A Method and System for Segmentation of Oil Spill Targets in Marine Radar

Abstract

The present invention discloses a method and system for segmenting oil spill targets of a marine radar, which relates to the technical field of target segmentation. The technical key points of the present invention include: preprocessing the shipborne radar image; the preprocessing includes convolving the shipborne radar image with a Laplacian operator; using the Otsu algorithm to segment the convolved image and extract the co-frequency interference noise; using mean filtering to smooth the co-frequency interference noise to obtain a preliminary smoothed image; using a gray threshold algorithm and a pixel area threshold method to segment the preliminary smoothed image and extract the block noise; using a dynamic window and distance-weighted median filtering to smooth the block noise to obtain a noise-reduced image; using an improved Phansalkar local threshold method to segment the noise-reduced image and extract the oil film. The present invention effectively suppresses noise, makes the characteristics of the oil spill target more prominent, thereby significantly improving the accuracy of oil spill detection and meeting the actual requirements for extracting effective regions in the field of oil spill detection in marine radar images.

Description

Technical Field

[0001] The present invention relates to the technical field of target segmentation, and particularly to a method and system for segmenting oil spill targets in marine radar. Background Art

[0002] The method for rapid noise reduction and segmentation of marine radar oil spill data is mainly applied to marine radar systems to identify oil spill areas on the sea surface and process relevant data. After an oil spill accident occurs, it is crucial to monitor and judge the scope and spread of the oil spill in a timely and accurate manner for environmental protection and accident emergency response.

[0003] Radar systems usually obtain a large amount of data through sea surface monitoring and use it for oil spill detection. However, due to the characteristics of radar data itself and the influence of the external environment, the data often contains a large amount of noise, which poses challenges to subsequent data analysis and oil spill detection. Summary of the Invention

[0004] In view of the above problems, the present invention proposes a method and system for segmenting oil spill targets in marine radar, in an attempt to solve or alleviate one or more of the above problems.

[0005] According to one aspect of the present invention, a method for segmenting oil spill targets in marine radar is proposed, and the method includes:

[0006] Obtain an on-board radar image;

[0007] Preprocess the on-board radar image; the preprocessing includes: performing convolution on the on-board radar image using a Laplacian operator; segmenting the convolved image using the Otsu algorithm to extract co-frequency interference noise; smoothing the co-frequency interference noise using mean filtering to obtain a preliminary smoothed image; segmenting the preliminary smoothed image using a gray threshold algorithm and a pixel area threshold method to extract block noise; smoothing the block noise using a dynamic window and distance-weighted median filtering to obtain a noise-reduced image;

[0008] Segment the noise-reduced image using an improved Phansalkar local threshold method to extract the oil film.

[0009] Further, the smoothing of the block noise using the dynamic window and distance-weighted median filtering in the preprocessing includes:

[0010] For each noise point of the block noise, a dynamic local window with an n×n size is selected with this noise point as the center, where n is greater than or equal to 3 and is an odd number; if the number of non-noise points in the dynamic local window with an n×n size is greater than the number of noise points, noise point suppression is performed; otherwise, the size of the dynamic local window is set to (n + 2)×(n + 2), and the above process is repeated until the number of non-noise points in the dynamic local window is not greater than the number of noise points and then stop;

[0011] When the number of non-noise points in the dynamic local window is greater than the number of noise points, the new gray value f(i,j) of each non-noise point is calculated according to the distance weight respectively:

[0012]

[0013] where cell() is the ceiling function, (i,j) is the position of the non-noise point in the local window, is the original gray value of the non-noise point (i,j) in the local window;

[0014] The newly calculated gray value f(i,j) of the non-noise point is sorted, and the gray value f(i,j) of the non-noise point corresponding to the median point after sorting is used to replace the gray value of the noise point at the center of the local window.

[0015] Furthermore, the segmentation threshold in the improved Phansalkar local threshold method is calculated according to the following formula:

[0016]

[0017] In the formula, m represents the local mean; p and q are constants; s represents the local standard deviation; k is a user-defined parameter; represents the maximum value of the variances of all local windows.

[0018] Furthermore, the method further includes: after preprocessing the shipborne radar image, using a gray correction matrix to perform gray correction on the preprocessed image; specifically including: calculating the mean value of the pixel points in the row direction of the denoised image, and all the mean values form a column vector C1; copying the column vector C1 column by column to generate a gray correction matrix with the same size as the denoised image; then performing a subtraction operation on the denoised image and the gray correction matrix to obtain the gray-corrected image.

[0019] Further, the method further includes: after performing gray correction on the image, using a local contrast enhancement method to enhance the features of the oil film in the gray-corrected image; specifically including: decomposing the image into sub-windows of equal size; calculating the gray histogram of each sub-window; performing histogram adjustment in each sub-window: evenly distributing the pixels with an occurrence probability greater than the threshold β to other gray levels; performing equalization processing on the adjusted histogram; performing bilinear interpolation operation between sub-windows to generate the final contrast-enhanced image.

[0020] According to another aspect of the present invention, a navigation radar oil spill target segmentation system is also proposed. The system includes:

[0021] An image acquisition module configured to acquire an on-board radar image;

[0022] A preprocessing module configured to preprocess the on-board radar image; the preprocessing includes: performing convolution on the on-board radar image using a Laplacian operator; performing segmentation on the convolved image using the Otsu algorithm to extract co-frequency interference noise; performing mean filtering on the co-frequency interference noise to obtain a preliminary smoothed image; performing segmentation on the preliminary smoothed image using a gray threshold algorithm and a pixel area threshold method to extract block noise; performing smoothing on the block noise using a dynamic window and distance-weighted median filtering to obtain a denoised image;

[0023] A segmentation module configured to segment the denoised image using an improved Phansalkar local threshold method to extract the oil film.

[0024] Further, the smoothing of the block noise using the dynamic window and distance-weighted median filtering in the preprocessing module includes:

[0025] For each noise point of the block noise, taking this noise point as the center, selecting a dynamic local window with an n×n size, where n is greater than or equal to 3 and is an odd number; if the number of non-noise points in the dynamic local window with an n×n size is greater than the number of noise points, then perform noise point suppression; otherwise, set the size of the dynamic local window to (n + 2)×(n + 2), and repeat the above process until the number of non-noise points in the dynamic local window is not greater than the number of noise points and then stop;

[0026] When the number of non-noise points in the dynamic local window is greater than the number of noise points, calculate the new gray value f(i,j) of each non-noise point according to the distance weight respectively:

[0027]

[0028] where cell() is the ceiling function, and (i,j) is the position of the non-noise point in the local window, is the original gray value of the non-noise point (i, j) in the local window;

[0029] Sort the newly calculated gray values f(i, j) of the non-noise points, and replace the gray value f(i, j) of the non-noise point corresponding to the median point after sorting with the gray value of the noise point at the center of the local window.

[0030] Further, the segmentation threshold in the improved Phansalkar local threshold method in the segmentation module is calculated according to the following formula:

[0031]

[0032] In the formula, m represents the local mean; p and q are constants; s represents the local standard deviation; k is a user-defined parameter; represents the maximum value of the variances of all local windows.

[0033] Further, the system further includes: a gray correction module configured to perform gray correction on the preprocessed image by using a gray correction matrix; specifically including: calculating the mean value of the pixel points in the denoised image row by row, and all the mean values form a column vector C1; copying the column vector C1 column by column to generate a gray correction matrix of the same size as the denoised image; then performing a subtraction operation on the denoised image and the gray correction matrix to obtain the gray-corrected image.

[0034] Further, the system further includes: a feature enhancement module configured to perform feature enhancement on the oil film in the gray-corrected image by using a local contrast enhancement method; specifically including: decomposing the image into sub-windows of equal size; calculating the gray histogram of each sub-window; performing histogram adjustment in each sub-window: evenly distributing the pixels with an occurrence probability greater than the threshold β to other gray levels; performing equalization processing on the adjusted histogram; performing bilinear interpolation operation between the sub-windows to generate the final contrast-enhanced image.

[0035] The beneficial technical effects of the present invention are:

[0036] Traditional marine radar oil spill detection methods are vulnerable to noise interference, resulting in unclear distinction between the oil spill area and the background. The present invention proposes a marine radar oil spill target segmentation method and system, which can effectively suppress noise, making the characteristics of the oil spill target more prominent, thus significantly improving the accuracy of oil spill detection. The method of the present invention can not only effectively reduce the computational cost while ensuring high accuracy, but also meet the requirements of real-time or near-real-time detection, with significant application advantages. The present invention can effectively suppress the noise information in the radar image, improve the accuracy of oil spill detection, compress the data volume, and enhance the important features in the image, making the marine oil spill detection more accurate and efficient. The present invention can enhance the robustness to oil spill signals, enabling the model or algorithm to accurately identify the oil spill area even when the image is unclear, and solving the actual need for extracting effective areas in the field of oil spill detection in marine radar images. Description of the Drawings

[0037] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, where:

[0038] Figure 1 is a flowchart of a marine radar oil spill target segmentation method according to an embodiment of the present invention.

[0039] Figure 2 is a preprocessing flowchart in an embodiment of the present invention.

[0040] Figure 3 is an example diagram of the image after preprocessing in an embodiment of the present invention.

[0041] Figure 4 is an example diagram of the gray correction process in an embodiment of the present invention.

[0042] Figure 5 is an example diagram of the generated gray correction in an embodiment of the present invention.

[0043] Figure 6 is an example diagram of histogram adjustment during image contrast enhancement in an embodiment of the present invention; where (a) corresponds to the part where the gray value frequency is greater than the threshold β and is deleted; (b) corresponds to the pixels with the deleted gray values and the gray values are evenly distributed.

[0044] Figure 7 is an example diagram of oil film feature enhancement in an embodiment of the present invention.

[0045] Figure 8 is an example diagram of the final segmentation result in an embodiment of the present invention.

[0046] Figure 9It is a schematic structural diagram of an oil spill target segmentation system for marine radar according to an embodiment of the present invention. Detailed implementation manners

[0047] The principles and spirit of the present invention will be described below with reference to several exemplary implementation manners. It should be understood that these implementation manners are given only to enable those skilled in the art to better understand and then implement the present invention, rather than limiting the scope of the present invention in any way. On the contrary, these implementation manners are provided to make the present disclosure more thorough and complete, and to be able to convey the scope of the present disclosure completely to those skilled in the art.

[0048] Those skilled in the art know that the implementation manners of the present invention can be implemented as a system, a device, an equipment, a method, or a computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: completely hardware, completely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software. In this article, it should be understood that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0049] An embodiment of the present invention proposes an oil spill target segmentation method for marine radar, as Figure 1 shown. This method includes:

[0050] Step 1: Obtain a shipborne radar image;

[0051] Step 2: Preprocess the shipborne radar image; the preprocessing includes: performing convolution on the shipborne radar image using a Laplacian operator; segmenting the convolved image using the Otsu algorithm to extract co-frequency interference noise; smoothing the co-frequency interference noise using a mean filter window to obtain a preliminary smoothed image; segmenting the preliminary smoothed image using a gray-scale threshold algorithm and a pixel area threshold method to extract block noise; smoothing the block noise using a dynamic window and distance-weighted median filtering to obtain a denoised image;

[0052] Step 3: Perform gray-scale correction on the preprocessed image using a gray-scale correction matrix;

[0053] Step 4: Use a local contrast enhancement method to enhance the features of the oil film in the gray-scale corrected image;

[0054] Step 5: Segment the oil film in the feature-enhanced image using an improved Phansalkar local threshold method.

[0055] The method starts from Step 1. In Step 1, a shipborne radar image is obtained.

[0056] According to an embodiment of the present invention, multiple radar images containing oil spills are collected under the same voyage and the same sea conditions.

[0057] Then, step two is executed. In step two, the on-board radar images are preprocessed.

[0058] According to an embodiment of the present invention, the preprocessing process is as Figure 2 shown. The radar image after coordinate transformation is convolved with a Laplacian operator; the Otsu algorithm is used to segment the convolved image to extract co-frequency interference noise; mean filtering is used to smooth the co-frequency interference noise to obtain a preliminary smoothed image; the gray threshold algorithm and the pixel area threshold method are used to segment the preliminary smoothed image to extract block noise; dynamic window and distance-weighted median filtering are used to smooth the block noise to obtain a denoised image.

[0059] In the prior art, the Otsu algorithm and the pixel area threshold (200) can be used to extract block noise targets; a window with a size of 21×21 (the window size is slightly larger than twice the pixel area threshold in step 4) is used to perform median filtering on the block noise targets. The embodiment of the present invention proposes to use dynamic window and distance-weighted median filtering to suppress each pixel point of the block noise, so as to effectively improve the noise smoothing effect. The specific process includes:

[0060] For each noise point of the block noise, a dynamic local window with a size of n×n (n is greater than or equal to 3 and is an odd number) is selected with this noise point as the center; starting from a size of 3×3, if the number of non-noise points in this dynamic local window is greater than the number of noise points, the noise point can be directly suppressed; otherwise, the size of the dynamic local window is set to (n + 2)×(n + 2), and the above process is repeated until the number of non-noise points in the dynamic local window is not greater than the number of noise points and then stops;

[0061] When the number of non-noise points in the dynamic local window is greater than the number of noise points, the new gray value f(i,j) of each non-noise point is calculated according to the distance weight:

[0062] (1)

[0063] where cell() is the ceiling function, (i,j) is the position of the non-noise point in the local window, is the original gray value of the non-noise point (i,j) in the local window;

[0064] The newly calculated gray values f(i,j) of the non-noise points are sorted, and the gray value f(i,j) of the non-noise point corresponding to the median point after sorting is used to replace the gray value of the noise point at the center of the local window.

[0065] After the above preprocessing, a preprocessed image example with a size of 512×2048 pixels containing an oil spill sample is as Figure 3 shown.

[0066] Then, perform Step 3: Use the grayscale correction matrix to perform grayscale correction on the preprocessed image.

[0067] According to the embodiment of the present invention, the grayscale correction matrix is used to perform global grayscale smoothing processing on the image to eliminate the influence of background noise. The specific calculation process is as follows: Calculate the mean value of the denoised image M1 in the "row" direction to generate a column vector C1; then use the mean value in C1 to fill the grayscale correction matrix M2 with the same specification as M1; then perform a subtraction operation on the denoised image M1 and the grayscale correction matrix M2 to obtain the grayscale-corrected image.

[0068] An example is as Figure 4 shown. The denoised image M1 is a 4×4 matrix, and the mean value of each row is 17, 28, 63, and 75 respectively, forming a column vector C1; expand the column vector C1 into a 4×4 grayscale correction matrix M2, where the values of each row are the same and the values of each column are C1. An example of the grayscale-corrected image is as Figure 5 shown.

[0069] Then, perform Step 4: Use the local contrast enhancement method to enhance the features of the oil film in the grayscale-corrected image.

[0070] According to the embodiment of the present invention, the CLAHE (Contrast-limited Adaptive Histogram Equalization) algorithm is used to enhance the contrast of the image, thereby enhancing the contrast between the inside and outside regions of the oil film, as Figure 6 shown. The specific implementation process is as follows:

[0071] First, decompose the image into sub-windows of equal size; then, calculate the grayscale histogram of each sub-window; then perform histogram adjustment in each sub-window: evenly distribute the pixels with an occurrence probability greater than the threshold β to other gray levels to avoid over-enhancement of certain gray levels; then, perform equalization processing on the adjusted histogram to enhance the local contrast; finally, perform bilinear interpolation operation between the sub-windows to avoid the "block" effect and generate the final contrast-enhanced image. An example of the feature-enhanced image is as Figure 7 shown.

[0072] Then, perform Step 5. In Step 5, use the improved Phansalkar local threshold method to segment the oil film in the feature-enhanced image.

[0073] According to an embodiment of the present invention, Niblack proposed a local threshold method for digital image segmentation as follows:

[0074] (2)

[0075] where m is the local mean; is the local standard deviation; k is a user-defined parameter that takes a negative value. Sauvola modified the method for implementing adaptive document image binarization as follows:

[0076] (3)

[0077] where R is the dynamic range of the standard deviation, and the parameter k takes a positive value. Phansalskar modified the Sauvola method to handle low-contrast images as follows:

[0078] (4)

[0079] where p and q are constants. The value of q is higher than a specific value of the local average, and the exponential term becomes negligible. Phansalkar suggested k = 0.25, R = 0.5, p = 2, and q = 10.

[0080] An embodiment of the present invention proposes to improve R to: the maximum value of the variances of all local windows . Preferably, k = 0.85, and the local window size is 63×63 pixels.

[0081] (5)

[0082] The local window refers to a window with an m×m size centered on the pixel to be calculated, where m×m is, for example, 3×3 or 5×5. The process of calculating the local window variance is as follows: First, calculate the mean of the image gray values within the local window, and then calculate the average of the squared differences between the gray values and the mean. An example of the segmentation result is shown Figure 8 as follows.

[0083] Another embodiment of the present invention proposes a marine radar oil spill target segmentation system, as shown Figure 9 below. The system includes:

[0084] An image acquisition module 910 configured to acquire an on-board radar image;

[0085] A preprocessing module 920 configured to preprocess the shipborne radar image; the preprocessing includes: convolving the shipborne radar image using a Laplacian operator; segmenting the convolved image using an Otsu algorithm to extract co-frequency interference noise; smoothing the co-frequency interference noise using mean filtering to obtain a preliminary smoothed image; segmenting the preliminary smoothed image using a gray threshold algorithm and a pixel area threshold method to extract block noise; smoothing the block noise using a dynamic window and distance-weighted median filtering to obtain a denoised image;

[0086] A segmentation module 930 configured to segment the denoised image using an improved Phansalkar local threshold method to extract an oil film.

[0087] In this embodiment, preferably, the smoothing of the block noise using a dynamic window and distance-weighted median filtering in the preprocessing module 920 includes:

[0088] For each noise point of the block noise, taking this noise point as the center, a dynamic local window with an n×n size is selected, where n is greater than or equal to 3 and is an odd number; if the number of non-noise points in the dynamic local window with an n×n size is greater than the number of noise points, noise point suppression is performed; otherwise, the size of the dynamic local window is set to (n + 2)×(n + 2), and the above process is repeated until the number of non-noise points in the dynamic local window is not greater than the number of noise points and then stops;

[0089] When the number of non-noise points in the dynamic local window is greater than the number of noise points, the new gray value f(i,j) of each non-noise point is calculated according to the distance weight:

[0090]

[0091] where cell() is the ceiling function, (i,j) is the position of the non-noise point in the local window, is the original gray value of the non-noise point (i,j) in the local window;

[0092] The newly calculated gray values f(i,j) of the non-noise points are sorted, and the gray value f(i,j) corresponding to the median point after sorting is used to replace the gray value of the noise point at the center of the local window.

[0093] In this embodiment, preferably, the segmentation threshold in the improved Phansalkar local threshold method in the segmentation module 930 is calculated according to the following formula:

[0094]

[0095] In the formula, m represents the local mean; p and q are constants, and the value of q is higher than a specific value of m; represents the local standard deviation; k is a user-defined parameter; represents the maximum value of all local window variances.

[0096] In this embodiment, preferably, the system further includes: a grayscale correction module 940, which is configured to perform grayscale correction on the preprocessed image by using a grayscale correction matrix; specifically including: calculating the mean value of the pixel points in the denoised image row by row, and all the mean values form a column vector C1; copying the column vector C1 column by column to generate a grayscale correction matrix of the same size as the denoised image; and then performing a subtraction operation on the denoised image and the grayscale correction matrix to obtain the grayscale-corrected image.

[0097] In this embodiment, preferably, the system further includes: a feature enhancement module 950, which is configured to perform feature enhancement on the oil film in the grayscale-corrected image by using a local contrast enhancement method; specifically including: decomposing the image into sub-windows of equal size; calculating the grayscale histogram of each sub-window; performing histogram adjustment in each sub-window: evenly distributing the pixels with an occurrence probability greater than the threshold β to other gray levels; performing equalization processing on the adjusted histogram; and performing bilinear interpolation operation between the sub-windows to generate the final contrast-enhanced image.

[0098] For the unspecified parts of a navigation radar oil spill target segmentation system according to an embodiment of the present invention, please also refer to the above specific description of the method embodiment.

[0099] The method of the present invention can be executed in an electronic device. The electronic device can be any device with storage and computing capabilities, which can be implemented as, for example, a server, a workstation, etc., or can be implemented as a personal-configured computer such as a desktop computer, a notebook computer, or can be implemented as a terminal device such as a mobile phone, a tablet computer, a smart wearable device, an Internet of Things device, etc., but is not limited thereto.

[0100] An electronic device may include: a processor, a memory, an input / output interface, a communication interface, and a bus. Among them, the processor, the memory, the input / output interface, and the communication interface are communicatively connected to each other inside the electronic device through the bus. The processor may be implemented in the form of a general-purpose CPU, a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification. The memory may be implemented in the form of ROM, RAM, a static storage device, a dynamic storage device, etc. The memory may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory and are called and executed by the processor. The input / output interface is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the electronic device or externally connected to the electronic device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc. The communication interface is used to connect to a communication module to implement communication interaction between this electronic device and other devices. Among them, the communication module may implement communication in a wired manner or in a wireless manner. The bus includes a path for transmitting information between various components of the electronic device.

[0101] An embodiment of the present invention also provides a non-transitory readable storage medium that stores instructions for causing the electronic device to execute the method according to the embodiments of the present invention. The readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information may be computer-readable instructions, data structures, program modules, or other data. Examples of the readable storage medium include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage, etc.

[0102] It should be noted that the terms used in the present invention are only for describing specific embodiments and do not limit the scope of the present application. As shown in the specification of the present invention, unless the context clearly indicates an exceptional situation, words such as "a", "an", "one kind" and / or "the" do not specifically refer to the singular and may also include the plural. The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method or device comprising a series of elements not only includes those elements but also other elements not explicitly listed, or further includes elements inherent to such a process, method or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of another identical element in the process, method or device comprising the said element.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for segmenting oil spill targets of a marine radar, characterized in that, Including: Obtain an on-board radar image; Preprocess the on-board radar image; the preprocessing includes: performing convolution on the on-board radar image using a Laplacian operator; performing segmentation on the convolved image using the Otsu algorithm to extract co-frequency interference noise; performing mean filtering on the co-frequency interference noise to obtain a preliminary smoothed image; performing segmentation on the preliminary smoothed image using a gray threshold algorithm and a pixel area threshold method to extract block noise; performing smoothing on the block noise using a dynamic window and distance-weighted median filtering to obtain a denoised image, including: For each noise point of the blocky noise, centered on this noise point, select n × n a dynamic local window of size, where n is greater than or equal to 3 and is odd; if n × n the number of non-noise points in the dynamic local window of size is greater than the number of noise points, then perform noise point suppression; otherwise, set the size of the dynamic local window to ([[]] n + 2) × ( n + 2), repeat the above process until the number of non-noise points in the dynamic local window is not greater than the number of noise points and then stop; When the number of non-noise points in the dynamic local window is greater than the number of noise points, calculate the new gray value of each non-noise point according to the distance weight respectively f ( i , j ): ； where cell() is the ceiling function, ( i , j ) is the position of non-noise points in the local window, is the original gray value of the non-noise point ([[]] i , j ) in the local window; The newly calculated gray values of non-noise points f ( i , j ) are sorted, and the gray value of the non-noise point corresponding to the median point after sorting f ( i , j ) is replaced with the gray value of the noise point at the center of the local window; Using an improved Phansalkar local threshold method to segment the denoised image to extract an oil film.

2. The method for segmenting oil spill targets of a marine radar according to claim 1, wherein The segmentation threshold in the improved Phansalkar local threshold method is calculated according to the following formula: ； In the formula, m represents the local mean; p and q are constants; represents the local standard deviation; k is a user-defined parameter; represents the maximum value of all local window variances.

3. A method for segmenting oil spill targets of a marine radar according to claim 1, characterized in that, The method further includes: after preprocessing the on-board radar image, performing gray correction on the preprocessed image using a gray correction matrix; specifically including: calculating the mean value of pixel points in the denoised image row by row, and all the mean values form a column vector C1; copying the column vector C1 column by column to generate a gray correction matrix of the same size as the denoised image; then performing a subtraction operation on the denoised image and the gray correction matrix to obtain a gray-corrected image.

4. A method for segmenting oil spill targets of a marine radar according to claim 3, characterized in that The method further includes: after performing gray correction on the image, using a local contrast enhancement method to enhance the features of the oil film in the gray-corrected image; specifically including: decomposing the image into sub-windows of equal size; calculating the gray histogram of each sub-window; performing histogram adjustment in each sub-window: evenly distributing the pixels with an occurrence probability greater than the threshold β to other gray levels; performing equalization processing on the adjusted histogram; performing bilinear interpolation operation between sub-windows to generate a final contrast-enhanced image.

5. A navigation radar oil spill target segmentation system, characterized in that, Including: An image acquisition module configured to obtain an on-board radar image; A preprocessing module configured to preprocess the on-board radar image; The preprocessing includes: performing convolution on the on-board radar image using a Laplacian operator; performing segmentation on the convolved image using the Otsu algorithm to extract co-frequency interference noise; performing mean filtering on the co-frequency interference noise to obtain a preliminary smoothed image; performing segmentation on the preliminary smoothed image using a gray threshold algorithm and a pixel area threshold method to extract block noise; performing smoothing on the block noise using a dynamic window and distance-weighted median filtering to obtain a denoised image, including: For each noise point of the blocky noise, centered on this noise point, select n × n a dynamic local window of size, where n is greater than or equal to 3 and is odd; if n × n the number of non-noise points in the dynamic local window of size is greater than the number of noise points, then noise point suppression is performed; otherwise, set the dynamic local window size to ([[]] n +2)×([[]] n +2), repeat the above process until the number of non-noise points in the dynamic local window is not greater than the number of noise points and then stop; When the number of non-noise points in the dynamic local window is greater than the number of noise points, calculate the new grayscale value of each non-noise point according to the distance weight respectively f ( i , j ): ； where cell() is the ceiling function, ( i , j ) is the position of non-noise points in the local window, is the original gray value of the non-noise point ( i , j ) in the local window; The newly calculated gray values of non-noise points f ( i , j ) are sorted, and the gray value of the non-noise point corresponding to the median point after sorting f ( i , j ) is replaced with the gray value of the noise point at the center of the local window; A segmentation module configured to use an improved Phansalkar local threshold method to segment the denoised image to extract an oil film.

6. The oil spill target segmentation system for marine radar according to claim 5, wherein The segmentation threshold in the improved Phansalkar local threshold method in the segmentation module is calculated according to the following formula: ； In the formula, m represents the local mean; p and q are constants; represents the local standard deviation; k is a user-defined parameter; represents the maximum value of all local window variances.

7. The oil spill target segmentation system for marine radar according to claim 5, characterized in that The system further includes: a grayscale correction module configured to perform grayscale correction on the preprocessed image by using a grayscale correction matrix; specifically including: calculating the mean value of pixel points in the denoised image row by row, and all the mean values form a column vector C1; copying the column vector C1 column by column to generate a grayscale correction matrix of the same size as the denoised image; and then performing a subtraction operation on the denoised image and the grayscale correction matrix to obtain the grayscale-corrected image.

8. The oil spill target segmentation system for marine radar according to claim 7, wherein, The system further includes: a feature enhancement module configured to perform feature enhancement on the oil film in the grayscale-corrected image by using a local contrast enhancement method; specifically including: decomposing the image into sub-windows of equal size; calculating the grayscale histogram of each sub-window; performing histogram adjustment in each sub-window: evenly distributing the pixels with an occurrence probability greater than the threshold β to other gray levels; performing equalization processing on the adjusted histogram; and performing bilinear interpolation operation between the sub-windows to generate the final contrast-enhanced image.

Images