Oil spill detection method, device and equipment based on polarimetric SAR imagery

Abstract

The present invention relates to the technical field of oil spill detection, and more particularly to an oil spill detection method based on polarimetric SAR images. The method comprises: acquiring a polarimetric SAR image of a target area, wherein the polarimetric SAR image includes a suspected oil spill area and a clean area; extracting target polarimetric features from the polarimetric features of the polarimetric SAR image, inputting the target polarimetric features into a preset detection model, performing several training cycles, and acquiring a target oil spill detection model; and responding to a detection instruction, wherein the detection instruction includes a polarimetric SAR image of the area to be detected, and acquiring an oil spill detection result output by the target oil spill detection model based on the polarimetric SAR image of the area to be detected and the target oil spill detection model. The method can effectively filter suspected oil spills from the polarimetric SAR image while achieving oil spill extraction, thereby reducing polarimetric feature redundancy and improving oil spill detection accuracy and oil film classification accuracy, thereby achieving rapid and effective detection of oil spills.

Description

Technical Field

[0001] The present invention relates to the technical field of oil spill detection, and in particular to an oil spill detection method, device, equipment and storage medium based on polarization SAR images. Background Art

[0002] Marine oil spills cause serious damage to the marine ecological environment and result in significant economic losses. After an oil spill occurs, a fast and effective method is needed to identify and detect the spill and obtain real-time information on the spill.

[0003] Most existing polarimetric SAR-based oil spill detection and classification technologies rely on a single polarization signature. However, this single polarization signature parameter is not universally applicable and cannot simultaneously identify the target oil spill area and distinguish suspected oil spills. This makes it difficult to quickly and effectively detect oil spills, enabling timely response and resource allocation for subsequent cleanup efforts, resulting in economic losses. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide an oil spill detection method, device, equipment and storage medium based on polarization SAR images. By comparing and analyzing polarization features, polarization features with optimal oil spill detection and classification performance are screened out, which can effectively filter suspected oil spills in polarization SAR images while achieving oil spill extraction. This can not only reduce polarization feature redundancy, but also improve oil spill detection accuracy and oil film classification accuracy, thereby achieving rapid and effective detection of oil spill conditions.

[0005] In a first aspect, an embodiment of the present application provides an oil spill detection method based on polarimetric SAR images, comprising the following steps:

[0006] Acquire a polarimetric SAR image of the target area, wherein the polarimetric SAR image includes a suspected oil spill area and a clean area;

[0007] Obtaining polarization features of the polarization SAR image, extracting target polarization features from the polarization features of the polarization SAR image, inputting the target polarization features into a preset detection model, performing several training cycles, and obtaining a target oil spill detection model, wherein the target polarization features include oil spill detection features and oil film classification features;

[0008] In response to a detection instruction, the detection instruction includes a polarimetric SAR image of the area to be detected, and according to the polarimetric SAR image of the area to be detected and a target oil spill detection model, an oil spill detection result output by the target oil spill detection model is acquired.

[0009] In a second aspect, an embodiment of the present application provides an oil spill detection device based on polarimetric SAR images, comprising:

[0010] An acquisition module, configured to acquire a polarimetric SAR image of a target area, wherein the polarimetric SAR image includes a suspected oil spill area and a clean area;

[0011] a training module, configured to obtain polarization features of the polarimetric SAR image, extract target polarization features from the polarimetric SAR image, input the target polarization features into a preset detection model, perform several training cycles, and obtain a target oil spill detection model, wherein the target polarization features include oil spill detection features and oil film classification features;

[0012] The detection module is configured to respond to a detection instruction, wherein the detection instruction includes a polarimetric SAR image of the area to be detected, and obtain an oil spill detection result output by the target oil spill detection model based on the polarimetric SAR image of the area to be detected and a target oil spill detection model.

[0013] In a third aspect, an embodiment of the present application provides a computer device comprising: a processor, a memory, and a computer program stored on the memory and executable on the processor; when the computer program is executed by the processor, the steps of the oil spill detection method based on polarization SAR images as described in the first aspect are implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the oil spill detection method based on polarization SAR images as described in the first aspect.

[0015] In an embodiment of the present application, a method, apparatus, device, and storage medium for oil spill detection based on polarimetric SAR images are provided. By comparing and analyzing polarimetric features, polarimetric features with optimal oil spill detection and classification performance are screened out. This method can effectively filter suspected oil spills in polarimetric SAR images while achieving oil spill extraction. This method not only reduces polarimetric feature redundancy but also improves the accuracy of oil spill detection and oil film classification, thereby enabling rapid and effective detection of oil spills.

[0016] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of an oil spill detection method based on polarimetric SAR images provided in the first embodiment of the present application;

[0018] Figure 2 This is a flow chart of step S2 in the oil spill detection method based on polarimetric SAR images provided in the first embodiment of the present application;

[0019] Figure 3This is a flow chart of step S2 in the oil spill detection method based on polarimetric SAR images provided in the second embodiment of the present application;

[0020] Figure 4 This is a flow chart of step S2 in the oil spill detection method based on polarimetric SAR images provided in the third embodiment of the present application;

[0021] Figure 5 A schematic structural diagram of an oil spill detection device based on polarimetric SAR images provided in the fourth embodiment of the present application;

[0022] Figure 6 A schematic structural diagram of a computer device provided in the fifth embodiment of the present application. DETAILED DESCRIPTION

[0023] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0024] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words "if" / "if" as used herein may be interpreted as "at the time of" or "when" or "in response to a determination."

[0026] See also Figure 1 , Figure 1 This is a flow chart of an oil spill detection method based on polarimetric SAR images provided in the first embodiment of the present application. The method comprises the following steps:

[0027] S1: Acquire a polarimetric SAR image of the target area.

[0028] The executor of the oil spill detection method based on polarimetric SAR images is a detection device for the oil spill detection method based on polarimetric SAR images (hereinafter referred to as the detection device). In an optional embodiment, the detection device can be a computer device, a server, or a server cluster composed of multiple computer devices.

[0029] The polarimetric SAR image is a satellite remote sensing image acquired by synthetic aperture radar (SAR) through polarization, and can be a multi-temporal ALOS radar image or a Landsat multispectral image. The ALOS radar image is remote sensing data acquired based on high-resolution synthetic aperture radar satellites, and the Landsat multispectral image is remote sensing data acquired based on the LANDSAT series of satellites.

[0030] Before obtaining the polarization features of the polarimetric SAR image, since most polarimetric SAR images are single-view complex images, the azimuth resolution and range resolution are different, resulting in a narrow and long image and difficulty in identifying oil spill information. Therefore, it is necessary to perform multi-view processing on the polarimetric SAR image along the azimuth direction to make the azimuth resolution and range resolution consistent, and simultaneously use a filter to perform noise reduction processing to obtain the processed polarimetric SAR image;

[0031] In this embodiment, the detection device can obtain the polarimetric SAR image of the target area through a radar remote sensing system, or can establish a data connection with a preset network database to obtain the polarimetric SAR image of the target area from the network database.

[0032] The polarimetric SAR image includes a suspected oil spill area and a clean area. When an oil spill occurs, the spilled oil will mix with other oily substances on the sea surface. The suspected oil spill area includes a non-target oil spill target area and an oil spill target area. The non-target oil spill target area is an area containing oily substances of other oily natures different from the spilled oil, and the oil spill target area is an area containing the spilled oil.

[0033] S2: Obtain polarization features of the polarization SAR image, extract target polarization features from the polarization features of the polarization SAR image, input the target polarization features into a preset detection model, perform several trainings, and obtain a target oil spill detection model.

[0034] The oil film suppresses the generation of capillary waves and short gravity waves, making the sea surface smoother. The smooth sponge reduces the backscattering of radar waves in the sponge, resulting in the oil-contaminated area in the SAR image showing dark shadow characteristics.

[0035] In this embodiment, the detection device analyzes the backscatter coefficient of the polarimetric SAR image, and performs polarimetric decomposition on the polarimetric SAR image based on the backscatter coefficient to obtain polarimetric features of the polarimetric SAR image, wherein the polarimetric features include a reduced polarimetric base station height feature, an even-order scattering feature, an odd-order scattering feature, a volume scattering feature, a roundness feature, a relative phase feature, a polarization degree feature, a circular level feature, a circular polarization degree feature, a circular polarization ratio feature, a linear level feature, a linear polarization ratio feature, a contrast feature, an ellipse azimuth feature, an ellipse angle feature, an average scattering angle feature, an anisotropy index feature, a reduced polarization entropy feature, and a total power feature.

[0036] To effectively filter suspected oil spill areas from the polarimetric SAR image while simultaneously extracting target oil spill areas, in this embodiment, the detection device extracts target polarimetric features from the polarimetric features of the polarimetric SAR image. These target polarimetric features are then fed into a pre-set detection model, which is trained several times to obtain a target oil spill detection model. The target polarimetric features include oil spill detection features and oil slick classification features. The oil spill detection features are used to detect suspected oil spill areas in the polarimetric SAR image, while the oil slick classification features are used to distinguish target oil spill areas from non-target oil spill areas within the suspected oil spill area.

[0037] See also Figure 2 , Figure 2 The flowchart of S2 in the oil spill detection method based on polarimetric SAR images provided in the first embodiment of the present application includes steps S201 to S203, which are specifically as follows:

[0038] S201: extracting images of a suspected oil spill area and a clean area from the polarimetric SAR image as a first sample image and a second sample image, respectively, and obtaining polarimetric features corresponding to the first sample image and the second sample image.

[0039] In this embodiment, the detection device extracts images of the suspected oil spill area and the clean area from the polarimetric SAR image, uses the suspected oil spill area as a first sample image and the clean area as a second sample image, and obtains polarization features corresponding to the first sample image and polarization features corresponding to the second sample image, wherein the polarization features corresponding to the first sample image include polarization features corresponding to the oil spill target area and polarization features corresponding to the non-target oil spill target area.

[0040] S202: Calculate a first Euclidean distance of each polarization feature according to the polarization features of the first sample image and the second sample image, and obtain the oil spill detection feature according to the first Euclidean distance.

[0041] In this embodiment, the detection device uses the polarization feature of the first sample image as the first selected sample and the polarization feature of the second sample image as the second selected sample, obtains the mean and variance of the first selected sample and the second selected sample, and inputs them into a preset Euclidean distance calculation algorithm. The first Euclidean distance between the polarization feature corresponding to the oil spill target area and the polarization feature corresponding to the clean area, and the first Euclidean distance between the polarization feature corresponding to the non-target oil spill target area and the polarization feature corresponding to the clean area are calculated for each polarization feature, and the polarization feature corresponding to the largest first Euclidean distance is used as the oil spill detection feature. The Euclidean distance calculation algorithm is as follows:

[0042]

[0043] Where m1 is the mean of the first selected samples, m2 is the mean of the second selected samples, σ1 is the variance of the first selected samples, and σ2 is the variance of the second selected samples. This improves the accuracy and efficiency of oil spill detection.

[0044] S203: Calculating a second Euclidean distance of each polarization feature according to the polarization feature corresponding to the first sample image, and obtaining the oil film classification feature according to the second Euclidean distance.

[0045] In this embodiment, the detection device uses the polarization features corresponding to the oil spill target area in the first sample image as the first selected sample, and the polarization features corresponding to the non-target oil spill target area as the second selected sample. The means and variances of the first selected samples and the second selected samples are obtained and input into a preset Euclidean distance calculation algorithm. The second Euclidean distance between the polarization features corresponding to the oil spill target area and the polarization features corresponding to the non-target oil spill target area under each polarization feature is calculated. The polarization feature corresponding to the largest second Euclidean distance is used as the oil film classification feature to improve the accuracy and efficiency of oil film classification.

[0046] See also Figure 3 , Figure 3 The flowchart of step S2 in the oil spill detection method based on polarimetric SAR images provided in the second embodiment of the present application further includes step S204, which is as follows:

[0047] S204: The oil spill detection feature and the oil film classification feature are input as input parameters to the detection model, and a target oil spill detection model is obtained by performing several trainings based on the hyperplane classification function in the detection model.

[0048] The detection model is SVM (Support Vector Machine, SVM), a support vector machine classifier, whose basic principle is to generalize and model the classification of one-dimensional linearly separable samples; for linearly inseparable samples, consider dimensionality increase, and gradually nonlinearly map the low-dimensional point set to higher dimensions until it can be separated.

[0049] In this embodiment, the detection device uses the oil spill detection features and oil film classification features as input parameters to the detection model, and performs several trainings based on the hyperplane classification function in the detection model to obtain a target oil spill detection model, wherein the hyperplane classification function is:

[0050] 1-y i (ω T f(x i )+b)-ξ i ≤0

[0051] Where y i is the output parameter, ω is the first segmentation plane parameter, b is the second segmentation plane parameter, ξ i is the third splitting plane parameter, f(x i ) is the mapping function, x i is the input parameter.

[0052] See also Figure 4 , Figure 4 The flowchart of the oil spill detection method based on polarimetric SAR images provided in the third embodiment of the present application further includes step S205, which is before step S204 and is specifically as follows:

[0053] S205: Constructing the objective function and objective constraints of the detection model, and constructing the hyperplane classification function of the detection model according to the objective function and objective constraints.

[0054] In this embodiment, the detection device constructs the objective function of the detection model, wherein the objective function is:

[0055]

[0056] The first segmentation plane parameter, the second segmentation plane parameter, and the third segmentation plane parameter in the objective function are respectively differentiated and taken to their extreme values to obtain the objective constraint condition, wherein the objective constraint condition is:

[0057]

[0058]

[0059] λ i +μ i=1

[0060]

[0061] Solving the first segmentation plane parameters and the second segmentation plane parameters to obtain the first segmentation plane parameters and the second segmentation plane parameters, and constructing a hyperplane classification function of the detection model according to the first segmentation plane parameters and the second segmentation plane parameters.

[0062] S3: Responding to a detection instruction, wherein the detection instruction includes a polarimetric SAR image of the area to be detected, obtaining an oil spill detection result output by the target oil spill detection model according to the polarimetric SAR image of the area to be detected and a target oil spill detection model.

[0063] The detection instruction is issued by the user and received by the detection device.

[0064] In this embodiment, the detection device receives the detection instruction sent by the user and responds to it by acquiring a polarimetric SAR image of the area to be detected. Based on the polarimetric SAR image of the area to be detected and a target oil spill detection model, the detection device analyzes the suspected oil spill area and the clean area in the polarimetric SAR image of the area to be detected. The device distinguishes between the target oil spill area and the non-target oil spill area within the suspected oil spill area, adds corresponding representations, and returns the oil spill detection results to the display interface of the detection device. The target oil spill area, the non-target oil spill area, and their corresponding identifiers are displayed and annotated on an electronic map.

[0065] Please refer to Figure 5 , Figure 5 This is a schematic diagram of the structure of an oil spill detection device based on polarimetric SAR images provided in the fourth embodiment of the present application. The device can implement all or part of the oil spill detection device based on polarimetric SAR images through software, hardware, or a combination of both. The device 5 includes:

[0066] An acquisition module 51 is configured to acquire a polarimetric SAR image of a target area, wherein the polarimetric SAR image includes a suspected oil spill area and a clean area;

[0067] a training module 52 configured to obtain polarization features of the polarimetric SAR image, extract target polarization features from the polarimetric SAR image, input the target polarization features into a preset detection model, perform several training cycles, and obtain a target oil spill detection model, wherein the target polarization features include oil spill detection features and oil film classification features;

[0068] The detection module 53 is configured to respond to a detection instruction including a polarimetric SAR image of the area to be detected, and obtain an oil spill detection result output by the target oil spill detection model based on the polarimetric SAR image of the area to be detected and the target oil spill detection model.

[0069] In an embodiment of the present application, an acquisition module acquires a polarimetric SAR image of a target area, wherein the polarimetric SAR image includes a suspected oil spill area and a clean area. A training module acquires polarimetric features from the polarimetric SAR image, extracts target polarimetric features from the polarimetric SAR image, and inputs the target polarimetric features into a preset detection model for several training cycles to acquire a target oil spill detection model, wherein the target polarimetric features include oil spill detection features and oil slick classification features. A detection module responds to a detection instruction, wherein the detection instruction includes a polarimetric SAR image of the target area to be detected, and acquires an oil spill detection result output by the target oil spill detection model based on the polarimetric SAR image of the target area to be detected and the target oil spill detection model. By comparing and analyzing the polarimetric features, polarimetric features with optimal oil spill detection and classification performance are selected. This allows for effective filtering of suspected oil spills from the polarimetric SAR image while simultaneously extracting oil spills. This not only reduces polarimetric feature redundancy but also improves the accuracy of oil spill detection and oil slick classification, enabling rapid and effective detection of oil spills.

[0070] Please refer to Figure 6 , Figure 6 The computer device 6 is a schematic diagram of the structure of the computer device provided in the fifth embodiment of the present application. The computer device 6 includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61; the computer device may store multiple instructions, which are suitable for being loaded and executed by the processor 61. Figures 1 to 4 The method steps of the embodiment shown, the specific execution process can be found in Figures 1 to 4 The detailed description of the illustrated embodiment will not be repeated here.

[0071] The processor 61 may include one or more processing cores. The processor 61 utilizes various interfaces and circuits to connect to various components within the server. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 62, as well as accessing data within the memory 62, the processor 61 performs various functions and processes data in the polarimetric SAR image-based oil spill detection device 5. Optionally, the processor 61 may be implemented in the form of at least one of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 61 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content displayed on the touchscreen display; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor 61 and may be implemented as a separate chip.

[0072] Among them, the memory 62 may include a random access memory 62 (Random Access Memory, RAM), and may also include a read-only memory 62 (Read-Only Memory). Optionally, the memory 62 includes a non-transitory computer-readable storage medium. The memory 62 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 62 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 62 may also be optionally at least one storage device located away from the aforementioned processor 61.

[0073] The embodiment of the present application also provides a storage medium, which can store multiple instructions, which are suitable for the processor to load and execute the above Figures 1 to 4 The method steps of the embodiment shown, the specific execution process can be found in Figures 1 to 4 The detailed description of the illustrated embodiment will not be repeated here.

[0074] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0075] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0076] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraint algorithm of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0077] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0078] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0079] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0080] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form.

[0081] The present invention is not limited to the above-mentioned embodiments. If various changes or modifications of the present invention do not depart from the spirit and scope of the present invention, and if these changes and modifications fall within the scope of the claims of the present invention and equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A method for oil spill detection based on polarimetric SAR images, characterized in that: The following steps are involved: Acquire a polarimetric SAR image of the target area, wherein the polarimetric SAR image includes a suspected oil spill area and a clean area; Extracting images of the suspected oil spill area and the clean area from the polarimetric SAR image as a first sample image and a second sample image, respectively, and obtaining polarization features corresponding to the first sample image and the second sample image; wherein the polarization features corresponding to the first sample image include polarization features corresponding to the oil spill target area and polarization features corresponding to the non-target oil spill target area; The polarization feature of the first sample image is used as the first selected sample, and the polarization feature of the second sample image is used as the second selected sample. The mean and variance of the first selected sample and the second selected sample are obtained and input into a preset Euclidean distance calculation algorithm. The first Euclidean distance between the polarization feature corresponding to the oil spill target area and the polarization feature corresponding to the clean area, and the first Euclidean distance between the polarization feature corresponding to the non-target oil spill target area and the polarization feature corresponding to the clean area are calculated. The polarization feature corresponding to the largest first Euclidean distance is used as the oil spill detection feature, wherein the Euclidean distance calculation algorithm is: Where D is the Euclidean distance, m1 is the mean of the first selected sample, m2 is the mean of the second selected sample, σ1 is the variance of the first selected sample, and σ2 is the variance of the second selected sample; The polarization features corresponding to the target oil spill area in the first sample image are used as the first selected sample, and the polarization features corresponding to the non-target oil spill area are used as the second selected sample. The means and variances of the first selected sample and the second selected sample are obtained and input into a preset Euclidean distance calculation algorithm. The second Euclidean distance between the polarization features corresponding to the target oil spill area and the polarization features corresponding to the non-target oil spill area is calculated, and the polarization feature corresponding to the largest second Euclidean distance is used as the oil film classification feature. Input the oil spill detection features and oil film classification features into a preset detection model, perform several trainings, and obtain a target oil spill detection model; In response to a detection instruction, the detection instruction includes a polarimetric SAR image of the area to be detected, and according to the polarimetric SAR image of the area to be detected and a target oil spill detection model, an oil spill detection result output by the target oil spill detection model is acquired.

2. The oil spill detection method based on polarimetric SAR images according to claim 1, wherein: The polarization characteristics include simplified polarization base station height characteristics, even-order scattering characteristics, odd-order scattering characteristics, volume scattering characteristics, roundness characteristics, relative phase characteristics, polarization degree characteristics, circular level characteristics, circular polarization degree characteristics, circular polarization ratio characteristics, linear level characteristics, linear polarization ratio characteristics, contrast characteristics, elliptical azimuth characteristics, elliptical angle characteristics, average scattering angle characteristics, anisotropy index characteristics, simplified polarization entropy characteristics and total power characteristics.

3. The oil spill detection method based on polarimetric SAR images according to claim 1, wherein The detection model is a SVM classifier.

4. The oil spill detection method based on polarization SAR images according to claim 3, wherein The oil spill detection features and oil film classification features are input into a preset detection model, and training is performed several times to obtain a target oil spill detection model, including the following steps: The oil spill detection features and oil film classification features are used as input parameters and input into the detection model. According to the hyperplane classification function in the detection model, several trainings are performed to obtain the target oil spill detection model, wherein the hyperplane classification function is: 1-y i (oh T f(x i )+b)-ξ i ≤0 Where y i is the output parameter, ω is the first segmentation plane parameter, b is the second segmentation plane parameter, ξ i is the third splitting plane parameter, f(x i ) is the mapping function, x i is the input parameter.

5. The oil spill detection method based on polarization SAR images according to claim 4, wherein The oil spill detection feature and the oil film classification feature are input as input parameters to the detection model, and a plurality of trainings are performed according to the hyperplane classification function in the detection model to obtain the target oil spill detection model, including the following steps: Constructing the objective function and objective constraints of the detection model, and constructing the hyperplane classification function of the detection model based on the objective function and objective constraints, wherein the objective function is: Where λ i is the first constraint parameter, μ i is the second constraint parameter, and n is the number of input parameters; The target constraints are: l i +m i =1 Where y i is the output parameter, ω is the first segmentation plane parameter, b is the second segmentation plane parameter, ξ i is the third splitting plane parameter, f(x i ) is the mapping function, x i is the input parameter.

6. An oil spill detection device based on polarimetric SAR images, characterized in that: include: An acquisition module, configured to acquire a polarimetric SAR image of a target area, wherein the polarimetric SAR image includes a suspected oil spill area and a clean area; A training module is configured to extract images of a suspected oil spill area and a clean area from the polarimetric SAR image as a first sample image and a second sample image, respectively, and obtain polarization features corresponding to the first sample image and the second sample image; wherein the polarization features corresponding to the first sample image include polarization features corresponding to the oil spill target area and polarization features corresponding to the non-target oil spill target area; The polarization feature of the first sample image is used as the first selected sample, and the polarization feature of the second sample image is used as the second selected sample. The mean and variance of the first selected sample and the second selected sample are obtained and input into a preset Euclidean distance calculation algorithm. The first Euclidean distance between the polarization feature corresponding to the oil spill target area and the polarization feature corresponding to the clean area, and the first Euclidean distance between the polarization feature corresponding to the non-target oil spill target area and the polarization feature corresponding to the clean area are calculated. The polarization feature corresponding to the largest first Euclidean distance is used as the oil spill detection feature, wherein the Euclidean distance calculation algorithm is: Where D is the Euclidean distance, m1 is the mean of the first selected sample, m2 is the mean of the second selected sample, σ1 is the variance of the first selected sample, and σ2 is the variance of the second selected sample; The polarization features corresponding to the target oil spill area in the first sample image are used as the first selected sample, and the polarization features corresponding to the non-target oil spill area are used as the second selected sample. The means and variances of the first selected sample and the second selected sample are obtained and input into a preset Euclidean distance calculation algorithm. The second Euclidean distance between the polarization features corresponding to the target oil spill area and the polarization features corresponding to the non-target oil spill area is calculated, and the polarization feature corresponding to the largest second Euclidean distance is used as the oil film classification feature. Input the oil spill detection features and oil film classification features into a preset detection model, perform several trainings, and obtain a target oil spill detection model; The detection module is configured to respond to a detection instruction, wherein the detection instruction includes a polarimetric SAR image of the area to be detected, and obtain an oil spill detection result output by the target oil spill detection model based on the polarimetric SAR image of the area to be detected and a target oil spill detection model.

7. A computer device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the oil spill detection method based on polarization SAR images as claimed in any one of claims 1 to 5 are implemented.

8. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the oil spill detection method based on polarization SAR images according to any one of claims 1 to 5 are implemented.

Images