A sand-dust image sharpening method, system, medium, device and terminal

Abstract

The application belongs to the field of image vision technology, and discloses a sand-dust image sharpening method, system, medium, equipment and terminal. The improved automatic color scale algorithm is used to perform secondary distribution on image pixels, so as to reduce image color deviation. The gamma correction algorithm and the improved dark channel prior algorithm are combined to perform brightness compensation on each image pixel, so as to enhance image sharpness. The gray world algorithm is combined to balance image color, so as to realize sharpening of deep-concentration sand-dust images. The application can effectively improve sand-dust image quality, improve the definition and sharpness of degraded images, and realize sharpening of blurred images in sand-dust weather. The application can effectively improve the definition and sharpness of deep-degraded sand-dust images. The image collected in severe weather with large sand-dust can be restored to a clear image by the processing of the application, which has important practical significance for security monitoring, road monitoring, face recognition and the like.

Description

Technical Field

[0001] This invention belongs to the field of image vision technology, and in particular relates to a method, system, medium, device and terminal for improving the clarity of sand and dust images. Background Technology

[0002] Smart security is a crucial line of defense for urban public safety, and its applications, from safe cities to smart transportation, have penetrated various industries. However, in adverse weather conditions such as rain, snow, fog, and haze, the clarity and contrast of images captured by cameras are severely degraded. Current research on image sharpening in adverse weather conditions mainly focuses on scenarios like fog, haze, and rain. Due to the scattering effect of suspended particles on light, images suffer from severe color distortion, and sandstorms pose an even greater challenge than rain, fog, and haze. Existing image sharpening methods fall into three categories: image enhancement-based, image restoration-based, and deep learning-based. Image enhancement-based methods do not consider the object imaging process and directly select appropriate image enhancement techniques to adjust pixels according to specific needs. Image restoration-based methods construct physical models based on the causes of image degradation, estimate the parameters of the physical model based on prior knowledge, and increase image contrast through model inversion. Deep learning-based methods learn image features through network perceptrons to assist in parameter estimation or directly learn the mapping relationship between blurred and sharp images to achieve image sharpening.

[0003] Traditional image sharpening techniques primarily target scenarios like rain, fog, and haze. However, in dusty weather, suspended sand particles absorb and scatter light, causing severe color distortion and reduced sharpness. This makes image sharpening research for monitoring images in dusty weather more challenging than for rain, fog, or haze. Current methods for sharpening dusty images, especially those with significant color distortion, cannot address the uneven brightness caused by substantial image degradation. Therefore, a novel method for sharpening dusty images is urgently needed.

[0004] Based on the above analysis, the problems and defects of the existing technology are as follows: the existing methods for improving the clarity of sand and dust images are geared towards rain, fog, haze and other scenarios, and cannot solve the problem of uneven brightness caused by the large degree of image degradation. Summary of the Invention

[0005] To address the problems existing in current image processing technologies, this invention provides a method, system, medium, device, and terminal for enhancing sand and dust images, and particularly relates to a method, system, medium, device, and terminal for enhancing sand and dust images based on high concentration.

[0006] This invention is implemented as follows: a method for sharpening sand and dust images, the method comprising:

[0007] The improved automatic color level algorithm is used to reallocate the image pixels, reducing the color cast of the image; the gamma correction algorithm and the improved dark channel prior algorithm are fused to perform brightness compensation on each image pixel, enhancing the image sharpness; the gray world algorithm is combined to balance the image color, achieving the clarification of deep-concentration dust images.

[0008] Further, the method for clarifying the dust image includes the following steps:

[0009] Step 1, perform color correction on the input dust image using the improved automatic color level algorithm, effectively reducing the color cast problem of the dust image;

[0010] Step 2, adopt the gamma correction algorithm for the image after adjusting the color difference to increase the image brightness and correct the local noise of the image;

[0011] Step 3, based on the atmospheric scattering model and dark channel prior knowledge, improve the estimation of the atmospheric light value and transmittance, increasing the image sharpness;

[0012] Step 4, perform brightness compensation on the L channel of the Lab channel of the image after dark channel processing, enhancing the brightness of the image after dark channel processing;

[0013] Step 5, through the weighted fusion algorithm, perform weighted fusion on the images after gamma correction and brightness compensation, enhancing the image clarity;

[0014] Step 6, process the weighted image using the gray world algorithm to balance the image color, making the image color softer and more natural.

[0015] Further, the color cast correction of the dust image in Step 1 includes:

[0016] (1) Statistically analyze the color channel histograms after separation, and calculate the upper and lower limits max and min through the clipping ratio;

[0017] (2) Calculate the adjustment parameters MAX and MIN in the mapping rule through the following formula, where α is the adjustment factor. When MAX>255, MAX takes 255, and when MIN<0, MIN takes 0;

[0018] MAX = max+(max - min)*α;

[0019] MIN = min-(max - min)*α;

[0020] (3) Map each pixel p to P through mapping;

[0021] When p < min, P = 0;

[0022] When min < p < max,

[0023] When p < max, P = 255;

[0024] (4) Fuse the pixel values of each channel after mapping through the mapping relationship.

[0025] Furthermore, the gamma correction for enhancing the image brightness of the image after color cast correction in the second step includes:

[0026] (1) Normalize the image pixel P to a real number E through the formula ;

[0027] (2) Perform pre-compensation on the normalized value through the formula f = E 1 / γ ;

[0028] (3) Complete the inverse transformation through the formula P' = f * 256 - 0.5;

[0029] (4) Transform the pixel values of each channel.

[0030] Furthermore, the dark channel processing for increasing the image sharpness of the image after color cast correction in the third step includes:

[0031] (1) According to the atmospheric scattering model I(x) = J(x)t(x) + A(1 - t(x)), and the dark channel prior, it can be known that the value of one of the RGB color channels is very low and almost approaches 0, and the transmittance is obtained as:

[0032]

[0033] (2) Improve the atmospheric light value estimation method, find the pixel values of the top 1% in terms of brightness in the dark channel of the image, and then calculate the average value of the brightness values of 1% of the pixel points in the original image;

[0034] (3) Perform guided filtering on the image after dark channel processing to smooth the image edges.

[0035] Furthermore, in the fourth step, separate the color channels of the image after guided filtering, extract the L component in the Lab color space, and perform brightness compensation through the formula L' = L * n; where n is the compensation parameter, when n < 1, reduce the image brightness; when n > 1, increase the image brightness.

[0036] In the fifth step, perform weighted fusion on the image after gamma correction, dark channel processing, and brightness compensation. The fusion expression is C = αG + (1 - α)D, where C is the fused image, G is the image after gamma correction, and D is the image after dark channel processing and brightness compensation.

[0037] The steps for balancing the color of the weighted fused image using the gray world algorithm in the sixth step include:

[0038] (1) Calculate the average values ​​of the R, G, and B channels of the image, denoted as R', G', and B', and take...

[0039] (2) Calculate the gain coefficients of the R, G, and B channels:

[0040]

[0041] (3) Adjust the R, G, and B channel components for each pixel P in the image using the following formula:

[0042] P(R′)=P(R)*kr, P(G′)=P(G)*kg, P(B′)=P(B)*kb;

[0043] (4) Synthesize the adjusted R, G, and B component maps.

[0044] Another object of the present invention is to provide a dust image sharpening system applying the aforementioned dust image sharpening method, the dust image sharpening system comprising:

[0045] The color correction module is used to reduce color cast by applying an improved automatic color level algorithm to the input sandstorm image.

[0046] The gamma correction module is used to increase the brightness of the image and correct local noise in the image after adjusting the color difference using the gamma correction algorithm.

[0047] The dark channel processing module is used to improve the estimation of atmospheric light value and transmittance based on atmospheric scattering models and prior knowledge of dark channels, thereby increasing image sharpness.

[0048] The brightness compensation module is used to perform brightness compensation on the L channel of the Lab channel of the image after dark channel processing;

[0049] The weighted fusion module is used to perform weighted fusion of images after gamma correction and brightness compensation using a weighted fusion algorithm to enhance image clarity;

[0050] The image color balance module is used to process the weighted image using the grayscale world algorithm and balance the image colors.

[0051] Another object of the present invention is to provide a computer device including a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the sandstorm image sharpening method.

[0052] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the sandstorm image sharpening method.

[0053] Another objective of this invention is to provide an information data processing terminal for implementing the aforementioned sandstorm image enhancement system.

[0054] Based on the above technical solutions and the technical problems solved, please analyze the advantages and positive effects of the technical solution to be protected by this invention from the following aspects:

[0055] First, addressing the technical problems existing in the prior art and the difficulty in solving them, this paper closely analyzes, in conjunction with the technical solution to be protected by this invention and the results and data obtained during the research and development process, how the technical solution of this invention solves the technical problems, and the inventive technical effects brought about by solving these problems. The specific description is as follows:

[0056] This invention discloses a method for image sharpening under sandstorm conditions, aiming to increase the clarity and sharpness of sandstorm images, ensuring good visual quality even in images acquired under adverse weather conditions. This invention combines the advantages of image enhancement and image restoration, including an improved automatic color grading algorithm, an improved dark channel prior algorithm, a gamma correction algorithm, a weighted fusion algorithm, and a grayscale world algorithm. To address the pixel grayscale shift problem caused by severe color cast, an improved automatic color grading algorithm is used to redistribute image pixels, reducing color cast. Gamma correction and dark channel algorithms are fused to compensate for the brightness of each pixel, enhancing image sharpness. Finally, the grayscale world algorithm is combined to balance image colors and improve image contrast, thereby achieving sharpening of deep-concentration sandstorm images.

[0057] Second, considering the technical solution as a whole or from a product perspective, the technical effects and advantages of the technical solution to be protected by this invention are specifically described as follows:

[0058] This invention combines the advantages of image enhancement and image restoration to effectively improve the quality of sandstorm images, increasing the clarity and sharpness of degraded images. It can clarify blurred images in sandstorm weather. For deeply degraded sandstorm images, this invention can effectively improve image clarity and sharpness. Images acquired in severe sandstorm weather can be restored to clear images through processing with this invention. This invention has significant practical implications for security monitoring, road surveillance, and facial recognition.

[0059] Third, as supplementary evidence of the inventive step of the claims of this invention, it is also reflected in the following important aspects:

[0060] (1) The expected benefits and commercial value of the technical solution of this invention after transformation are as follows:

[0061] In dusty weather scenarios, cameras integrating this method can directly convert captured dust maps into clear images.

[0062] (2) The technical solution of this invention fills a technical gap in the industry both domestically and internationally:

[0063] Compared with domestic and foreign methods for improving the clarity of sand and dust images, the technical solution of this invention is superior to other methods in terms of both subjective visual effects and objective index values. Attached Figure Description

[0064] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart of the sandstorm image sharpening method provided in the embodiments of the present invention.

[0066] Figure 2 This is a schematic diagram of the sandstorm image sharpening method provided in the embodiment of the present invention.

[0067] Figure 3 This is the original diagram provided in the embodiment of the present invention.

[0068] Figure 4 This is an automatic color gradation effect diagram provided in an embodiment of the present invention.

[0069] Figure 5 This is a gamma correction effect diagram provided in an embodiment of the present invention.

[0070] Figure 6 This is a diagram showing the effect of dark channel processing provided in an embodiment of the present invention.

[0071] Figure 7 This is a weighted fusion effect diagram provided in an embodiment of the present invention.

[0072] Figure 8 This is a diagram illustrating the effect of the grayscale world algorithm provided in an embodiment of the present invention.

[0073] Figure 9 This is a comparison image showing the improvement in clarity of sand and dust images provided in an embodiment of the present invention.

[0074] Figure 10 These are comparison images of classic dehazing algorithms provided in embodiments of the present invention. Detailed Implementation

[0075] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0076] To address the problems existing in the prior art, the present invention provides a method, system, medium, device, and terminal for improving the clarity of sand and dust images. The present invention will be described in detail below with reference to the accompanying drawings.

[0077] I. Explanatory and Illustrative Embodiments. To enable those skilled in the art to fully understand how the present invention is specifically implemented, this section provides an explanatory and illustrative description of the embodiments described in the claims.

[0078] The dust image sharpening method provided in this invention combines the advantages of image enhancement and image restoration, including an improved automatic color grading algorithm, an improved dark channel prior algorithm, a gamma correction algorithm, a weighted fusion algorithm, and a grayscale world algorithm. Addressing the pixel grayscale shift problem caused by severe color cast, the method employs an improved automatic color grading algorithm to redistribute image pixels, reducing color cast; it integrates gamma correction and dark channel algorithms to compensate the brightness of each pixel, enhancing image sharpness; and finally, it combines a grayscale world algorithm to balance colors and improve image contrast, thereby achieving sharpening of deep-concentration dust images.

[0079] like Figure 1 As shown, the sandstorm image sharpening method provided in this embodiment of the invention includes the following steps:

[0080] S101, reduces image color cast by performing color correction on the input sandstorm image using an improved automatic color level algorithm;

[0081] S102, Apply the gamma correction algorithm to the image after adjusting the color difference to increase the image brightness and correct local noise in the image;

[0082] S103, based on atmospheric scattering models and prior knowledge of dark channels, improves the estimation of atmospheric light value and transmittance, thereby increasing image sharpness;

[0083] S104 performs brightness compensation on the L channel of the Lab channel of the image after dark channel processing;

[0084] S105 enhances image clarity by combining images after gamma correction and brightness compensation using a weighted fusion algorithm.

[0085] S106 uses the grayscale world algorithm to process the weighted image and balance the image colors.

[0086] The automatic color level improvement algorithm provided by the embodiments of the present invention statistically analyzes the histogram of the separated color channels, calculates the upper and lower limits max and min through the clipping ratio; maps each pixel p to P according to the adjustment parameters MAX and MIN. When p < min, P = 0. When min < p < max, When p < max, P = 255. The color cast correction is achieved through pixel reallocation.

[0087] The gamma correction algorithm provided by the embodiments of the present invention enhances the image brightness of the color cast - corrected image. For each pixel, the image pixel P is normalized to a real number E through the formula ; the normalized value is pre - compensated through the formula f = E 1 / γ ; the inverse transformation is completed through the formula P' = f * 256 - 0.5.

[0088] The improved dark channel prior algorithm provided by the embodiments of the present invention improves the methods of atmospheric light value and transmittance. The transmittance removes the correction factor. For the atmospheric light value estimation method, first find the pixel values of the top 1% in terms of brightness in the dark channel of the image, and then calculate the average value of the brightness values of these 1% of the pixel points in the original image.

[0089] The embodiments of the present invention provide brightness enhancement for the image after dark channel processing. Extract the L component in the Lab color space, and perform brightness compensation through the formula L' = L * n. Here, n is the compensation parameter. When n < 1, the image brightness is reduced; when n > 1, the image brightness is increased.

[0090] The embodiments of the present invention provide weighted fusion for the image after gamma correction, dark channel processing, and brightness compensation. The fusion expression is C = αG+(1 - α)D, where C is the fused image, G is the image after gamma correction, and D is the image after dark channel processing and brightness compensation.

[0091] The embodiments of the present invention provide color balancing for the weighted - fused image using the gray - world algorithm. First, calculate the average values of the R, G, and B channels of the image, denoted as R', G', and B'. Take Calculate the gain coefficients of the R, G, and B channels For each pixel P in the image, adjust the R, G, and B channel components through the following formula: P(R') = P(R) * kr, P(G') = P(G) * kg, P(B') = P(B) * kb; finally, synthesize the adjusted R, G, and B component maps.

[0092] The sand - dust image clarity system provided by the embodiments of the present invention includes:

[0093] A color correction module, which is used to perform color correction on the input sand - dust image using the improved automatic color level algorithm to reduce the color cast of the image;

[0094] The gamma correction module is used to increase the brightness of the image and correct local noise in the image after adjusting the color difference using the gamma correction algorithm.

[0095] The dark channel processing module is used to improve the estimation of atmospheric light value and transmittance based on atmospheric scattering models and prior knowledge of dark channels, thereby increasing image sharpness.

[0096] The brightness compensation module is used to perform brightness compensation on the L channel of the Lab channel of the image after dark channel processing;

[0097] The weighted fusion module is used to perform weighted fusion of images after gamma correction and brightness compensation using a weighted fusion algorithm to enhance image clarity;

[0098] The image color balance module is used to process the weighted image using the grayscale world algorithm and balance the image colors.

[0099] II. Application Examples. To demonstrate the inventiveness and technical value of the technical solution of this invention, this section provides application examples of the technical solution of the claims on specific products or related technologies.

[0100] The following diagram illustrates the effects of different processing steps.

[0101] like Figure 3 As shown, this is the original diagram provided in the embodiment of the present invention.

[0102] like Figure 4 As shown, this is an automatic color gradation effect diagram provided by an embodiment of the present invention.

[0103] like Figure 5 As shown, this is a diagram illustrating the gamma correction effect provided in an embodiment of the present invention.

[0104] like Figure 6 As shown, this is a diagram illustrating the dark channel processing effect provided in an embodiment of the present invention.

[0105] like Figure 7 As shown, this is a weighted fusion effect diagram provided by an embodiment of the present invention.

[0106] like Figure 8 As shown, this is a diagram illustrating the effect of the grayscale world algorithm provided in this embodiment of the invention.

[0107] III. Evidence of the Relevant Effects of the Embodiments. The embodiments of the present invention have achieved some positive effects during research and development or use, and indeed possess significant advantages compared to existing technologies. The following description, combined with charts and other materials from the experimental process, illustrates these advantages.

[0108] Figure 9This paper presents a comparison of the image sharpening effects of sandstorm images and the effects of classic dehazing algorithms. In the sandstorm image sharpening comparison, the first column shows the original image, where details are severely obscured by sand, resulting in significant image degradation and an overall dark yellow tint. The second column shows the processed image with severe distortion and decreased contrast. The third column shows the processed image, which corrects the overall color, but the background color in the sky area is overexposed. The fourth column also shows color deviation and even more severe image sharpness degradation. The fifth column shows an overall dark gray tint, where image information is no longer displayed correctly; this is the most severely degraded image in the entire comparison. The sixth column shows three images with poor color correction after processing, with the overall background still yellow. The seventh column shows the effect of adding aperture to landmark objects in the image. The last column shows the processing effect of the proposed method. It can be seen that the color difference is significantly improved after color correction, effectively solving the color cast problem, resulting in softer and more natural colors, and effectively improving image sharpness and clarity. Subjectively, the overall effect is superior to other methods.

[0109] like Figure 10 As shown in the comparison chart of classic dehazing algorithms, the first column is the original image. The second column shows the effects of the methods used. It can be seen that after processing the four images using the dark channel dehazing algorithm, the color cast of the images is intensified, and the yellowish tinge is more pronounced in each image compared to the original, without any improvement in overall image clarity. The third column shows the effects of the methods used, with little difference from the original images; the color cast is almost unchanged, and the image clarity remains similar to the original. Figure 1 The blurred image, as shown in multiple comparison images, demonstrates that classic dehazing methods are unsuitable for sandstorm images. They fail to address color cast issues and exacerbate image degradation after processing. The fourth column shows the results of Retinex processing; the overall image tone is dark, appearing as dark black and dark red, further intensifying the degradation. The final column presents the results of the algorithm presented in this invention. This algorithm effectively corrects color cast, increases image brightness, and improves overall image clarity. It effectively sharpens images with high-density sandstorms.

[0110] It should be noted that embodiments of the present invention can be implemented in hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the above-described devices and methods can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuitry such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of the above-described hardware circuitry and software, such as firmware.

[0111] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for sharpening sandstorm images, characterized in that, The method for clarifying the dust image includes the following steps: Step 1: Perform color correction on the input dust image using an improved automatic level algorithm to reduce image color cast. Step 2: Apply the gamma correction algorithm to the image after color cast correction to increase the image brightness and correct local image noise. Step 3: Perform dark channel processing on the image after color cast correction to increase image sharpness. Among them, Step 3 specifically includes: (1) According to the atmospheric scattering model I(x) = J(x)t(x) + A(1 - t(x)), the dark channel prior indicates that the value of one of the RGB color channels is very low, almost approaching 0, and the transmittance is obtained as: (2) Improve the atmospheric light value estimation method. Find the top 1% of pixel values in the dark channel of the image, and then calculate the average value of the brightness values of 1% of the pixel points in the original image. (3) Perform guided filtering on the image after dark channel processing to smooth the image edges. Step 4: Perform brightness compensation on the L channel of the Lab channel of the image after guided filtering. Step 5: Through the weighted fusion algorithm, perform weighted fusion on the images after gamma correction and brightness compensation to enhance image clarity. Step 6: Process the weighted image using the gray world algorithm to balance the image color. The color correction by using the improved automatic level algorithm on the input dust image in Step 1 includes: (1) Statistically analyze the histograms of the separated color channels, and calculate the upper and lower limits max and min through the clipping ratio. (2) Calculate the adjustment parameters MAX and MIN in the mapping rule through the following formula, where α is the adjustment factor. When MAX > 255, MAX takes 255, and when MIN < 0, MIN takes 0. MAX = max + (max - min) * α; MIN = min - (max - min) * α; (3) Map each pixel p to P through mapping transformation. When p < min, P = 0; When min < p < max, When p < max, P = 255; (4) Map the pixel values of each channel through the mapping relationship and then perform fusion.

2. The method for enhancing sandstorm images as described in claim 1, characterized in that, The increase in image brightness by applying the gamma correction algorithm to the image after color cast correction in Step 2 includes: (1) The image pixel P is calculated using the formula Normalized to a real number E; (2) The normalized value is obtained by applying the formula f = E 1 / γ Perform pre-compensation; (3) Complete the inverse transformation through the formula P' = f * 256 - 0.

5. (4) Transform the pixel values of each channel.

3. The method for enhancing sandstorm images as described in claim 1, characterized in that, In Step 4, perform color channel separation on the image after guided filtering, extract the L component in the Lab color space, and perform brightness compensation through the formula L' = L * n. Among them, n is the compensation parameter. When n < 1, the image brightness is reduced; when n > 1, the image brightness is increased. In Step 5, perform weighted fusion on the images after gamma correction, dark channel processing, and brightness compensation. The fusion expression is C = βG + (1 - β)D, where C is the fused image, G is the image after gamma correction, and D is the image after dark channel processing and brightness compensation. The balance of color by using the gray world algorithm on the weighted fused image in Step 6 includes: (1) Calculate the average values ​​of the R, G, and B channels of the image, denoted as R', G', and B', and take... (2) Calculate the gain coefficients of the R, G, and B channels: (3) Adjust the R, G, and B channel components of each pixel P in the image through the following formula: P(R′)=P(R)*kr, P(G′)=P(G)*kg, P(B′)=P(B)*kb; (4) Synthesize the adjusted R, G, and B component maps.

4. A sandstorm image sharpening system applying the sandstorm image sharpening method as described in any one of claims 1 to 3, characterized in that, The dust storm image enhancement system includes: The color correction module is used to reduce color cast by applying an improved automatic color level algorithm to the input sandstorm image. The gamma correction module is used to increase the brightness of the image and correct local noise in the image after color cast correction using the gamma correction algorithm. The dark channel processing module is used to improve the estimation of atmospheric light value and transmittance based on atmospheric scattering models and prior knowledge of dark channels, thereby increasing image sharpness. The brightness compensation module is used to perform brightness compensation on the L channel of the Lab channel of the guided filtered image; The weighted fusion module is used to perform weighted fusion of images after gamma correction and brightness compensation using a weighted fusion algorithm to enhance image clarity; The image color balance module is used to process the weighted image using the grayscale world algorithm and balance the image colors.

5. A computer device, characterized in that, The computer device includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the sandstorm image sharpening method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the sandstorm image sharpening method as described in any one of claims 1 to 3.

7. An information data processing terminal, characterized in that, The information data processing terminal is used to implement the sandstorm image enhancement system as described in claim 4.

Images