An underwater image enhancement method based on relative total variation

Abstract

The application discloses an underwater image enhancement method based on relative total variation, comprising the following steps: obtaining an original image shot underwater, performing linear stretching on the original image to obtain a color correction image; constructing a relative total variation statistical line model of the underwater image based on an atmospheric scattering model and combined with texture information of the color correction image, estimating the color correction image according to the relative total variation statistical line model to obtain a depth map; processing the color correction image by using an image block subdivision method to obtain a candidate background region, selecting a brightness point in a dark channel image of the candidate background region, and obtaining a global background light estimation value by calculating an average value of the brightness point; and obtaining an underwater enhanced image according to the depth map and the global background light estimation value. The application can effectively restore the color of the underwater image and improve the overall contrast and detail definition of the underwater image.

Description

Technical Field

[0001] The present invention belongs to the technical field of image enhancement, and in particular relates to an underwater image enhancement method based on relative total variation. Background Art

[0002] Underwater images, as the primary carrier of ocean information, play a vital role in ocean exploration and are widely used in marine engineering fields such as marine resource development, autonomous underwater target search and detection, and underwater robotics. However, light absorption and scattering in water can cause underwater image degradation, such as color cast, fogging, and reduced contrast. In degraded underwater images, the lack of effective feature information in the target image leads to low accuracy in underwater target detection. Therefore, underwater image enhancement technology remains an urgent problem in the field of image processing. To address these challenges, researchers have proposed a variety of underwater image enhancement methods, which are mainly categorized as non-physical model methods, physical imaging model methods, and deep learning methods. Underwater image enhancement techniques based on non-physical models improve image quality by directly adjusting the pixel values ​​without considering the physical imaging model. Common image enhancement methods include histogram equalization and Retinex image enhancement. Although simple, enhancement algorithms based on non-physical models ignore the principles of underwater imaging and are prone to introducing noise and artifacts, resulting in over-enhancement or under-enhancement. With the rapid development of artificial intelligence technology, deep learning has made significant progress in improving underwater image quality, mainly based on convolutional neural networks and generative adversarial networks. However, deep learning-based methods require a large amount of paired data. Currently, the underwater datasets required for training are relatively scarce. At the same time, the loss function of the training network is difficult to achieve Nash equilibrium in the high-dimensional parameter space. Underwater image enhancement methods based on physical models introduce prior knowledge and use underwater physical imaging models to reversely solve the image depth rate and background light to obtain an undegraded image. Although image enhancement algorithms based on prior information have achieved certain results in solving problems such as underwater image fogging and color distortion, the parameter settings in these algorithms often rely on the subjective experience of researchers, which limits the maximum performance of the algorithm. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes an underwater image enhancement method based on relative total variation, which can effectively restore the color of underwater images and improve the overall contrast and detail clarity of underwater images.

[0004] To achieve the above object, the present invention provides an underwater image enhancement method based on relative total variation, comprising: acquiring an original image taken underwater, linearly stretching the original image to obtain a color-corrected image;

[0005] Based on the atmospheric scattering model and in combination with the texture information of the color-corrected image, a relative total variation statistical line model of the underwater image is constructed, and the color-corrected image is estimated according to the relative total variation statistical line model to obtain a depth map;

[0006] Processing the color-corrected image using an image block subdivision method to obtain a candidate background area, selecting brightness points from a dark channel image of the candidate background area, and obtaining a global background light estimation value by calculating an average value of the brightness points;

[0007] An underwater enhanced image is obtained according to the depth map and the global background light estimation value.

[0008] Optionally, linearly stretching the original image includes:

[0009]

[0010] Among them, c∈{r,g,b} represents the three color channels of the image color space; and J c (x) represents the color corrected image and restored image respectively; (x) and Represent the minimum and maximum values ​​of the channel respectively.

[0011] Optionally, the atmospheric scattering model is:

[0012] I(x,y)=J(x,y)t(x,y)+A(1-t(x,y));

[0013] Where (x, y) represents the position of a pixel in the image; I(x, y) represents the observed image; J(x, y) represents the clear image; A represents the background light; and t(x, y) represents the medium depth rate.

[0014] Optionally, the relative total variation statistical line model is:

[0015]

[0016] Among them, H x / y and M x / y They represent the relative total variation of the observed image and the clear image respectively; (x, y) represents the position of a pixel in the image; I(x, y) represents the observed image; J(x, y) represents the clear image; A represents the background light; and t(x, y) represents the medium depth rate.

[0017] Optionally, estimating the color-corrected image according to the relative total variation statistical line model to obtain a smoothed medium depth rate includes:

[0018]

[0019] in, represents the smoothed medium depth rate; G(·) represents the guided filter operator; t(x,y) represents the medium depth rate.

[0020] Optionally, obtaining a candidate background region includes:

[0021]

[0022] Among them, R i Indicates the divided small area; R bg Represents the candidate background area; It is region R i The average value of the inner pixel values; It is region R i The standard deviation of the inline pixel values.

[0023] Optionally, obtaining a global background light estimate includes:

[0024]

[0025] Among them, A represents the background light; p represents the candidate area R bg Each pixel in; N represents the candidate region R bg The total number of pixels in .

[0026] Optionally, obtaining underwater enhanced images includes:

[0027]

[0028] Where J(x,y) represents the clear image; I(x,y) represents the observed image; A represents the background light; Indicates the smoothed medium depth rate.

[0029] Technical effect of the invention: The present invention discloses an underwater image enhancement method based on relative total variation. In view of the fact that existing underwater image enhancement algorithms may over-smooth images, resulting in loss of edge details, and in some cases introduce a "gradient step effect", which makes the image have unnatural stepped edges, the present invention obtains an original image taken underwater, linearly stretches the original image, and obtains a color-corrected image; based on an atmospheric scattering model and in combination with texture information of the color-corrected image, a relative total variation statistical line model of the underwater image is constructed, and the color-corrected image is estimated according to the relative total variation statistical line model to obtain a depth map; the color-corrected image is processed by an image block subdivision method to obtain a candidate background area, and brightness points are selected from a dark channel image of the candidate background area, and a global background light estimation value is obtained by calculating the average value of the brightness points; an underwater enhanced image is obtained according to the depth map and the global background light estimation value; the present invention can effectively restore the color of the underwater image and improve the overall contrast and detail clarity of the underwater image. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0031] Figure 1 Schematic diagram of a flow chart of an underwater image enhancement method based on relative total variation according to an embodiment of the present invention;

[0032] Figure 2 The figures are comparison diagrams of the image enhancement effects of the embodiments of the present invention, where (a) is the original image and (b) is the effect diagram after image enhancement. DETAILED DESCRIPTION

[0033] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0034] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] like Figure 1 As shown, this embodiment provides an underwater image enhancement method based on relative total variation, including:

[0036] Obtain the original image taken underwater, perform linear stretching on the original image, and obtain a color-corrected image;

[0037] Based on the atmospheric scattering model and the texture information of the color-corrected image, a relative total variation statistical line model of the underwater image is constructed. The color-corrected image is estimated according to the relative total variation statistical line model to obtain a depth map.

[0038] The color-corrected image is processed using the image block subdivision method to obtain candidate background areas. Brightness points are selected from the dark channel image of the candidate background areas, and the global background light estimation value is obtained by calculating the average value of the brightness points.

[0039] Based on the depth map and the global background light estimation value, an underwater enhanced image is obtained.

[0040] Furthermore, linear stretching of the original image includes:

[0041]

[0042] Among them, c∈{r,g,b} represents the three color channels of the image color space; and J c (x) represents the color corrected image and restored image respectively; and Represent the minimum and maximum values ​​of the channel, respectively, and are defined as:

[0043]

[0044] in, and Represent the value and variance of a single channel respectively; λ represents the parameter that controls the dynamic range of the image.

[0045] Furthermore, the atmospheric scattering model is:

[0046] I(x,y)=J(x,y)t(x,y)+A(1-t(x,y));

[0047] Where (x, y) represents the position of a pixel in the image; I(x, y) represents the observed image; J(x, y) represents the clear image; A represents the background light; and t(x, y) represents the medium depth rate.

[0048] Furthermore, the relative total variation statistical line model is:

[0049]

[0050] Among them, H x / y and M x / y They represent the relative total variation of the observed image and the clear image respectively; (x, y) represents the position of a pixel in the image; I(x, y) represents the observed image; J(x, y) represents the clear image; A represents the background light; and t(x, y) represents the medium depth rate.

[0051] Specifically, H x / y and M x / y They represent the relative total variation of the observed image and the clear image respectively. The specific expressions are as follows:

[0052]

[0053] Based on the local pixel I(x,y) / H x / y and A / H x / y The relative total variation line is constructed based on the distribution characteristics relationship between them, and the slope k is obtained. The depth map of the local area is obtained as follows:

[0054] t(x,y)=1-k;

[0055] The guided filter is further used to obtain a smooth depth map:

[0056]

[0057] in, represents the smoothed medium depth rate; G(·) represents the guided filter operator; t(x,y) represents the medium depth rate.

[0058] Furthermore, obtaining candidate background regions includes:

[0059]

[0060] Among them, R i Indicates the divided small area; R bg Represents the candidate background area; It is region R i The average value of the inner pixel values; It is region R i The standard deviation of the inline pixel values.

[0061] Furthermore, obtaining a global background light estimation value includes:

[0062]

[0063] Where A represents the background light and p represents the candidate area R bg Each pixel in; N represents the candidate region R bg In this embodiment, the brightness points selected are the points in the top 1% of brightness.

[0064] Furthermore, obtaining the underwater enhanced image includes:

[0065]

[0066] Where J(x,y) represents the clear image; I(x,y) represents the observed image; A represents the background light; Indicates the smoothed medium depth rate.

[0067] like Figure 2 The comparison diagram of the image enhancement effect is shown in Table 1, where (a) is the original image and (b) is the image enhancement effect.

[0068] Table 1

[0069]

[0070] A specific application example of the present invention is as follows:

[0071] like Figure 1 As shown, this embodiment provides an underwater image enhancement method based on relative total variation, including the following steps:

[0072] Step 1: Linearly stretch the original image taken underwater to obtain a color-corrected image;

[0073] Step 2: Based on the atmospheric scattering model and the texture information of the image, a relative total variation statistical line model of the underwater image is constructed, and the image depth map is estimated using this model;

[0074] Step 3: Based on the image block segmentation method, the global background light estimation value is obtained;

[0075] Step 4: Obtain an underwater enhanced image that conforms to human eye sensory vision based on the estimated depth map and background light.

[0076] As a specific implementation, the process of performing linear stretching on the original image captured underwater in step 1 includes:

[0077]

[0078] Among them, c∈{r,g,b} represents the three color channels of the image color space; and J c (x) represents the color corrected image and restored image respectively; and Represent the minimum and maximum values ​​of the channel respectively.

[0079] As a specific implementation, the atmospheric scattering model described in step 2 is:

[0080] I(x,y)=J(x,y)t(x,y)+A(1-t(x,y));

[0081] Where (x, y) represents the position of a pixel in the image; I(x, y) represents the observed image; J(x, y) represents the clear image; A represents the background light; and t(x, y) represents the medium depth rate.

[0082] Furthermore, the relative total variation statistical line model is:

[0083]

[0084] Among them, H x / y and M x / y They represent the relative total variation of the observed image and the clear image respectively; (x, y) represents the position of a pixel in the image; I(x, y) represents the observed image; J(x, y) represents the clear image; A represents the background light; and t(x, y) represents the medium depth rate.

[0085] Specifically, H x / y and M x / y They represent the relative total variation of the observed image and the clear image respectively. The specific expressions are as follows:

[0086]

[0087] Based on the local pixel I(x,y) / H x / y and A / H x / y The relative total variation line is constructed based on the distribution characteristics relationship between them, and the slope k is obtained. The depth map of the local area is obtained as follows:

[0088] t(x,y)=1-k;

[0089] The guided filter is further used to obtain a smooth depth map:

[0090]

[0091] in, represents the smoothed medium depth rate; G(·) represents the guided filter operator; t(x,y) represents the medium depth rate.

[0092] As a specific implementation, the step 3 of obtaining the candidate background area includes:

[0093]

[0094] Among them, R i Indicates the divided small area; R bg Represents the candidate background area; It is region R i The average value of the inner pixel values; It is region R i The standard deviation of the inline pixel values.

[0095] Furthermore, obtaining a global background light estimation value includes:

[0096]

[0097] Among them, A represents the background light; p represents the candidate area R bg Each pixel in; N represents the candidate region R bg In this embodiment, the brightness points selected are the points in the top 1% of brightness.

[0098] As a specific implementation, the step 4 of obtaining the underwater enhanced image includes:

[0099]

[0100] Where J(x,y) represents the clear image; I(x,y) represents the observed image; A represents the background light; Indicates the smoothed medium depth rate.

[0101] The present invention discloses an underwater image enhancement method based on relative total variation. The method comprises the following steps: obtaining an original image shot underwater, linearly stretching the original image, and obtaining a color-corrected image; constructing a relative total variation statistical line model of the underwater image based on an atmospheric scattering model and combining the texture information of the color-corrected image; estimating the color-corrected image according to the relative total variation statistical line model, and obtaining a depth map; processing the color-corrected image by adopting an image block subdivision method, obtaining a candidate background area, selecting brightness points from a dark channel image of the candidate background area, and obtaining a global background light estimation value by calculating the average value of the brightness points; and obtaining an underwater enhanced image according to the depth map and the global background light estimation value. The present invention can effectively restore the color of the underwater image and improve the overall contrast and detail clarity of the underwater image.

[0102] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An underwater image enhancement method based on relative total variation, characterized in that: include: Acquire an original image captured underwater, and perform linear stretching on the original image to obtain a color-corrected image; Based on the atmospheric scattering model and combined with the texture information of the color-corrected image, a relative total variation statistical line model of the underwater image is constructed. The relative total variation statistical line model is: ； in, and Represent the relative total variation of the observed image and the clear image respectively; Indicates the position of a pixel in the image; represents the observed image; Indicates a clear image; Indicates background light; Indicates the medium depth rate; Based on local pixels and The distribution characteristics relationship between them is used to construct the relative total variation line and obtain the slope , the medium depth rate of the local area is obtained as: ； Estimating the color-corrected image according to the relative total variation statistical line model to obtain a smoothed medium depth rate includes: ； in, Indicates the smoothed medium depth rate; represents the guided filtering operator; Indicates the medium depth rate; Processing the color-corrected image using an image block subdivision method to obtain a candidate background area, selecting brightness points from a dark channel image of the candidate background area, and obtaining a global background light estimation value by calculating an average value of the brightness points; An underwater enhanced image is obtained according to the smoothed medium depth rate and the global background light estimation value.

2. The underwater image enhancement method based on relative total variation according to claim 1, wherein: Linearly stretching the original image includes: ； in, Represents the three color channels of the image color space; and Represent the color corrected image and restored image respectively; and Represent the minimum and maximum values ​​of the channel respectively.

3. The underwater image enhancement method based on relative total variation according to claim 1, wherein: The atmospheric scattering model is: ； in, Indicates the position of a pixel in the image; represents the observed image; Indicates a clear image; Indicates background light; Indicates the medium depth rate.

4. The underwater image enhancement method based on relative total variation according to claim 1, wherein: Obtaining candidate background areas includes: ； in, Indicates a small area divided; Represents the candidate background area; It is a region The average value of the inner pixel values; It is a region The standard deviation of the inline pixel values.

5. The underwater image enhancement method based on relative total variation according to claim 1, wherein: Obtaining a global background light estimate involves: ； in, A Indicates background light; Represents the candidate region Each pixel in Represents the candidate region The total number of pixels in .

6. The underwater image enhancement method based on relative total variation according to claim 1, wherein: Obtaining underwater enhanced images includes: ； in, Indicates a clear image; represents the observed image; Indicates background light; Indicates the smoothed medium depth rate.

Images