Underwater image enhancement method based on information entropy fidelity and multi-order illumination prior

Abstract

The invention provides an underwater image enhancement method based on information entropy fidelity and multi-order illumination prior, comprising: inputting a low-illuminance underwater image, and converting it from an RGB color space to an HSV color space; processing a brightness channel, comprising: decomposing the brightness channel into illumination and reflectivity according to a Retinex variational model, and performing non-Gaussian modeling of information entropy for data fidelity; performing sparse prior constraints on the illumination multi-order gradient and the reflectivity first-order gradient; decomposing the above-mentioned joint optimization problem into two sub-problems of reflectivity and illumination by an alternating direction multiplier method, and performing iterative updating and solving the two sub-problems respectively by using a semi-quadratic optimization method to obtain enhanced illumination and reflectivity; multiplying the two sub-problems pixel by pixel to obtain an enhanced brightness channel, merging the enhanced brightness channel with an original chromaticity channel and a saturation channel, and then converting the enhanced brightness channel from the HSV color space back to the RGB color space, thereby realizing the enhancement of the low-illuminance underwater image.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater image enhancement, and in particular to a low-illuminance (non-uniform illumination) underwater image enhancement method based on information entropy fidelity and multi-order illumination prior. Background Art

[0002] Due to the unique and complex optical characteristics of the underwater environment, underwater imaging equipment will be affected by the absorption of visible light by water and the scattering of visible light by suspended sediment particles when collecting underwater images. These will cause the final underwater images collected to present uneven illumination (low illumination), which seriously limits the subsequent analysis and processing of underwater images and other related applications. Therefore, low-illumination underwater image enhancement is a key underwater image processing technology that removes non-uniform illumination and has been widely used in underwater fields such as biological monitoring, resource exploration, and archaeology.

[0003] In view of the low illumination problem (uneven illumination) of underwater images, researchers have proposed a series of low illumination underwater image enhancement methods, among which the low illumination underwater image enhancement method based on the Retinex variational model shows significant non-uniform illumination removal performance. In the prior art, there are mainly the following low illumination underwater image enhancement methods based on the Retinex variational model: 1) Retinex variational framework based on sparse prior of illumination channel: Design L with background light 0 The norm term, the reflectivity constraint term and the background light gradient term are used to integrate the sparse prior of the illumination channel into the extended underwater image imaging model. The data fidelity uses the traditional Gaussian modeling method to restore the underwater image with non-uniform illumination. 2) Retinex variational model inspired by super-Laplacian reflectance prior: The data fidelity uses the traditional Gaussian modeling method, and the norm is used to impose sparse prior constraints on the first-order and second-order gradients of the illumination.

[0004] However, the underwater Retinex variational model of the above method has the following problems: (1) The data fidelity terms all adopt Gaussian modeling, which cannot effectively model non-Gaussian data fidelity; (2) It does not make comprehensive use of the multi-order sparse prior of illumination, and cannot better solve the problem of non-uniform illumination. Therefore, how to construct a low-light underwater image enhancement method based on information entropy fidelity and multi-order illumination prior is one of the core problems that technicians in this field need to solve urgently. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide an underwater image enhancement method based on information entropy fidelity and multi-order illumination prior to solve the problem that the data fidelity in low-illuminance underwater images does not conform to the Gaussian distribution, and use information entropy to perform non-Gaussian modeling on data fidelity; at the same time, the multi-order (first-order, second-order) gradient sparse prior of illumination is comprehensively utilized, that is, L1 The norm (Laplacian distribution) is used to constrain the first-order and second-order gradient sparse priors of illumination to effectively remove the non-uniform illumination problem in low-light underwater images.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] On the one hand, a method for underwater image enhancement based on information entropy fidelity and multi-order illumination prior is provided, the method comprising the following steps:

[0008] S1, input low-light underwater image as the starting input data;

[0009] S2, converting the input low-light underwater image from RGB color space to HSV color space;

[0010] S3. Processing the brightness channel of the HSV color space, including: decomposing the brightness channel into illumination and reflectance according to the Retinex variational model, and performing non-Gaussian modeling of information entropy for data fidelity; performing sparse prior constraints on the multi-order gradients of illumination, and performing sparse prior constraints on the first-order gradient of reflectance;

[0011] S4, expressing the low-light underwater image enhancement problem as a joint optimization problem, using the alternating direction multiplier method to decompose the joint optimization problem into two sub-problems of reflectivity and illumination, and using the semi-quadratic optimization method to optimize and solve the two sub-problems respectively;

[0012] S5, iteratively updating the optimization solution process to obtain enhanced illumination and reflectivity;

[0013] S6, multiplying the enhanced illumination and reflectivity pixel by pixel to obtain an enhanced brightness channel;

[0014] S7, merging the enhanced brightness channel with the original chrominance channel and saturation channel, and then converting the merged image from the HSV color space back to the RGB color space to obtain the final underwater enhanced image.

[0015] Optionally, in step S3, the brightness channel V is decomposed into illumination and reflectivity according to the Retinex variational model, and non-Gaussian modeling of information entropy is performed on the data fidelity; L is performed on the sparse prior of the first-order and second-order gradients of illumination. 1 norm constraint, and L is used for the sparse prior of the first-order gradient of reflectivity 1 Norm constraint; the specific calculation is as follows:

[0016]

[0017] Among them, I represents illumination, R represents reflectivity, Represents the dot multiplication operation of image pixels, and Δ represent the first-order gradient operator and the second-order gradient operator, respectively; represents the data fidelity term of information entropy non-Gaussian modeling, Indicated by L 1 Norm constrained first-order gradient of illumination Indicated by L 1 The norm constrains the second-order gradient of illumination ΔI, Indicated by L 1 Norm-constrained first-order gradient of reflectivity ; α, β, γ are weight balancing parameters.

[0018] Optionally, in step S4, the low-light underwater image enhancement problem is expressed as a joint optimization problem, and the specific operation is as follows:

[0019]

[0020]

[0021]

[0022]

[0023] Where N represents the total number of image pixels, D i,j Indicates I i and I j The distance between σ represents the Gaussian kernel, σ ω represents the standard deviation of the Gaussian kernel.

[0024] Optionally, the alternating direction multiplier method is used to decompose the joint optimization problem (5) into two sub-problems of reflectivity and illumination, and the semi-quadratic optimization method is used to optimize and solve the two sub-problems separately. The specific calculation process is as follows:

[0025] Lighting I sub-problem:

[0026]

[0027]

[0028] Reflectivity R subproblem:

[0029]

[0030]

[0031] Where k is the kth outer loop iteration.

[0032] Optionally, the updating process of the illumination I subproblem is as follows:

[0033] Input: reflectivity R k-1 , t = 1;

[0034] Calculate using formula (7) and

[0035] Loop until convergence:

[0036]

[0037]

[0038] Output after the loop ends: k-th updated illumination I t →I k ;

[0039] Where t is the tth inner loop iteration, and → represents the assignment symbol.

[0040] Optionally, the update process of the reflectivity R subproblem is as follows:

[0041] Input: Reflectivity I k , t = 1;

[0042] Calculate using formula (9) and

[0043] Loop until convergence:

[0044]

[0045]

[0046] Output after the loop ends: reflectivity R updated for the kth time t →R k ;

[0047] Where t is the tth inner loop iteration, and → represents the assignment symbol.

[0048] Optionally, in step S6, the enhanced illumination and reflectivity are multiplied pixel by pixel to obtain an enhanced brightness channel The specific calculation is as follows:

[0049]

[0050] in, represents the enhanced illumination, represents the enhanced reflectivity, Represents the dot multiplication operation of image pixels.

[0051] On the other hand, an underwater image enhancement system based on information entropy fidelity and multi-order illumination prior is provided, for implementing any of the above methods, the system comprising:

[0052] An input module, used for inputting low-light underwater images as initial input data;

[0053] A first conversion module, used for converting an input low-light underwater image from an RGB color space to an HSV color space;

[0054] A processing module is used to process the brightness channel of the HSV color space, including: decomposing the brightness channel into illumination and reflectance according to the Retinex variational model, and performing non-Gaussian modeling of information entropy for data fidelity; performing sparse prior constraints on the multi-order gradients of illumination, and performing sparse prior constraints on the first-order gradient of reflectance;

[0055] A solution module is used to express the low-light underwater image enhancement problem as a joint optimization problem, decompose the joint optimization problem into two sub-problems of reflectivity and illumination by using an alternating direction multiplier method, and optimize and solve the two sub-problems respectively by using a semi-quadratic optimization method;

[0056] An updating module is used to iteratively update the optimization solution process to obtain enhanced illumination and reflectivity;

[0057] The dot multiplication module is used to multiply the enhanced illumination and reflectivity pixel by pixel to obtain the enhanced brightness channel;

[0058] The second conversion module is used to merge the enhanced brightness channel with the original chrominance channel and saturation channel, and then convert the merged image from the HSV color space back to the RGB color space to obtain the final underwater enhanced image.

[0059] In another aspect, an electronic device is provided, the electronic device comprising:

[0060] processor;

[0061] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are loaded and executed by the processor, the steps of the underwater image enhancement method described above are implemented.

[0062] On the other hand, a computer-readable storage medium is provided, in which program codes are stored. The program codes can be called by a processor to execute the steps of the underwater image enhancement method as described above.

[0063] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0064] The present invention proposes a low-illuminance underwater image enhancement method based on information entropy fidelity and multi-order illumination prior. Compared with the existing low-illuminance underwater image enhancement method based on Gaussian fidelity modeling, the present invention has the following advantages: (1) information entropy (non-Gaussian) modeling is used for data fidelity to solve the problem that data fidelity in low-illuminance underwater images does not conform to Gaussian distribution; (2) multi-order (first-order and second-order) gradient sparse priors of illumination are comprehensively utilized to effectively solve the non-uniform illumination problem of underwater images. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0066] Figure 1 It is a flow chart of an underwater image enhancement method based on information entropy fidelity and multi-order illumination prior provided by an embodiment of the present invention;

[0067] Figure 2 It is a structural schematic diagram of an underwater image enhancement system based on information entropy fidelity and multi-order illumination prior provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a concrete way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two. In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings to be expressed are consistent. In the embodiments of the present invention, sometimes subscripts such as W 1 It may be written in non-subscript form such as W1. When the difference is not emphasized, the meaning is the same.

[0070] The embodiment of the present invention provides an underwater image enhancement method based on information entropy fidelity and multi-order illumination priors, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 As shown, the processing flow of the method may include the following steps:

[0071] S1. Input a low-light underwater image as the starting input data.

[0072] S2. Convert the input low-light underwater image from RGB color space to HSV color space.

[0073] In the embodiment of the present invention, only the brightness channel V in the HSV color space needs to be processed, while the chroma channel H and the saturation channel S remain unchanged.

[0074] S3. Processing the brightness channel of the HSV color space, including: decomposing the brightness channel into illumination and reflectance according to the Retinex variational model, and performing non-Gaussian modeling of information entropy for data fidelity; performing sparse prior constraints on multi-order illumination gradients, and performing sparse prior constraints on the first-order reflectance gradient.

[0075] In the embodiment of the present invention, the brightness channel V is decomposed into illumination and reflectivity according to the Retinex variational model, and non-Gaussian modeling of information entropy is performed on the data fidelity; the sparse prior of the multi-order (first-order and second-order) gradient of illumination is L 1 norm constraint, and L is used for the sparse prior of the first-order gradient of reflectivity 1 Norm constraint; the specific calculation is as follows:

[0076]

[0077] Among them, I represents illumination, R represents reflectivity, Represents the dot multiplication operation of image pixels, and Δ represent the first-order gradient operator and the second-order gradient operator, respectively; represents the data fidelity term of information entropy non-Gaussian modeling, Indicated by L 1 Norm constrained first-order gradient of illumination Indicated by L 1 The norm constrains the second-order gradient of illumination ΔI, Indicated by L 1 Norm-constrained first-order gradient of reflectivity ; α, β, γ are weight balance parameters, which are set to 10 based on empirical values. -2 , 10 -3 , 10 -4 .

[0078] S4. The low-light underwater image enhancement problem is expressed as a joint optimization problem. The alternating direction multiplier method is used to decompose the joint optimization problem into two sub-problems of reflectivity and illumination. The semi-quadratic optimization method is used to optimize and solve the two sub-problems respectively.

[0079] In the embodiment of the present invention, the low-light underwater image enhancement problem is expressed as a joint optimization problem, and the specific operation is as follows:

[0080]

[0081]

[0082]

[0083]

[0084] Where N represents the total number of image pixels, D i,j Indicates I i and I j The distance between σ represents the Gaussian kernel, σ ω represents the standard deviation of the Gaussian kernel. According to the empirical value, Set to N / 1000.

[0085] Furthermore, the alternating direction multiplier method is used to decompose the joint optimization problem (5) into two sub-problems: reflectivity and illumination. The semi-quadratic optimization method is used to optimize and solve the two sub-problems separately. The calculation is as follows:

[0086] Lighting I sub-problem:

[0087]

[0088]

[0089] Where k is the kth outer loop iteration.

[0090] The updating process of the illumination I subproblem is as follows:

[0091]

[0092] Where t is the tth inner loop iteration, and → represents the assignment symbol.

[0093] Reflectivity R subproblem:

[0094]

[0095]

[0096] Where k is the kth outer loop iteration.

[0097] The updating process of the reflectivity R subproblem is as follows:

[0098]

[0099] Where t is the tth inner loop iteration, and → represents the assignment symbol.

[0100] S5. Iterate and update the optimization solution process to obtain enhanced illumination and reflectivity.

[0101] In the embodiment of the present invention, the optimization solution process in step S4 is iterated and updated n (n=10) times to obtain the enhanced illumination and reflectivity

[0102] S6. Multiply the enhanced illumination and reflectivity pixel by pixel to obtain an enhanced brightness channel.

[0103] In the embodiment of the present invention, the enhanced illumination and reflectivity are multiplied pixel by pixel to obtain the enhanced brightness channel The specific calculation is as follows:

[0104]

[0105] in, represents the enhanced illumination, represents the enhanced reflectivity, Represents the dot multiplication operation of image pixels.

[0106] S7, the enhanced brightness channel It is merged with the original chroma channel H and saturation channel S, and then the merged image is converted from the HSV color space back to the RGB color space to obtain the final underwater enhanced image.

[0107] The present invention proposes a low-illuminance underwater image enhancement method based on information entropy fidelity and multi-order illumination prior. Compared with the existing low-illuminance underwater image enhancement method based on Gaussian fidelity modeling, the present invention has the following advantages: (1) information entropy (non-Gaussian) modeling is used for data fidelity to solve the problem that data fidelity in low-illuminance underwater images does not conform to Gaussian distribution; (2) multi-order (first-order and second-order) gradient sparse priors of illumination are comprehensively utilized to effectively solve the non-uniform illumination problem of underwater images.

[0108] Accordingly, an embodiment of the present invention further provides an underwater image enhancement system based on information entropy fidelity and multi-order illumination priors. Figure 2 is a structural block diagram of a system based on information entropy fidelity and multi-order illumination priors according to an exemplary embodiment. Figure 2As shown, the system includes:

[0109] An input module 201 is used to input a low-light underwater image as initial input data;

[0110] A first conversion module 202 is used to convert the input low-light underwater image from the RGB color space to the HSV color space;

[0111] The processing module 203 is used to process the brightness channel of the HSV color space, including: decomposing the brightness channel into illumination and reflectance according to the Retinex variational model, and performing non-Gaussian modeling of information entropy for data fidelity; performing sparse prior constraints on the multi-order gradients of illumination, and performing sparse prior constraints on the first-order gradient of reflectance;

[0112] A solution module 204 is used to express the low-light underwater image enhancement problem as a joint optimization problem, decompose the joint optimization problem into two sub-problems of reflectivity and illumination using an alternating direction multiplier method, and optimize and solve the two sub-problems respectively using a semi-quadratic optimization method;

[0113] An updating module 205 is used to iteratively update the optimization solution process to obtain enhanced illumination and reflectivity;

[0114] A dot multiplication module 206 is used to multiply the enhanced illumination and reflectivity pixel by pixel to obtain an enhanced brightness channel;

[0115] The second conversion module 207 is used to merge the enhanced brightness channel with the original chrominance channel and saturation channel, and then convert the merged image from the HSV color space back to the RGB color space to obtain the final underwater enhanced image.

[0116] For ease of explanation, Figure 2 Only the main components of the device are shown. The device of this embodiment can be used to perform Figure 1 The technical solution of the method embodiment shown has similar implementation principles and technical effects, which will not be repeated here.

[0117] In an exemplary embodiment, the present invention further provides an electronic device, the electronic device comprising:

[0118] processor;

[0119] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are loaded and executed by the processor, the steps of the underwater image enhancement method described above are implemented.

[0120] In an exemplary embodiment, the present invention further provides a computer-readable storage medium, wherein at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is loaded and executed by a processor to implement the steps of the underwater image enhancement method as described above. For example, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0121] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0122] References in the specification to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments", etc. indicate that the described embodiments may include a particular feature, structure, or characteristic, but not every embodiment may include the particular feature, structure, or characteristic. In addition, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the relevant art to implement such feature, structure, or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0123] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0124] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0125] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0126] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0127] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0128] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0129] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0130] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0131] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An underwater image enhancement method based on information entropy fidelity and multi-order illumination prior, characterized in that: The following steps are involved: S1, input low-light underwater image as the starting input data; S2, converting the input low-light underwater image from RGB color space to HSV color space; S3. Processing the brightness channel of the HSV color space, including: decomposing the brightness channel into illumination and reflectance according to the Retinex variational model, and performing non-Gaussian modeling of information entropy for data fidelity; performing sparse prior constraints on the multi-order gradients of illumination, and performing sparse prior constraints on the first-order gradient of reflectance; S4, expressing the low-light underwater image enhancement problem as a joint optimization problem, using the alternating direction multiplier method to decompose the joint optimization problem into two sub-problems of reflectivity and illumination, and using the semi-quadratic optimization method to optimize and solve the two sub-problems respectively; S5, iteratively updating the optimization solution process to obtain enhanced illumination and reflectivity; S6, multiplying the enhanced illumination and reflectivity pixel by pixel to obtain an enhanced brightness channel; S7, merging the enhanced brightness channel with the original chrominance channel and saturation channel, and then converting the merged image from the HSV color space back to the RGB color space to obtain the final underwater enhanced image; In step S3, the brightness channel V is decomposed into illumination and reflectivity according to the Retinex variational model, and non-Gaussian modeling of information entropy is performed for data fidelity; L1 norm constraints are performed on the sparse priors of the first-order and second-order gradients of illumination, and L1 norm constraints are performed on the sparse priors of the first-order gradients of reflectivity; the specific calculation is as follows: Among them, I represents illumination, R represents reflectivity, Represents the dot multiplication operation of image pixels, and Δ represent the first-order gradient operator and the second-order gradient operator, respectively; represents the data fidelity term of information entropy non-Gaussian modeling, Represents the first-order gradient of illumination constrained by the L1 norm represents the second-order gradient ΔI of the illumination constrained by the L1 norm, represents the first-order gradient of reflectivity constrained by L1 norm α, β, and γ are weight balancing parameters; In step S4, the low-light underwater image enhancement problem is expressed as a joint optimization problem, and the specific operation is as follows: Where N represents the total number of image pixels, D i,j Indicates I i and I j The distance between σ represents the Gaussian kernel, σ ω represents the standard deviation of the Gaussian kernel; The alternating direction multiplier method is used to decompose the joint optimization problem (5) into two sub-problems: reflectivity and illumination. The semi-quadratic optimization method is used to optimize and solve the two sub-problems respectively. The specific calculation process is as follows: Lighting I sub-problem: Reflectivity R subproblem: Where k is the kth outer loop iteration.

2. The underwater image enhancement method based on information entropy fidelity and multi-order illumination prior according to claim 1 is characterized in that: The updating process of the illumination I subproblem is as follows: Input: reflectivity R k-1 , t = 1; Calculate using formula (7) and Loop until convergence: t = t + 1; Output after the loop ends: k-th updated illumination I t →I k ; Where t is the tth inner loop iteration, and → represents the assignment symbol.

3. The underwater image enhancement method based on information entropy fidelity and multi-order illumination prior according to claim 1, characterized in that: The updating process of the reflectivity R subproblem is as follows: Input: Lighting I k , t = 1; Calculate using formula (9) and Loop until convergence: t = t + 1; Output after the loop ends: reflectivity R updated for the kth time t →R k ; Where t is the tth inner loop iteration, and → represents the assignment symbol.

4. The underwater image enhancement method based on information entropy fidelity and multi-order illumination prior according to claim 1, characterized in that: In step S6, the enhanced illumination and reflectivity are multiplied pixel by pixel to obtain the enhanced brightness channel. The specific calculation is as follows: in, represents the enhanced illumination, represents the enhanced reflectivity, Represents the dot multiplication operation of image pixels.

5. An underwater image enhancement system based on information entropy fidelity and multi-order illumination prior, the system is used to implement the method according to any one of claims 1 to 4, characterized in that: The system comprises: An input module, used for inputting low-light underwater images as initial input data; A first conversion module, used for converting an input low-light underwater image from an RGB color space to an HSV color space; A processing module is used to process the brightness channel of the HSV color space, including: decomposing the brightness channel into illumination and reflectance according to the Retinex variational model, and performing non-Gaussian modeling of information entropy for data fidelity; performing sparse prior constraints on the multi-order gradients of illumination, and performing sparse prior constraints on the first-order gradient of reflectance; A solution module is used to express the low-light underwater image enhancement problem as a joint optimization problem, decompose the joint optimization problem into two sub-problems of reflectivity and illumination by using an alternating direction multiplier method, and optimize and solve the two sub-problems respectively by using a semi-quadratic optimization method; An updating module is used to iteratively update the optimization solution process to obtain enhanced illumination and reflectivity; The dot multiplication module is used to multiply the enhanced illumination and reflectivity pixel by pixel to obtain the enhanced brightness channel; The second conversion module is used to merge the enhanced brightness channel with the original chrominance channel and saturation channel, and then convert the merged image from the HSV color space back to the RGB color space to obtain the final underwater enhanced image.

6. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when loaded and executed by the processor, implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, which can be called by a processor to execute the method according to any one of claims 1 to 4.

Images