Ocean detection image processing method

Abstract

The invention discloses a marine detection image processing method, and relates to the technical field of image processing, and the method comprises the following steps: S1, collecting an initial detection image of a marine ranch through an image sensor, and obtaining a stable inhibition coefficient of the initial detection image; s2, constructing a global suppression processing model for the initial detection image; and S3, processing the initial detection image by using the global suppression processing model to obtain a final ocean detection image. The invention provides an ocean detection image processing method, which comprises the following steps of: before an initial detection image is input into a global suppression processing model, extracting an accompanying pixel point set of the initial detection image to obtain a stable suppression coefficient representing a relatively important pixel point condition; the stable suppression coefficient is used as one of the input parameters of the global suppression processing model, so that the model can carry out targeted expansion processing on the initial detection image, thereby improving the quality of the detection image, and providing effective support for resource evaluation of the marine ranch.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for processing ocean detection images. Background Art

[0002] Marine ranching refers to the use of large-scale fishery facilities and a systematic management system within a defined sea area, leveraging the natural marine ecosystem to gather commercially released marine organisms. Similar to grazing cattle and sheep on land, marine resources such as fish, shrimp, shellfish, and algae are systematically and purposefully stocked at sea. Currently, marine ranching is primarily monitored through regular manual inspections and fixed-point measurements using buoys. However, these two methods lack the ability to capture underwater images, cannot fully meet the data types and volumes required for the digital ocean, and cannot provide aquaculture personnel with a comprehensive understanding of underwater conditions. Furthermore, the image clarity captured by existing image sensors needs to be further improved. Summary of the Invention

[0003] In order to solve the above problems, the present invention proposes a method for processing ocean detection images.

[0004] The technical solution of the present invention is: a method for processing ocean detection images comprises the following steps:

[0005] S1. Collecting an initial detection image of the marine ranch through an image sensor to obtain a stable suppression coefficient of the initial detection image;

[0006] S2, building a global suppression processing model for the initial detection image;

[0007] S3. According to the stable suppression coefficient of the initial detection image, the global suppression processing model is used to process the initial detection image to obtain the final ocean detection image.

[0008] Furthermore, S1 includes the following sub-steps:

[0009] S11, collecting an initial detection image of the ocean ranch through an image sensor, and determining a head pixel point of the initial detection image;

[0010] S12, determining a set of accompanying pixel points of the head pixel point in the initial detection image;

[0011] S13. Determine a stable suppression coefficient of the initial detection image based on the head pixel point and the accompanying pixel point set.

[0012] The beneficial effect of the above further scheme is: in the present invention, the initial detection image contains a large number of pixels with low pixel quality, which are easy to interfere with image processing. Therefore, before the initial detection image is input into the global suppression processing model, the pixels with low quality are first screened, and the set of accompanying pixels obtained by screening is used to obtain a stable suppression coefficient as the characteristic value of the initial detection image, which is conducive to the subsequent global suppression processing model to complete image processing in a targeted manner.

[0013] Furthermore, in S11, the pixel point with the maximum pixel value is used as the head pixel point.

[0014] Furthermore, in S12, the accompanying pixel set of the head pixel The calculation formula is:

[0015] ;

[0016] Where, Indicates the number of pixels in the companion pixel set The pixel value of each pixel, Represents the pixel value of the head pixel of the initial detection image, Represents an exponent.

[0017] Furthermore, in S13, the stable suppression coefficient of the initial detection image is The calculation formula is:

[0018] ;

[0019] Where, Indicates the number of pixels in the companion pixel set The pixel value of each pixel, Represents the pixel value of the head pixel of the initial detection image, Indicates the number of pixels accompanying the pixel set, Indicates the maximum value operation, Indicates minimum operation.

[0020] Furthermore, in S2, the global suppression processing model includes a first convolutional layer, a second convolutional layer, a scaling layer, an adder, and a feature enhancement layer;

[0021] The input end of the first convolutional layer serves as the first input end of the global inhibition processing model; the output end of the first convolutional layer is connected to the input end of the scaling layer; the output end of the scaling layer is connected to the first input end of the adder; the input end of the second convolutional layer serves as the second input end of the global inhibition processing model; the first output end of the second convolutional layer is connected to the second input end of the adder; the second output end of the second convolutional layer is connected to the first input end of the feature enhancement layer; the output end of the adder is connected to the second input end of the feature enhancement layer; and the output end of the feature enhancement layer serves as the output end of the global inhibition processing model.

[0022] The beneficial effect of the above further scheme is: in the present invention, the first convolution layer is used to extract features from the initial detection image to obtain a feature map for each pixel point. Each feature map can be used as the image feature of the pixel point, and the feature map is scaled using the scaling layer. The second convolution layer is used to extract the Sobel operator for each pixel point in the initial detection image. The Sobel operator can be used for edge detection to minimize the influence of edge pixels in the input of the adder. The adder is used to fuse the features extracted by the two convolution layers and input them into the feature enhancement layer for pixel enhancement. The feature enhancement layer is used to train the features of the two convolution layers, which is beneficial to improving image quality.

[0023] Furthermore, the expression of the scaling layer is:

[0024] ;

[0025] Where, represents the output of the scaling layer, represents the stable suppression coefficient of the initial detection image, represents the logarithmic function, represents the first output of the first convolutional layer, represents the first convolutional layer outputs, represents the first convolutional layer outputs.

[0026] Furthermore, the expression of the adder is:

[0027] ;

[0028] Where, represents the output of the adder, represents the output of the scaling layer, Indicates the maximum value operation, Indicates rounding up operation. represents the first output of the second convolutional layer, represents the second convolutional layer outputs, represents the second convolutional layer outputs.

[0029] In the expression of the adder, the first and second output terminals of the second convolutional layer both output the same content. The second convolutional layer contains multiple convolution kernels, each of which corresponds to one output.

[0030] Furthermore, the expression of the feature enhancement layer is:

[0031] ;

[0032] Where, represents the output of the feature enhancement layer, represents the output of the adder, Indicates rounding up operation. represents the first output of the second convolutional layer, represents the second convolutional layer outputs, represents the second convolutional layer outputs, represents the weight of the first output of the second convolutional layer, represents the second convolutional layer The weight of the output, represents the weight of the K-th output of the second convolutional layer, Represents the activation function.

[0033] The weight of an output in the second convolutional layer is the ratio of the output to the sum of the total outputs.

[0034] The beneficial effects of the present invention are: the present invention proposes a method for processing ocean detection images, which extracts a set of accompanying pixel points of the initial detection image before inputting the initial detection image into the global suppression processing model to obtain a stable suppression coefficient that characterizes the situation of more important pixel points; using the stable suppression coefficient as one of the input parameters of the global suppression processing model can enable the model to process the initial detection image in a targeted manner, thereby improving the quality of the detection image and providing effective support for the resource assessment of marine ranches. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of the ocean exploration image processing method;

[0036] Figure 2 Schematic diagram of the structure of the global inhibition processing model. DETAILED DESCRIPTION

[0037] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0038] like Figure 1As shown, the present invention provides a method for processing ocean detection images, comprising the following steps:

[0039] S1. Collecting an initial detection image of the marine ranch through an image sensor to obtain a stable suppression coefficient of the initial detection image;

[0040] S2, building a global suppression processing model for the initial detection image;

[0041] S3. According to the stable suppression coefficient of the initial detection image, the global suppression processing model is used to process the initial detection image to obtain the final ocean detection image.

[0042] In this embodiment of the present invention, S1 includes the following sub-steps:

[0043] S11, collecting an initial detection image of the ocean ranch through an image sensor, and determining a head pixel point of the initial detection image;

[0044] S12, determining a set of accompanying pixel points of the head pixel point in the initial detection image;

[0045] S13. Determine a stable suppression coefficient of the initial detection image based on the head pixel point and the accompanying pixel point set.

[0046] In the present invention, the initial detection image contains a large number of pixels with low pixel quality, which are easy to interfere with image processing. Therefore, before the initial detection image is input into the global suppression processing model, the pixels with low quality are first screened, and the set of accompanying pixel points obtained by screening is used to obtain a stable suppression coefficient as the characteristic value of the initial detection image, which is conducive to the subsequent global suppression processing model to complete image processing in a targeted manner.

[0047] In the embodiment of the present invention, in S11, the pixel point with the maximum pixel value is used as the head pixel point.

[0048] In the embodiment of the present invention, in S12, the companion pixel set of the head pixel is The calculation formula is:

[0049] ;

[0050] Where, Indicates the number of pixels in the companion pixel set The pixel value of each pixel, Represents the pixel value of the head pixel of the initial detection image, Represents an exponent.

[0051] In the embodiment of the present invention, in S13, the stable suppression coefficient of the initial detection image The calculation formula is:

[0052] ;

[0053] Where, Indicates the number of pixels in the companion pixel set The pixel value of each pixel, Represents the pixel value of the head pixel of the initial detection image, Indicates the number of pixels accompanying the pixel set, Indicates the maximum value operation, Indicates minimum operation.

[0054] In the embodiment of the present invention, in S2, as Figure 2 As shown, the global inhibition processing model includes a first convolutional layer, a second convolutional layer, a scaling layer, an adder, and a feature enhancement layer;

[0055] The input end of the first convolutional layer serves as the first input end of the global inhibition processing model; the output end of the first convolutional layer is connected to the input end of the scaling layer; the output end of the scaling layer is connected to the first input end of the adder; the input end of the second convolutional layer serves as the second input end of the global inhibition processing model; the first output end of the second convolutional layer is connected to the second input end of the adder; the second output end of the second convolutional layer is connected to the first input end of the feature enhancement layer; the output end of the adder is connected to the second input end of the feature enhancement layer; and the output end of the feature enhancement layer serves as the output end of the global inhibition processing model.

[0056] In the present invention, the first convolutional layer is used to extract features from the initial detection image to obtain a feature map for each pixel. Each feature map can be used as the image feature of the pixel, and the feature map is scaled using a scaling layer. The second convolutional layer is used to extract the Sobel operator for each pixel in the initial detection image. The Sobel operator can be used for edge detection to minimize the influence of edge pixels in the adder input. The adder is used to fuse the features extracted by the two convolutional layers and input them into the feature enhancement layer for pixel enhancement. The feature enhancement layer is used to train the features of the two convolutional layers, which is beneficial to improving image quality.

[0057] In the embodiment of the present invention, the expression of the scaling layer is:

[0058] ;

[0059] Where, represents the output of the scaling layer, represents the stable suppression coefficient of the initial detection image, represents the logarithmic function, represents the first output of the first convolutional layer, represents the first convolutional layer outputs, represents the first convolutional layer outputs.

[0060] In the embodiment of the present invention, the expression of the adder is:

[0061] ;

[0062] Where, represents the output of the adder, represents the output of the scaling layer, Indicates the maximum value operation, Indicates rounding up operation. represents the first output of the second convolutional layer, represents the second convolutional layer outputs, represents the second convolutional layer outputs.

[0063] In the expression of the adder, the first and second output terminals of the second convolutional layer both output the same content. The second convolutional layer contains multiple convolution kernels, each of which corresponds to one output.

[0064] In the embodiment of the present invention, the expression of the feature enhancement layer is:

[0065] ;

[0066] Where, represents the output of the feature enhancement layer, represents the output of the adder, Indicates rounding up operation. represents the first output of the second convolutional layer, represents the second convolutional layer outputs, represents the second convolutional layer outputs, represents the weight of the first output of the second convolutional layer, represents the second convolutional layer The weight of the output, represents the weight of the K-th output of the second convolutional layer, Represents the activation function.

[0067] The weight of an output in the second convolutional layer is the ratio of the output to the sum of the total outputs.

[0068] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. A method for processing ocean detection images, characterized in that: The following steps are involved: S1. Collecting an initial detection image of the ocean ranch through an image sensor to obtain a stable suppression coefficient of the initial detection image; S2, building a global inhibition processing model for the initial detection image; S3. According to the stable suppression coefficient of the initial detection image, the initial detection image is processed using the global suppression processing model to obtain the final ocean detection image.

2. The ocean exploration image processing method according to claim 1, characterized in that: The S1 comprises the following sub-steps: S11, collecting an initial detection image of the ocean ranch through an image sensor, and determining a head pixel point of the initial detection image; S12, determining a set of companion pixels of a head pixel in the initial detection image; S13. Determine a stable suppression coefficient of the initial detection image according to the head pixel point and the accompanying pixel point set.

3. The ocean exploration image processing method according to claim 2, characterized in that: In S11, the pixel point with the maximum pixel value is used as the head pixel point.

4. The method for processing ocean detection images according to claim 2, characterized in that: In S12, the companion pixel set of the head pixel The calculation formula is: ； In the formula, Indicates the number of companion pixels in the set The pixel value of a pixel, represents the pixel value of the head pixel of the initial detection image, Represents an exponent.

5. The method for processing ocean detection images according to claim 2, characterized in that: In S13, the stable suppression coefficient of the initial detection image The calculation formula is: ； In the formula, Indicates the number of companion pixels in the set The pixel value of a pixel, represents the pixel value of the head pixel of the initial detection image, represents the number of pixels in the companion pixel set, Indicates the maximum value operation, Represents the minimum operation.

6. The method for processing ocean detection images according to claim 1, characterized in that: In S2, the global suppression processing model includes a first convolutional layer, a second convolutional layer, a scaling layer, an adder, and a feature enhancement layer; The input end of the first convolutional layer is used as the first input end of the global inhibition processing model; the output end of the first convolutional layer is connected to the input end of the scaling layer; the output end of the scaling layer is connected to the first input end of the adder; The input end of the second convolutional layer serves as the second input end of the global inhibition processing model; the first output end of the second convolutional layer is connected to the second input end of the adder; the second output end of the second convolutional layer is connected to the first input end of the feature enhancement layer; the output end of the adder is connected to the second input end of the feature enhancement layer; the output end of the feature enhancement layer serves as the output end of the global inhibition processing model.

7. The ocean exploration image processing method according to claim 6, characterized in that: The expression of the scaling layer is: ； In the formula, represents the output of the scaling layer, represents the stable suppression coefficient of the initial detection image, represents the logarithmic function, represents the first output of the first convolutional layer, represents the first convolutional layer outputs, represents the first convolutional layer outputs.

8. The method for processing ocean detection images according to claim 6, characterized in that: The expression of the adder is: ； In the formula, represents the output of the adder, represents the output of the scaling layer, represents the maximum value operation, Indicates rounding up operation. represents the first output of the second convolutional layer, represents the second convolutional layer outputs, represents the second convolutional layer outputs.

9. The method for processing ocean detection images according to claim 6, characterized in that: The expression of the feature enhancement layer is: ； In the formula, represents the output of the feature enhancement layer, represents the output of the adder, Indicates rounding up operation. represents the first output of the second convolutional layer, represents the second convolutional layer outputs, represents the second convolutional layer outputs, represents the weight of the first output of the second convolutional layer, represents the second convolutional layer The weight of the output, represents the weight of the Kth output of the second convolutional layer, Represents the activation function.

Images