Methods, systems, electronic devices and storage media for underwater image processing

Abstract

This application relates to a method, system, electronic device, and storage medium for underwater image processing. The method involves performing color difference correction and dynamic mapping on the original underwater image to obtain a dynamically mapped underwater image; eliminating noise in the dynamically mapped underwater image; acquiring the dark channel image of the denoised underwater image; obtaining the background light value based on the dark channel image and the original underwater image; obtaining the transmittance transfer function based on the dark channel image and the background light value; performing guided filtering on the transmittance transfer function to obtain a transmittance map; and inputting the transmittance map into an underwater image imaging model to obtain a restored underwater image. In other words, through a series of processes such as color difference correction and dynamic mapping, the method improves the color richness of the image, achieves brightness correction, and improves algorithm performance. It solves the problems of computationally intensive and cumbersome underwater image enhancement methods in related technologies, which suffer from poor image enhancement effects and are unsuitable for real-time underwater image enhancement.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to methods, systems, electronic devices, and storage media for underwater image processing. Background Technology

[0002] The development and utilization of nuclear energy is of great strategic significance to my country's energy security and energy transition, and safe operation has always been the foundation of nuclear energy development. Thermocouples, as key components in the reactor core measurement system (RIC), are used to measure temperature. If thermocouples are defective, temperature measurements will be inaccurate, seriously affecting operators' monitoring of the reactor core status and posing a significant threat to the safe and stable operation of nuclear power plants. Therefore, it is necessary to detect surface defects in thermocouples. However, RIC thermocouples are located in a boric acid pool, and detection must be carried out in a boric acid solution. This presents challenges such as difficult detection environments, harsh imaging conditions, and image color distortion, making it difficult to meet the high-quality image requirements for thermocouple surface defect detection. Furthermore, underwater image enhancement methods in related technologies are computationally complex, computationally intensive, and produce poor image enhancement results, making them unsuitable for real-time underwater image enhancement. They also require multiple encoding and decoding calculations, which is cumbersome.

[0003] Current underwater image enhancement methods suffer from high computational complexity, cumbersome calculations, and poor image enhancement results, making them unsuitable for real-time underwater image enhancement. No effective solution has yet been proposed. Summary of the Invention

[0004] This application provides a method, system, electronic device, and storage medium for underwater image processing, which at least solves the problems of underwater image enhancement methods in the related art, which are computationally intensive, cumbersome, and have poor image enhancement effects, and are not suitable for real-time underwater image enhancement.

[0005] In a first aspect, embodiments of this application provide a method for underwater image processing, the method comprising:

[0006] Acquire the original underwater image, perform color difference correction on the original underwater image, and obtain the corrected underwater image;

[0007] The corrected underwater image is dynamically mapped to obtain a dynamically mapped underwater image.

[0008] The noise in the dynamically mapped underwater image is eliminated to obtain a denoised underwater image;

[0009] Obtain the dark channel image of the denoised underwater image, and obtain the background light value based on the dark channel image and the original underwater image;

[0010] Based on the dark channel image and the background light value, the transmittance transfer function is obtained, and the transmittance transfer function is subjected to guided filtering to obtain a transmittance map.

[0011] The transmittance map is input into the underwater image imaging model to obtain the underwater reconstruction image.

[0012] In some embodiments, after obtaining the transmittance transfer function, the method further includes:

[0013] The transmittance transfer function is corrected by using the mean of the dark channel image to obtain the corrected transmittance transfer function.

[0014] The modified transmittance transfer function is subjected to guided filtering to obtain the modified transmittance map.

[0015] The corrected transmittance map is input into the underwater image imaging model to obtain the final underwater reconstruction image.

[0016] In some embodiments, obtaining the background light value based on the dark channel image and the original underwater image includes:

[0017] The pixel with the highest grayscale value of 0.1% in the dark channel image corresponds to the pixel with the highest grayscale value in the original underwater image, which is the background light value.

[0018] In some embodiments, color difference correction is performed on the original underwater image to obtain a corrected underwater image, including:

[0019] The color difference correction includes color adjustment and spatial domain adjustment. The original underwater image is subjected to color adjustment and spatial domain adjustment to obtain the corrected underwater image.

[0020] In some embodiments, dynamically mapping the corrected underwater image to obtain a dynamically mapped underwater image includes:

[0021] The three image channels of the corrected underwater image are dynamically mapped to obtain three channel images, and the three channel images are synthesized to obtain the dynamically mapped underwater image.

[0022] In some embodiments, the three image channels of the corrected underwater image are dynamically mapped to obtain a dynamically mapped underwater image, including:

[0023] Acquire the R-channel image, G-channel image, and B-channel image of the corrected underwater image;

[0024] The R-channel image, the G-channel image, and the B-channel image are dynamically mapped respectively to obtain the R-channel mapped image, the G-channel mapped image, and the B-channel mapped image;

[0025] The R-channel mapped image, the G-channel mapped image, and the B-channel mapped image are synthesized to obtain the dynamically mapped underwater image.

[0026] In some embodiments, inputting the transmittance map into an underwater image imaging model to obtain an underwater reconstructed image includes:

[0027]

[0028] in, The underwater reconstructed image, The denoised underwater image, The background light value, This is the transmittance diagram.

[0029] Secondly, embodiments of this application provide an underwater image processing system, the system comprising a first acquisition module, a mapping module, a denoising module, a second acquisition module, a filtering module, and a restoration module.

[0030] The first acquisition module is used to acquire the original underwater image, perform color difference correction on the original underwater image, and obtain the corrected underwater image;

[0031] The mapping module is used to dynamically map the corrected underwater image to obtain a dynamically mapped underwater image.

[0032] The denoising module is used to eliminate noise from the dynamically mapped underwater image to obtain a denoised underwater image.

[0033] The second acquisition module is used to acquire the dark channel image of the denoised underwater image, and obtain the background light value based on the dark channel image and the original underwater image;

[0034] The filtering module is used to obtain a transmittance transfer function based on the dark channel image and the background light value, and to perform guided filtering on the transmittance transfer function to obtain a transmittance map.

[0035] The restoration module is used to input the transmittance map into the underwater image imaging model to obtain an underwater restored image.

[0036] Thirdly, embodiments of this application provide an electronic device including 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 underwater image processing method as described in the first aspect above.

[0037] Fourthly, embodiments of this application provide a storage medium storing a computer program that, when executed by a processor, implements the underwater image processing method as described in the first aspect above.

[0038] Compared to related technologies, the underwater image processing method provided in this application involves acquiring an original underwater image, performing color difference correction on the original underwater image to obtain a corrected underwater image, performing dynamic mapping on the corrected underwater image to obtain a dynamically mapped underwater image, eliminating noise in the dynamically mapped underwater image to obtain a denoised underwater image, acquiring the dark channel image of the denoised underwater image, obtaining the background light value based on the dark channel image and the original underwater image, obtaining the transmittance transfer function based on the dark channel image and the background light value, performing guided filtering on the transmittance transfer function to obtain a transmittance map, and inputting the transmittance map into an underwater image imaging model to obtain an underwater restored image. In other words, through a series of processes such as color difference correction and dynamic mapping, the method improves the color richness of the image, achieves brightness correction, improves algorithm performance, and solves the problems of related underwater image enhancement methods, which are computationally intensive, cumbersome, and have poor image enhancement effects, making them unsuitable for real-time underwater image enhancement. Attached Figure Description

[0039] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0040] Figure 1 This is a schematic diagram illustrating the application environment of the underwater image processing method according to an embodiment of this application;

[0041] Figure 2 This is a flowchart of an underwater image processing method according to an embodiment of this application;

[0042] Figure 3 This is a flowchart of another underwater image processing method according to an embodiment of this application;

[0043] Figure 4 This is a structural block diagram of an underwater image processing system according to an embodiment of this application. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application. Furthermore, it is understood that although the efforts made in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, modifications to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0045] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0046] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application means two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The terms “first,” “second,” “third,” etc., used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0047] The underwater image processing method provided in this application can be applied to, for example... Figure 1The application environment shown is an underwater thermocouple detection system. Figure 1 This is a schematic diagram illustrating the application environment of the underwater image processing method according to an embodiment of this application, such as... Figure 1 As shown, the underwater thermocouple inspection system mainly consists of a light source, an image sensor, an underwater radiation-resistant precision-targeting mobile platform, and a host computer. When the host computer is executed by the processor, it implements an underwater image processing method. The light source provides appropriate illumination conditions, and the image sensor captures the original underwater image of the surface of the object under inspection. The underwater thermocouple inspection system can also have a built-in gimbal device for adjusting the shooting angle. The underwater thermocouple inspection system is mounted on the underwater radiation-resistant precision-targeting mobile platform, which accurately transports it to the location to be inspected. The underwater thermocouple inspection system in this embodiment enhances the quality of the original underwater image, solving the problem of image color distortion caused by the harsh imaging environment due to the thermocouple being located in a boric acid pool, and meeting the requirements for high-quality images for thermocouple surface defect detection.

[0048] This embodiment provides a method for underwater image processing. Figure 2 This is a flowchart of an underwater image processing method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0049] Step S201: Acquire the original underwater image, perform color difference correction on the original underwater image, and obtain the corrected underwater image. In this embodiment, due to factors such as light source and acquisition equipment, the acquired original underwater image may be distorted in color, which seriously affects the process of restoring the image. Therefore, color difference correction should be performed on the original underwater image to eliminate the impact of color distortion.

[0050] Step S202: Dynamically map the corrected underwater image to obtain a dynamically mapped underwater image. In this embodiment, by dynamically mapping the corrected underwater image, the dynamic range of the tone of the corrected underwater image is mapped to an appropriate range, thereby further improving the image quality.

[0051] Step S203: Eliminate noise in the dynamically mapped underwater image to obtain a denoised underwater image. In this embodiment, while eliminating the influence of noise, it is also necessary to retain image detail information as much as possible. Therefore, a bilateral filtering method can be used to improve the image signal-to-noise ratio, and then the edge texture details can be preserved by introducing differences in the pixel neighborhood.

[0052] The processing of pixels by bilateral filtering is shown in Formula 1 below:

[0053] Formula 1

[0054] in, The underwater image after denoising. These are the position coordinates of the pixel. The center point is indicated as A field, the size of 1 pixel, Indicates the range of values ​​for a pixel. For the dynamically mapped underwater image, after filtering, the gray value of a pixel is equivalent to the weighted average of the pixel values ​​in its neighborhood, with the weighting coefficients... In the formula:

[0055]

[0056]

[0057] in, It is the spatial proximity factor. It is the gray-scale similarity factor. For spatial filtering kernel, For grayscale filtering kernel, For grayscale and Similar points, yes A point-based image model.

[0058] Step S204: Obtain the dark channel image of the denoised underwater image, and obtain the background light value based on the dark channel image and the original underwater image; in this embodiment, the dark channel image is obtained from the denoised underwater image as shown in Formula 2 below:

[0059] Formula 2

[0060] in, For dark channel images, These represent the three channels of the image. For the subset of pixels participating in the calculation, This is the underwater image after noise reduction.

[0061] After obtaining the dark channel image, the pixel with the highest grayscale value in the dark channel image (0.1%) corresponds to the maximum grayscale value of the pixel in the original underwater image, which is the estimated background light value. .

[0062] Step S205: Based on the dark channel image and background light value, obtain the transmittance transfer function, perform guided filtering on the transmittance transfer function, and obtain the transmittance map; In this embodiment, based on the dark channel prior algorithm assumption, the transmittance transfer function is as shown in the following formula 3:

[0063] Formula 3

[0064] in, Let be the transmittance transfer function. Represents the position coordinates of a pixel. For the subset of pixels participating in the calculation, These represent the three channels of the image. The underwater image after denoising. This represents the background light value.

[0065] By applying a guided filter to the transmittance transfer function, the transmittance map is obtained as shown in Equation 4 below:

[0066] Formula 4

[0067] in, This is a transmittance diagram. For guided filter functions, is the transmittance transfer function.

[0068] Step S206: The transmittance map is input into the underwater image imaging model to obtain the underwater restored image. In this embodiment, brightness correction is achieved through background light estimation and the transmittance formula, improving algorithm performance and ultimately enhancing the quality of the original underwater image. Specifically, a guided filter is used to refine the transmittance transfer function to obtain the transmittance map. Substituting the underwater image imaging model into the model, the underwater reconstructed image is obtained, as shown in Formula 5 below:

[0069] Formula 5

[0070] in, For underwater reconstruction images, The underwater image after denoising. Background light value, This is a transmittance diagram.

[0071] Through steps S201 to S206, compared to related underwater image enhancement methods, which involve high computational complexity, cumbersome calculations, poor image enhancement effects, and are unsuitable for real-time underwater image enhancement, this embodiment obtains the original underwater image, performs color difference correction, dynamic mapping, and noise reduction on the original underwater image, and obtains the dark channel image of the processed underwater image. Based on the dark channel image and the original underwater image, the background light value is obtained; based on the dark channel image and the background light value, the transmittance transfer function is obtained; guided filtering is applied to the transmittance transfer function to obtain a transmittance map; the transmittance map is input into the underwater image imaging model to obtain the underwater restored image. In other words, through a series of processes such as color difference correction and dynamic mapping, the color richness of the image is improved, brightness correction is achieved, and algorithm performance is improved. This solves the problems of related underwater image enhancement methods, which involve high computational complexity, cumbersome calculations, poor image enhancement effects, and are unsuitable for real-time underwater image enhancement.

[0072] In some of these embodiments, Figure 3 This is a flowchart of another underwater image processing method according to an embodiment of this application, such as... Figure 3 As shown, after obtaining the transmittance transfer function, the method includes the following steps:

[0073] Step S301: The transmittance transfer function is corrected by the mean value of the dark channel image to obtain the corrected transmittance transfer function. In this embodiment, since the mean value of the dark channel image has the function of automatically adjusting the low background light caused by uneven illumination, the transmittance transfer function can be corrected by increasing the mean value of the dark channel image. The corrected transmittance transfer function is as shown in Formula 6 below:

[0074] Formula 6

[0075] in, This is the corrected transmittance transfer function. Represents the position coordinates of a pixel. For the subset of pixels participating in the calculation, These represent the three channels of the image. The underwater image after denoising. This represents the background light value.

[0076] Step S302: Perform guided filtering on the corrected transmittance transfer function to obtain the corrected transmittance map; in this embodiment, the corrected transmittance map is shown in Formula 7 below:

[0077] Formula 7

[0078] in, This is the corrected transmittance diagram. For guided filter functions, This is the corrected transmittance transfer function.

[0079] Step S303: Input the corrected transmittance map into the underwater image imaging model to obtain the final underwater reconstructed image. In this embodiment, the final underwater reconstructed image is shown in Formula 8 below:

[0080] Formula 8

[0081] in, For the final underwater reconstruction image, The underwater image after denoising. Background light value, This is a transmittance diagram.

[0082] Through steps S301 to S302, the transmittance transfer function is corrected by the mean of the dark channel image, which adjusts the problem of low background light caused by uneven illumination, thereby further enhancing the quality of the underwater restored image.

[0083] In some embodiments, color difference correction is performed on the original underwater image to obtain a corrected underwater image. Color difference correction includes color adjustment and spatial domain adjustment. The original underwater image is subjected to color adjustment and spatial domain adjustment to obtain the corrected underwater image. In this embodiment, color difference correction is performed based on each pixel of the original underwater image, as shown in Formula 9 below.

[0084] Formula 9

[0085] in, The corrected underwater image, These are the position coordinates of the pixel. The coordinates of the origin pixel are... This indicates a lateral inhibition mechanism. These represent the three channels of the image. For the subset of pixels participating in the calculation, Indicates the pixels involved in the calculation. Represents the processed pixels. This is a function representing relative brightness. The distance metric function between two pixels is often the Manhattan distance, as shown in Formula 10 below:

[0086] Formula 10

[0087] Only functions that are both odd and nonlinear can possess the properties of the white balance hypothesis. The functional form of is shown in Formula 11 below:

[0088] Formula 11

[0089] in, The color temperature can be adjusted according to the actual scene. If the color temperature is 20, then T can be set to 20. x represents the displacement of the pixel in the x-axis direction.

[0090] In some embodiments, dynamically mapping the corrected underwater image to obtain the dynamically mapped underwater image includes: dynamically mapping each of the three image channels of the corrected underwater image to obtain three-channel images, and then synthesizing the three-channel images to obtain the dynamically mapped underwater image. In this embodiment, the dynamic mapping is achieved using a white spot / grayscale world mapping adjustment calculation formula, as shown in Formula 12 below:

[0091] Formula 12

[0092] in, This is the underwater image after dynamic mapping. These represent the three image channels respectively. This is a rounding function. The corrected underwater image, for The slope of the line segment between them. This indicates the maximum value for color gamut adjustment. This represents the minimum value for color gamut adjustment. Represents the position coordinates of a pixel. This refers to the subset of pixels that participate in the computation.

[0093] Specifically, dynamic mapping is performed on the three image channels of the corrected underwater image to obtain the dynamically mapped underwater image, including:

[0094] Acquire the R-channel, G-channel, and B-channel images of the corrected underwater image;

[0095] Dynamically map the R-channel image, G-channel image, and B-channel image respectively to obtain the R-channel mapped image, G-channel mapped image, and B-channel mapped image;

[0096] By synthesizing the R-channel mapped image, G-channel mapped image, and B-channel mapped image, a dynamically mapped underwater image is obtained.

[0097] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0098] This embodiment also provides an underwater image processing system for implementing the above embodiments and preferred embodiments, which will not be repeated hereafter. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0099] Figure 4 This is a structural block diagram of an underwater image processing system according to an embodiment of this application, such as... Figure 4As shown, the system includes a first acquisition module 41, a mapping module 42, a denoising module 43, a second acquisition module 44, a filtering module 45, and a restoration module 46. The first acquisition module 41 is used to acquire the original underwater image, perform color difference correction on the original underwater image, and obtain a corrected underwater image. The mapping module 42 is used to perform dynamic mapping on the corrected underwater image to obtain a dynamically mapped underwater image. The denoising module 43 is used to eliminate noise in the dynamically mapped underwater image to obtain a denoised underwater image. The second acquisition module 44 is used to acquire the dark channel image of the denoised underwater image, and obtain the background light value based on the dark channel image and the original underwater image. The filtering module 45 is used to obtain the transmittance transfer function based on the dark channel image and the background light value, and perform guided filtering on the transmittance transfer function to obtain a transmittance map. The restoration module 46 is used to input the transmittance map into the underwater image imaging model to obtain an underwater restored image. This system solves the problem that underwater image enhancement methods in related technologies are computationally intensive, cumbersome, and have poor image enhancement effects, making them unsuitable for real-time underwater image enhancement.

[0100] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0101] This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0102] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0103] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0104] Furthermore, in conjunction with the underwater image processing methods described in the above embodiments, this application embodiment can provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the underwater image processing methods described in the above embodiments.

[0105] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for underwater image processing. The display screen may be a liquid crystal display (LCD) or an e-ink display. The input device may be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0106] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0107] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been 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.

[0108] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for underwater image processing, characterized in that, The method includes: Acquire the original underwater image, and perform color difference correction, including color adjustment and spatial domain adjustment, on each pixel of the original underwater image to obtain the corrected underwater image; the formula for color difference correction is: , The corrected underwater image, These are the position coordinates of the pixel. The coordinates of the origin pixel are... This indicates a lateral inhibition mechanism. These represent the three channels of the image. For the subset of pixels participating in the calculation, Indicates the pixels involved in the calculation. Represents the processed pixels. This is a function representing relative brightness. A distance metric function representing the distance between two pixels; The formula is: , Here, x represents the color temperature, and x represents the displacement of the pixel along the x-axis. The formula is: ; The corrected underwater image is dynamically mapped to obtain a dynamically mapped underwater image; the dynamic mapping is implemented using a white spot / grayscale world mapping adjustment calculation formula; the formula for implementing dynamic mapping using the white spot / grayscale world mapping adjustment calculation formula is as follows: , This is the underwater image after dynamic mapping. These represent the three image channels. This is a rounding function. The corrected underwater image, for The slope of the line segment between them. This indicates the maximum value for color gamut adjustment. This represents the minimum value for color gamut adjustment. Represents the position coordinates of a pixel. A subset of pixels participating in the computation; The noise in the dynamically mapped underwater image is eliminated by using a bilateral filtering method and introducing differences in the pixel neighborhood, thus obtaining a denoised underwater image. Obtain the dark channel image of the denoised underwater image, and obtain the background light value based on the dark channel image and the original underwater image; Based on the dark channel image and the background light value, the transmittance transfer function is obtained, and the transmittance transfer function is subjected to guided filtering to obtain a transmittance map. The transmittance map is input into the underwater image imaging model to obtain the underwater reconstruction image.

2. The method according to claim 1, characterized in that, After obtaining the transmittance transfer function, the method further includes: The transmittance transfer function is corrected by using the mean of the dark channel image to obtain the corrected transmittance transfer function. The modified transmittance transfer function is subjected to guided filtering to obtain the modified transmittance map. The corrected transmittance map is input into the underwater image imaging model to obtain the final underwater reconstruction image.

3. The method according to claim 1, characterized in that, The background light value is obtained based on the dark channel image and the original underwater image, including: The pixel with the highest grayscale value of 0.1% in the dark channel image corresponds to the pixel with the highest grayscale value in the original underwater image, which is the background light value.

4. The method according to claim 1, characterized in that, The corrected underwater image is dynamically mapped to obtain a dynamically mapped underwater image, including: The three image channels of the corrected underwater image are dynamically mapped to obtain three channel images, and the three channel images are synthesized to obtain the dynamically mapped underwater image.

5. The method according to claim 4, characterized in that, Dynamically map the three image channels of the corrected underwater image to obtain a dynamically mapped underwater image, including: Acquire the R-channel image, G-channel image, and B-channel image of the corrected underwater image; The R-channel image, the G-channel image, and the B-channel image are dynamically mapped respectively to obtain the R-channel mapped image, the G-channel mapped image, and the B-channel mapped image; The R-channel mapped image, the G-channel mapped image, and the B-channel mapped image are synthesized to obtain the dynamically mapped underwater image.

6. The method according to claim 1, characterized in that, The transmittance map is input into the underwater image imaging model to obtain the underwater restored image, including: in, The underwater reconstructed image, The denoised underwater image, The background light value, This is the transmittance diagram.

7. A system for underwater image processing, characterized in that, The system includes a first acquisition module, a mapping module, a denoising module, a second acquisition module, a filtering module, and a restoration module. The first acquisition module is used to acquire an original underwater image, and perform color difference correction, including color adjustment and spatial domain adjustment, on each pixel of the original underwater image to obtain a corrected underwater image; the formula for color difference correction is: , The corrected underwater image, These are the position coordinates of the pixel. The coordinates of the origin pixel are... This indicates a lateral inhibition mechanism. These represent the three channels of the image. For the subset of pixels participating in the calculation, Indicates the pixels involved in the calculation. Represents the processed pixels. This is a function representing relative brightness. A distance metric function representing the distance between two pixels; The formula is: , Here, x represents the color temperature, and x represents the displacement of the pixel along the x-axis. The formula is: ; The mapping module is used to dynamically map the corrected underwater image to obtain a dynamically mapped underwater image; the dynamic mapping is achieved using a white spot / grayscale world mapping adjustment calculation formula; the formula for achieving dynamic mapping using the white spot / grayscale world mapping adjustment calculation formula is as follows: , This is the underwater image after dynamic mapping. These represent the three image channels. This is a rounding function. The corrected underwater image, for The slope of the line segment between them. This indicates the maximum value for color gamut adjustment. This represents the minimum value for color gamut adjustment. Represents the position coordinates of a pixel. A subset of pixels participating in the computation; The denoising module is used to eliminate noise in the dynamically mapped underwater image by using a bilateral filtering method and introducing differences in the pixel neighborhood, thereby obtaining a denoised underwater image. The second acquisition module is used to acquire the dark channel image of the denoised underwater image, and obtain the background light value based on the dark channel image and the original underwater image; The filtering module is used to obtain a transmittance transfer function based on the dark channel image and the background light value, and to perform guided filtering on the transmittance transfer function to obtain a transmittance map. The restoration module is used to input the transmittance map into the underwater image imaging model to obtain an underwater restored image.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the underwater image processing method according to any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the underwater image processing method according to any one of claims 1 to 6 when it is run.

Images