Satellite-borne synthetic aperture radar marine oil spill detection method, equipment, medium and product

Abstract

The invention discloses a satellite-borne synthetic aperture radar marine oil spill detection method and device, a medium and a product, and relates to the field of oil spill detection, and the method comprises the steps: obtaining a satellite-borne synthetic aperture radar image of a marine oil spill region; based on a Faster R-CNN model and a UNet + + model, constructing a marine oil spill detection model; in the marine oil spill detection model, according to a satellite-borne synthetic aperture radar image, a Faster R-CNN model is adopted to determine a candidate frame containing a marine oil spill area; according to a spaceborne synthetic aperture radar image corresponding to the candidate frame, a UNet + + model is adopted to detect the marine oil spill area, and a detection result is obtained; and according to the satellite-borne synthetic aperture radar image of the marine oil spill area, adopting a marine oil spill detection model to obtain a detection result of the marine oil spill area. According to the invention, more efficient and accurate detection of spaceborne SAR marine oil spill can be realized.

Description

Technical Field

[0001] The present application relates to the field of oil spill detection, and in particular to a method, equipment, medium and product for detecting marine oil spills using a spaceborne synthetic aperture radar. Background Art

[0002] With the rapid development of marine resource development and maritime transportation, marine oil spill accidents occur frequently, and the pollution caused by oil leaking into the sea can last for many years in the marine environment. Therefore, it is crucial to develop intelligent, efficient and rapid oil spill detection technology to reduce the harmful effects of oil pollution on the marine environment.

[0003] Compared with ships and aircraft, satellites are more suitable for oil spill monitoring due to their low cost, high efficiency and large coverage area. Satellite-borne synthetic aperture radar (SAR) is not affected by clouds and light, and can observe large areas with high resolution. This capability makes it a unique microwave instrument for timely monitoring of marine oil spills. Oil spills appear on the sea surface in the form of floating viscoelastic hydrocarbon layers, which damp short surface gravity waves and capillary waves generated by the wind due to increased surface tension. This damping effect causes a reduction in radar echoes from the ocean surface, making the oil spill appear as dark spots in synthetic aperture radar images. However, suspected oil spill phenomena such as biofilms, low wind speed areas, oil ice, rain cells, wind shadow areas near the coastline, upwelling areas and internal waves can also weaken radar backscattering, resulting in dark spots in SAR images. Under certain conditions, multiple types of dark spots may appear simultaneously in SAR images, making oil spill detection more complicated.

[0004] Traditional mathematical models and image processing techniques have been widely used to detect oil spills in single-polarization SAR images. Early studies used a combination of adaptive thresholding and statistical modeling to achieve automatic detection of oil spills. In the process of oil spill detection, an adaptive thresholding method is used to identify dark spots in SAR images. However, this method has difficulty in accurately detecting dark spots in images due to the influence of speckle noise. For classifiers based on multivariate probability distribution functions, it is crucial to combine prior information about the possibility of observing an oil spill with auxiliary data including wind speed. Image processing techniques including texture analysis and wavelet transform have also been used for oil spill detection. However, these two methods may produce inaccurate detection results when the contrast between the oil spill and the surrounding area is low.

[0005] The above methods rely entirely on the ocean surface radar echo intensity measured by single-polarization SAR to detect oil spills. The target scattering matrix measured by full-polarization SAR includes phase and amplitude information. According to the polarization target decomposition theory, various polarization feature parameters can be decomposed from the scattering matrix. Since these polarization features can describe and quantify different scattering mechanisms, they have been widely used in oil spill detection. However, a previous study showed that the polarization features extracted from full-polarization SAR data are affected by multiplicative and additive system noise, making them unsuitable for analyzing scattering characteristics and features. In addition, analysis of airborne full-polarization SAR observations of the oil spill in the Deepwater Horizon disaster showed that radar backscattering in oil-covered areas and clean sea surfaces is mainly related to surface Bragg scattering. Therefore, the difference in polarization features between oil spills and clean waters may be caused by instrument noise rather than different scattering mechanisms. In addition, the coverage range of full-polarization SAR (20 km to 70 km) is much smaller than that of single-polarization SAR (250 km to 500 km), making it unsuitable for oil spill monitoring.

[0006] Machine learning techniques are increasingly being applied to remote sensing image classification and segmentation tasks due to their remarkable ability to map complex nonlinear relationships between inputs and outputs. Various machine learning models, including artificial neural networks, genetic algorithms, and random forests, have been used to detect oil spills in SAR images. Several artificial neural network-based oil spill detection algorithms use two sets of models: one for segmenting dark spots and the other for classifying dark spots. This dual-model approach increases the complexity of the oil spill detection process. In addition, the inputs to artificial neural network models are usually selected subjectively by humans, so this approach cannot select the most representative features for oil spill detection. Although random forests and genetic algorithms can eliminate redundant inputs and identify the most important physical, geometric, and texture features, they still require human intervention to achieve oil spill detection.

[0007] Deep learning models consist of multiple processing layers and can effectively learn various features in images. For example, convolutional neural networks can automatically extract multi-level image features from large datasets and fuse information, thereby facilitating fast and accurate image classification and segmentation. Various deep learning models such as YOLOv4, Faster R-CNN, and VGG-16 have been used for oil spill detection. These classification or object detection models are optimized for dark spot classification or oil spill location in SAR images in practical applications. In addition, some semantic and instance segmentation models have been used to segment oil spills and extract their extent. However, most segmentation models require sub-images containing oil spills as input. To obtain these sub-images, the location of the oil spill in the entire image must be determined in advance. The original SAR image can be divided into several sub-images, and the oil spill detection process must be repeated for each sub-image, which increases the detection time and computational load. In addition, segmenting the full SAR image into sub-images may split large or narrow oil spills into several parts, increasing the risk of a single oil spill going undetected.

[0008] Based on the development status and existing problems of the above-mentioned existing technologies, there is an urgent need to provide a new SAR marine oil spill detection method to solve the problems of the difficulty in balancing detection accuracy and efficiency, difficulty in feature extraction, and high false detection rate in the existing technologies, so as to achieve more efficient and accurate detection of marine oil spills by satellite-borne SAR, and provide strong technical support for marine environmental protection and emergency response to oil spill accidents. Summary of the invention

[0009] The purpose of this application is to provide a space-borne synthetic aperture radar ocean oil spill detection method, equipment, medium and product, which can achieve more efficient and accurate detection of space-borne SAR ocean oil spills.

[0010] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a spaceborne synthetic aperture radar ocean oil spill detection method, the spaceborne synthetic aperture radar ocean oil spill detection method comprising: Acquire spaceborne synthetic aperture radar images of marine oil spill areas; Based on the Faster R-CNN model and the UNet++ model, a marine oil spill detection model is constructed; in the marine oil spill detection model, the Faster R-CNN model is used according to the satellite-borne synthetic aperture radar image to determine the candidate frame containing the marine oil spill area; and according to the satellite-borne synthetic aperture radar image corresponding to the candidate frame, the UNet++ model is used to detect the marine oil spill area to obtain the detection result; the detection result includes: the boundary, shape and internal detail features of the marine oil spill area; According to the satellite-borne synthetic aperture radar images of the marine oil spill area, the marine oil spill detection model is used to obtain the detection results of the marine oil spill area.

[0011] Optionally, the marine oil spill detection model further includes: The confidence scores of candidate boxes containing the marine oil spill area are sorted using the non-maximum suppression algorithm; Starting from the candidate box with the highest confidence score, the candidate boxes whose overlapping area with the current candidate box exceeds the area threshold and whose confidence scores are less than the confidence score threshold are eliminated to obtain the eliminated candidate boxes.

[0012] Optionally, the method of obtaining the detection result of the marine oil spill area by using a marine oil spill detection model based on the satellite-borne synthetic aperture radar image of the marine oil spill area specifically includes: Performing preprocessing operations on the satellite-borne synthetic aperture radar image of the marine oil spill area; the preprocessing operations include: speckle noise suppression, incident angle correction, land masking and data normalization; According to the preprocessed spaceborne synthetic aperture radar images, the marine oil spill detection model is adopted to obtain the detection results of the marine oil spill area.

[0013] Optionally, the preprocessing operation of the satellite-borne synthetic aperture radar image of the marine oil spill area specifically includes: Using moving mean filtering to suppress speckle noise in spaceborne synthetic aperture radar images; The CMOD5.N geophysical model function is used to perform intensity scaling operation on the spaceborne synthetic aperture radar image after speckle noise suppression in the distance direction to obtain the spaceborne synthetic aperture radar image after incident angle correction. The global high-resolution digital elevation model is used to mask the land area and enhance the image contrast of the spaceborne synthetic aperture radar image after incident angle correction, so as to obtain the spaceborne synthetic aperture radar image after land masking. The data of the spaceborne synthetic aperture radar image after land masking is normalized to obtain the preprocessed spaceborne synthetic aperture radar image.

[0014] Optionally, using a CMOD5.N geophysical model function to perform an intensity scaling operation in the distance direction on the spaceborne synthetic aperture radar image after speckle noise suppression to obtain a spaceborne synthetic aperture radar image after incident angle correction, specifically including: Using the formula Perform intensity scaling operation in the distance direction on the spaceborne synthetic aperture radar image after speckle noise suppression; in, is the vertical polarization radar backscatter coefficient, represent wind speed, relative wind direction and incident angle respectively, ssr represents the sea surface roughness after incident angle correction, and CMOD5.N() is the CMOD5.N geophysical model function.

[0015] Optionally, according to the pre-processed satellite-borne synthetic aperture radar image, a marine oil spill detection model is used to obtain a detection result of the marine oil spill area, and then the method further includes: Visualize the detection results.

[0016] In a second aspect, the present application provides a spaceborne synthetic aperture radar ocean oil spill detection device, the spaceborne synthetic aperture radar ocean oil spill detection device comprising: An image acquisition module, used to acquire satellite-borne synthetic aperture radar images of the marine oil spill area; The marine oil spill detection model construction module is used to construct a marine oil spill detection model based on the Faster R-CNN model and the UNet++ model; in the marine oil spill detection model, the Faster R-CNN model is used to determine the candidate frame containing the marine oil spill area according to the satellite-borne synthetic aperture radar image; and the UNet++ model is used to detect the marine oil spill area according to the satellite-borne synthetic aperture radar image corresponding to the candidate frame to obtain the detection result; the detection result includes: the boundary, shape and internal detail features of the marine oil spill area; The detection result determination module is used to obtain the detection result of the marine oil spill area based on the satellite-borne synthetic aperture radar image of the marine oil spill area and the marine oil spill detection model.

[0017] 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 spaceborne synthetic aperture radar ocean oil spill detection method.

[0018] 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 spaceborne synthetic aperture radar ocean oil spill detection method.

[0019] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the satellite-borne synthetic aperture radar ocean oil spill detection method.

[0020] According to the specific embodiments provided in this application, this application has the following technical effects: The present application provides a method, device, medium and product for detecting marine oil spills by using a spaceborne synthetic aperture radar. Based on the Faster R-CNN model and the UNet++ model, a marine oil spill detection model is constructed. Based on the Faster R-CNN model, preliminary target positioning and identification of the marine oil spill area are performed, and the range of the possible oil spill area is determined by using the characteristics of the Faster R-CNN to quickly and accurately detect the target object. At the same time, with the advantage of UNet++ in semantic segmentation, a more refined segmentation and feature extraction are performed on the located area, so as to accurately depict the boundary, shape and internal detail features of the oil spill area. By using the marine oil spill detection model for marine oil spill detection, the present application can solve the problems of the difficulty in balancing detection accuracy and efficiency, difficulty in feature extraction and high false detection rate in the prior art, so as to achieve more efficient and accurate detection of marine oil spills by using spaceborne SAR, and provide strong technical support for marine environmental protection and emergency response to oil spill accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 This is a schematic flow chart of a method for detecting marine oil spills using a space-borne synthetic aperture radar in one embodiment of the present application. DETAILED DESCRIPTION

[0023] 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.

[0024] 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 with reference to the accompanying drawings and specific implementation methods.

[0025] In an exemplary embodiment, Figure 1 As shown, a method for detecting marine oil spills using a spaceborne synthetic aperture radar is provided, the method comprising the following S101 to S103. Among them: S101, obtains spaceborne synthetic aperture radar images of the marine oil spill area; S102, constructing a marine oil spill detection model based on the Faster R-CNN model and the UNet++ model; in the marine oil spill detection model, the Faster R-CNN model is used to determine a candidate frame containing the marine oil spill area according to the satellite-borne synthetic aperture radar image; and the UNet++ model is used to detect the marine oil spill area according to the satellite-borne synthetic aperture radar image corresponding to the candidate frame, to obtain a detection result; the detection result includes: the boundary, shape and internal detail features of the marine oil spill area; The Faster R-CNN (Fast Regional Convolutional Neural Network) model includes a feature extraction network (such as using VGG-16 as the basic network), a Regional Proposal Network (RPN), and a classification and regression head. The Faster R-CNN model is trained using labeled training set data. During the training process, the feature extraction network is responsible for extracting deep semantic features from SAR images, the RPN network generates a series of candidate boxes that may contain marine oil spill areas based on these features, and the classification and regression head classifies these candidate boxes (determines whether it is an oil spill area) and regresses (precisely adjusts the position and size of the candidate boxes). The weight parameters of the model are continuously adjusted through the back-propagation algorithm to minimize the loss function, which comprehensively considers the classification loss and regression loss.

[0026] The nested U-shaped structure of the UNet++ model is one of its core advantages. Compared with the traditional U-shaped structure, this structure is not a simple single-layer encoding-decoding design, but contains multiple encoding-decoding paths. The existence of multiple paths enables the model to capture image features of different scales and levels at the same time. When faced with complex and changeable marine oil spill images, whether it is a large area of ​​oil spill patches or a tiny oil spill spot, it can accurately perceive it. Features at different levels are fused and transmitted in these paths, forming a rich feature information network. For example, in the encoding part, as the image is gradually downsampled, the spatial resolution of the image gradually decreases, but the semantic information is constantly enhanced. Each layer can extract feature information of different abstract levels, from low-level features such as edges and textures to more semantic shapes and regional features. The decoding part cleverly upsamples these feature information step by step to restore it to the original image resolution, and fuses features from different levels in the process. This cross-level feature fusion mechanism greatly improves the model's ability to perceive the boundaries and internal details of the oil spill area. For example, for those pixels at the border of the oil spill area that are unclear and have a subtle transition with the background, by fusing low-level edge features and high-level semantic features, it is possible to more accurately determine their category, thereby finely depicting the boundary contour of the oil spill area. For internal details, it is also possible to better identify the uniformity of distribution, shape changes, etc. based on multi-scale features. During the training process, the UNet++ model is trained using labeled training set data. The model performs semantic segmentation specifically for possible oil spill areas that have been initially located by Faster R-CNN. The model parameters are adjusted by minimizing the cross entropy loss function, which can effectively measure the difference between the model prediction results and the true label, prompting the model to continuously optimize the parameters to improve the accuracy of the prediction. The trained model can assign labels to each pixel in the image (usually two categories, oil spill area and background, in marine oil spill detection). This accurate classification capability based on the pixel level significantly improves the accuracy and meticulousness of detection compared to the traditional method that can only make rough judgments on the area, laying a solid foundation for subsequent quantitative assessment of oil spills and accurate definition of pollution scope.

[0027] The trained Faster R-CNN model and UNet++ model are fused using high-performance computers. The specific fusion method is: the pre-processed spaceborne synthetic aperture radar image is provided as input data to the trained Faster R-CNN model. The Faster R-CNN model uses a feature extraction network to deeply mine and learn features such as complex textures and grayscale changes in SAR images. After extracting rich feature information, RPN constructs a series of candidate boxes that may contain marine oil spill areas based on these features. Each candidate box contains location information and a corresponding confidence score, which reflects the probability that the candidate box contains the oil spill area.

[0028] In order to further improve the detection efficiency and reduce the interference of redundant information, the non-maximum suppression (NMS) algorithm is introduced. The NMS algorithm will sort all candidate boxes according to the confidence score, and then start from the candidate box with the highest confidence score, and suppress the candidate boxes whose overlapping area exceeds the area threshold (such as 0.5) and whose confidence score is less than the confidence score threshold. Then, the most representative and credible candidate boxes of the oil spill area are effectively screened out, thereby greatly reducing the amount of data for subsequent processing and improving the accuracy and efficiency of detection.

[0029] The satellite synthetic aperture radar image (i.e., the oil spill dark spot sub-image) corresponding to the candidate frame of the oil spill area obtained after NMS processing is used as the input of the UNet++ model. The UNet++ model performs fine oil spill segmentation based on the received satellite synthetic aperture radar image. The encoding part first downsamples the input oil spill dark spot sub-image. Through a series of convolutional layers and pooling layers, the resolution of the image is gradually reduced, but each layer will extract different levels of feature information, from shallow local features such as edges and textures to deep semantic features. When the encoding part completes the downsampling operation, the decoding part starts to work. The decoding process is a process of gradually upsampling to restore the image resolution, and in this process, the UNet++ model uses a special jump connection mechanism to fuse and transmit the feature information extracted from different levels of the encoding part. Specifically, each decoding layer will fuse the feature information from the corresponding encoding layer and the shallower encoding layer, so that the model can fully utilize the multi-scale feature information to perform more accurate segmentation and feature extraction of the oil spill area while restoring the image resolution.

[0030] After completing the model fusion and obtaining the preliminary detection results, optimizing and adjusting the fused model using the validation set data is a key step to improve the model performance and reliability. As a data sample independent of the training set, the validation set data can truly reflect the performance of the model when facing unknown data. By applying the fused model to the validation set data, the performance indicators of the model on the validation set are comprehensively evaluated. Among them, the accuracy rate is the proportion of the number of samples correctly predicted by the model as oil spill areas and correctly predicted as non-oil spill areas to the total number of samples, which reflects the overall accuracy of the model; the recall rate refers to the proportion of the number of samples that are actually oil spill areas and correctly predicted by the model as oil spill areas to the total number of samples of the actual oil spill areas, which reflects the model's ability to capture oil spill areas. Based on the evaluation results of the performance indicators, the hyperparameters of the model are finely adjusted. Through rounds of validation set evaluation and hyperparameter adjustment, the fused model is continuously optimized so that it can continuously improve the detection accuracy and generalization ability while maintaining efficient detection speed. Finally, it can adapt to the marine oil spill detection tasks of satellite-borne SAR images in various complex marine environments, providing strong technical support and guarantee for marine environmental protection and emergency response to oil spill accidents.

[0031] S103, obtaining a detection result of the marine oil spill area by using a marine oil spill detection model according to the satellite-borne synthetic aperture radar image of the marine oil spill area.

[0032] S103 specifically includes: S31, performing a preprocessing operation on the satellite-borne synthetic aperture radar image of the marine oil spill area; the preprocessing operation includes: speckle noise suppression, incident angle correction, land masking and data normalization; In a specific embodiment, a server equipped with an Intel i9-10900x CPU, 256 GB RAM, and an NVIDIA RTX3090 graphics card is used to perform preprocessing operations on a spaceborne synthetic aperture radar image of an ocean oil spill area; S31 specifically includes: S1, using moving mean filtering to suppress speckle noise of the spaceborne synthetic aperture radar image; the spaceborne synthetic aperture radar image after speckle noise suppression is filtered and smoothed to 100-meter pixel interval; S2, using the CMOD5.N geophysical model function to perform intensity scaling in the range direction on the spaceborne synthetic aperture radar image after speckle noise suppression, in order to reduce the variation of radar backscatter with the incident angle; Specifically, using the formula Perform intensity scaling operation in the distance direction on the spaceborne synthetic aperture radar image after speckle noise suppression; in, is the vertical polarization radar backscatter coefficient, represent wind speed, relative wind direction and incident angle respectively, ssr represents the sea surface roughness after incident angle correction, and CMOD5.N() is the CMOD5.N geophysical model function.

[0033] S3, using the global high-resolution digital elevation model to mask the land area and enhance the image contrast of the spaceborne synthetic aperture radar images after incident angle correction, to eliminate the impact of dark land targets on oil spill detection, especially for spaceborne synthetic aperture radar images acquired in coastal areas; S4, data normalization is performed on spaceborne synthetic aperture radar images after land masking to avoid inputting outliers that may dominate the results.

[0034] S32, according to the pre-processed satellite-borne synthetic aperture radar image, using the ocean oil spill detection model to obtain the detection result of the ocean oil spill area.

[0035] S103 and later also include: Visualize the detection results, such as marking the oil spill area on the map, generating a detection report, etc., so that relevant departments can timely and accurately grasp the marine oil spill situation and take corresponding response measures.

[0036] This application combines the target detection capability of the Faster R-CNN model with the semantic segmentation advantage of the UNet++ model. The Faster R-CNN model can use its feature extraction network and region proposal network to quickly locate the possible scope of the marine oil spill area, providing a basis for subsequent accurate detection. The UNet++ model, through its unique nested U-shaped structure and multi-path encoding-decoding feature fusion mechanism, can finely segment the area located by the Faster R-CNN model and accurately depict the boundaries, shapes and internal detail features of the oil spill area. For example, when detecting some areas with irregular shapes and uneven oil spill distribution, the UNet++ model can effectively use feature information at different levels for comprehensive judgment, avoiding segmentation errors caused by single-level features, thereby greatly improving the overall detection accuracy, and the overall detection accuracy exceeds 89%. Through the initial positioning accuracy of the target area by the Faster R-CNN model and the fine segmentation ability of the UNet++ model in the positioning area, the synergy of the two significantly improves the detection accuracy.

[0037] Since the Faster R-CNN model is used for rapid early target positioning, it can quickly screen out possible oil spill areas from the massive data of satellite-borne SAR, reducing the amount of data to be processed later. Compared with the traditional full-image one-by-one analysis method, the detection time is greatly shortened. For example, when processing large-area ocean monitoring data, the Faster R-CNN model can quickly exclude a large number of non-oil spill areas, and then the UNet++ model only needs to perform fine processing on these small number of suspicious areas, avoiding unnecessary waste of computing resources and significantly improving detection efficiency. The time to process a SAR image does not exceed one minute. The detection efficiency is improved through the ability of the RPN network in the Faster R-CNN model to quickly generate candidate boxes and the overall optimization of the marine oil spill detection model.

[0038] In the data preprocessing stage, this application performs speckle noise suppression, incident angle correction, land masking and data normalization operations based on the characteristics of spaceborne SAR data, and uses a suitable loss function to optimize the model training in the marine oil spill detection model training stage. The dual optimization of data and marine oil spill detection model enables the marine oil spill detection model to better adapt to the complexity and variability of spaceborne SAR data. Whether it is data acquired in different sea areas and different climatic conditions, or various noises and geometric deformation interferences in the data, the model can maintain good detection performance. Through the coordinated optimization and adjustment of data and marine oil spill detection model, the adaptability and robustness of the model are enhanced.

[0039] Based on the same inventive concept, the embodiment of the present application also provides a satellite-borne synthetic aperture radar ocean oil spill detection device for implementing the above-mentioned satellite-borne synthetic aperture radar ocean oil spill detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more satellite-borne synthetic aperture radar ocean oil spill detection devices provided below can refer to the limitations of the satellite-borne synthetic aperture radar ocean oil spill detection method above, and will not be repeated here.

[0040] In an exemplary embodiment, a spaceborne synthetic aperture radar ocean oil spill detection device is provided, comprising: An image acquisition module, used to acquire satellite-borne synthetic aperture radar images of the marine oil spill area; The marine oil spill detection model construction module is used to construct a marine oil spill detection model based on the Faster R-CNN model and the UNet++ model; in the marine oil spill detection model, the Faster R-CNN model is used to determine the candidate frame containing the marine oil spill area according to the satellite-borne synthetic aperture radar image; and the UNet++ model is used to detect the marine oil spill area according to the satellite-borne synthetic aperture radar image corresponding to the candidate frame to obtain the detection result; the detection result includes: the boundary, shape and internal detail features of the marine oil spill area; The detection result determination module is used to obtain the detection result of the marine oil spill area based on the satellite-borne synthetic aperture radar image of the marine oil spill area and the marine oil spill detection model.

[0041] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via 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 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 via a network connection. When the computer program is executed by the processor, a method for detecting marine oil spills by a spaceborne synthetic aperture radar is implemented.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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 this 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), magnetoresistive 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).

[0046] 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.

[0047] The technical features of the above embodiments may be arbitrarily combined. 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.

[0048] 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 method for detecting marine oil spills using spaceborne synthetic aperture radar, characterized in that: The spaceborne synthetic aperture radar ocean oil spill detection method comprises: Acquire spaceborne synthetic aperture radar images of marine oil spill areas; Based on the Faster R-CNN model and the UNet++ model, a marine oil spill detection model is constructed; in the marine oil spill detection model, the Faster R-CNN model is used according to the satellite-borne synthetic aperture radar image to determine the candidate frame containing the marine oil spill area; and according to the satellite-borne synthetic aperture radar image corresponding to the candidate frame, the UNet++ model is used to detect the marine oil spill area to obtain the detection result; the detection result includes: the boundary, shape and internal detail features of the marine oil spill area; According to the satellite-borne synthetic aperture radar images of the marine oil spill area, the marine oil spill detection model is used to obtain the detection results of the marine oil spill area.

2. The method for detecting marine oil spills using spaceborne synthetic aperture radar according to claim 1, characterized in that: The marine oil spill detection model also includes: The confidence scores of candidate boxes containing the marine oil spill area are sorted using the non-maximum suppression algorithm; Starting from the candidate box with the highest confidence score, the candidate boxes whose overlapping area with the current candidate box exceeds the area threshold and whose confidence scores are less than the confidence score threshold are eliminated to obtain the eliminated candidate boxes.

3. The spaceborne synthetic aperture radar ocean oil spill detection method according to claim 1, characterized in that: The detection result of the marine oil spill area is obtained by using the marine oil spill detection model based on the satellite-borne synthetic aperture radar image of the marine oil spill area, specifically including: Performing preprocessing operations on the satellite-borne synthetic aperture radar image of the marine oil spill area; the preprocessing operations include: speckle noise suppression, incident angle correction, land masking and data normalization; According to the preprocessed spaceborne synthetic aperture radar images, the marine oil spill detection model is adopted to obtain the detection results of the marine oil spill area.

4. The spaceborne synthetic aperture radar ocean oil spill detection method according to claim 3, characterized in that: The preprocessing operation of the satellite-borne synthetic aperture radar image of the marine oil spill area specifically includes: Using moving mean filtering to suppress speckle noise in spaceborne synthetic aperture radar images; The CMOD5.N geophysical model function is used to perform intensity scaling operation on the spaceborne synthetic aperture radar image after speckle noise suppression in the distance direction to obtain the spaceborne synthetic aperture radar image after incident angle correction. The global high-resolution digital elevation model is used to mask the land area and enhance the image contrast of the spaceborne synthetic aperture radar image after incident angle correction, so as to obtain the spaceborne synthetic aperture radar image after land masking. The data of the spaceborne synthetic aperture radar image after land masking is normalized to obtain the preprocessed spaceborne synthetic aperture radar image.

5. The method for detecting marine oil spills using spaceborne synthetic aperture radar according to claim 4, characterized in that: The CMOD5.N geophysical model function is used to perform intensity scaling operations on the spaceborne synthetic aperture radar image after speckle noise suppression in the distance direction to obtain the spaceborne synthetic aperture radar image after incident angle correction, which specifically includes: Using the formula Perform intensity scaling operation in the distance direction on the spaceborne synthetic aperture radar image after speckle noise suppression; in, is the vertical polarization radar backscatter coefficient, represent wind speed, relative wind direction and incident angle respectively, ssr represents the sea surface roughness after incident angle correction, and CMOD5.N() is the CMOD5.N geophysical model function.

6. The method for detecting marine oil spills using spaceborne synthetic aperture radar according to claim 1, characterized in that: According to the pre-processed spaceborne synthetic aperture radar image, the marine oil spill detection model is used to obtain the detection results of the marine oil spill area, which also includes: Visualize the detection results.

7. A spaceborne synthetic aperture radar marine oil spill detection device, characterized in that: The spaceborne synthetic aperture radar ocean oil spill detection equipment comprises: An image acquisition module, used to acquire satellite-borne synthetic aperture radar images of the marine oil spill area; The marine oil spill detection model construction module is used to construct a marine oil spill detection model based on the Faster R-CNN model and the UNet++ model; in the marine oil spill detection model, the Faster R-CNN model is used to determine the candidate frame containing the marine oil spill area according to the satellite-borne synthetic aperture radar image; and the UNet++ model is used to detect the marine oil spill area according to the satellite-borne synthetic aperture radar image corresponding to the candidate frame, and obtain the detection result; the detection result includes: the boundary, shape and internal detail features of the marine oil spill area; The detection result determination module is used to obtain the detection result of the marine oil spill area based on the satellite-borne synthetic aperture radar image of the marine oil spill area and the marine oil spill detection model.

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 spaceborne synthetic aperture radar ocean oil spill 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 spaceborne synthetic aperture radar ocean oil spill detection method described in 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 spaceborne synthetic aperture radar ocean oil spill detection method described in any one of claims 1 to 6 is implemented.

Images