band polarimetric SAR images according to any one of claims 1 to 6 is implemented.

Images