A Method for Geological Disaster Exploration Image Enhancement

Abstract

The present invention relates to the technical field of image data processing, and particularly relates to a method for enhancing geological disaster exploration images, including: obtaining the values of a pixel point in the R, G, and B channels and the gray value of the pixel point in the current mountain image; for the target pixel point among the pixel points in the current mountain image, determining the noise factor of the target pixel point; determining the landslide factor of the target pixel point; determining the number of reference historical mountain images of the target pixel point; determining the weight during weighting of the dark channel value of the pixel point at the corresponding position in each frame of the reference historical mountain image; obtaining the optimized dark channel value of the target pixel point; and enhancing the current mountain image by using the dark channel defogging algorithm based on the optimized dark channel value. The present invention provides more accurate input for the dark channel defogging algorithm by accurately determining the optimized dark channel value of the pixel point, thereby improving the clarity and contrast of the mountain image.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and particularly relates to a method for enhancing geological disaster exploration images. Background Art

[0002] Near landslides not only pose a serious threat to the safety of human life and property, but also may lead to traffic interruption, damage to infrastructure, and deterioration of the ecological environment. Therefore, timely identification of mountain images in potential landslide areas is of great significance for quickly responding to the negative impacts of landslide disasters.

[0003] During the acquisition of mountain images, due to the interference of environmental factors such as haze and clouds, the image quality often deteriorates, and key geological features are covered, thus affecting the accuracy and real-time nature of the analysis results. In this context, the dark channel dehazing algorithm, as an advanced image enhancement technology, shows significant advantages in improving image clarity and highlighting potential landslide features. The dark channel dehazing algorithm effectively removes haze interference in the image, making the image clearer and the geological features more prominent, thereby providing accurate data support for the timely response to landslide disasters.

[0004] When processing images, the dark channel dehazing algorithm realizes enhancement based on the dark channel values of each pixel point. The dark channel value is derived from the minimum value of all pixel points in the R, G, and B channels within the neighboring range of the pixel point. However, during the transmission of mountain images, due to signal interference or transmission errors, image data is lost or abnormal, thus forming noise pixel points in the image. Noise pixel points usually have extremely small dark channel values. Therefore, the existence of noise pixel points will reduce the accuracy of the dark channel value of a single pixel point, and further affect the overall performance of the dark channel dehazing algorithm. Summary of the Invention

[0005] In order to solve the problem that during the transmission of mountain images, due to signal interference or transmission errors, image data is lost or abnormal, thus forming noise pixel points in the image. Noise pixel points usually have extremely small dark channel values. Therefore, the existence of noise pixel points will reduce the accuracy of the dark channel value of a single pixel point, and further affect the overall performance of the dark channel dehazing algorithm, the present invention proposes a method for enhancing geological disaster exploration images, and the method includes the following steps:

[0006] Obtain the values of the pixel points in the current mountain image in the R, G, and B channels and the grayscale values of the pixel points; for the target pixel points among the pixel points in the current mountain image, determine the noise factor of the target pixel points according to the grayscale values of the target pixel points and the pixel points in the neighborhood, and the values of the target pixel points and the pixel points in the neighborhood in each channel; determine the landslide factor of the target pixel points according to the mean value of the values of the target pixel points and the pixel points in the surrounding area in the R channel, the mean value of the values of the pixel points in the current mountain image in the R channel, and the standard deviation of the gradient direction values of all the pixel points with gradient changes in the surrounding area of the target pixel points; determine the number of reference historical mountain images of the target pixel points according to the noise factor; determine the weight when weighting the dark channel values of the pixel points corresponding to the target pixel points in each frame of the reference historical mountain images according to the landslide factor, the landslide factors of the pixel points corresponding to the target pixel points in each frame of the reference historical mountain images, and the noise factor; perform weighted summation on the dark channel values of the pixel points corresponding to the target pixel points in the historical mountain images according to the weight to obtain the optimized dark channel value of the target pixel points; based on the optimized dark channel value, use the dark channel dehazing algorithm to enhance the current mountain image.

[0007] By analyzing the noise factor of the target pixel points, the present invention can effectively identify and suppress the influence of noise pixel points on the dark channel value, thereby improving the quality and accuracy of image data; dynamically adjust the weight of the reference image in the weighted operation according to the landslide factor and the noise situation of the historical image, so that when performing dark channel dehazing processing, the change of the environmental conditions can be better considered, thereby enhancing the robustness of the algorithm; by introducing the historical mountain image and processing in combination with multiple frames of images, the richness of data can be effectively increased, and the change of the mountain image in the time series can be tracked, so as to more accurately obtain the dark channel value of the target pixel; by optimizing the dark channel value, the processing effect of the dark channel dehazing algorithm can be significantly improved, making the restoration of clear visual information more effective, thereby providing a more real and reliable image in actual exploration and analysis.

[0008] Further, the values in the R, G, and B channels are obtained by performing RGB separation processing on the current mountain image.

[0009] Further, the grayscale value is obtained by performing grayscale processing on the current mountain image.

[0010] Further, the noise factor satisfies:

[0011] ; where is the noise factor of the pixel point in the current mountain image, is the number of pixel points in the neighborhood of the pixel point in the current mountain image, is the gray value of the pixel point within the current mountain image ; is the gray value of the th pixel point within the neighborhood of the pixel point within the current mountain image is the number of channels of the R, G, and B channels of the pixel point within the current mountain image is the value in the th channel among the R, G, and B channels of the pixel point within the current mountain image is the value in the th channel among the R, G, and B channels of the th pixel point within the neighborhood of the pixel point within the current mountain image is the standard normalization function

[0012] By comprehensively considering the differences in gray values and channel values between the target pixel point and all pixel points within its neighborhood, the present invention can more accurately identify noise pixels, thereby reducing misjudgments and improving the rigor of noise detection. The noise factor not only considers the difference in gray values but also takes into account the data in the RGB channels, enabling more comprehensive noise identification, reducing judgment errors caused by a single perspective, and thus better adapting to complex image environments

[0013] Further, the gradient direction value is obtained by using the Sobel operator

[0014] Further, the landslide factor satisfies:

[0015] ; where is the landslide factor of the pixel point within the current mountain image is the mean value of the values of the pixel point within the current mountain image and the values of the pixel points in the R channel within the surrounding area is the mean value of the values of the pixel point in the R channel within the current mountain image is the standard deviation of the gradient direction values of the pixel point within the current mountain image and all pixel points with gradient changes within the surrounding area is the first hyperparameter is the standard normalization function

[0016] By comparing the R-channel value of the target pixel with the average value of its surrounding area, the present invention can dynamically monitor the possible landslide characteristics of the pixel, facilitating the rapid identification of key areas in geological disaster research; the calculation of the landslide factor utilizes the pixel gradient change, enabling the algorithm to respond in real time to instantaneous changes and helping to provide more accurate image information in a changing environment; by jointly considering the average gray value and the standard deviation of the gradient direction, the landslide factor can more comprehensively reflect the structural characteristics within the area and improve the accuracy of feature extraction.

[0017] Further, the number of the reference historical mountain images satisfies:

[0018] ; where is the number of reference historical mountain images of the pixel in the current mountain image, is the preset initial number, is the pixel in the current mountain image, is the noise factor, and

[0019] is the rounding function.

[0020] By incorporating the noise factor into the calculation of the number of reference historical mountain images, the present invention enables the number of reference images to be dynamically adjusted according to the noise level; in the case of a high noise level, increasing the number of reference historical images helps to provide more supplementary information to compensate for the information that may be lost in the current image, and more historical data can make the restored image approximate the real situation and reduce distortion; through the adjustment of the product of the initial number and the noise factor, it is possible to ensure the quality of image restoration while avoiding the computational burden caused by excessive reliance on historical images.

[0020] Further, the weight satisfies:

[0021] ; where is the weight during weighting of the dark channel value of the pixel at the corresponding position in the th frame of the reference historical mountain image and the pixel in the current mountain image, is the landslide factor of the pixel in the current mountain image, is the landslide factor of the pixel at the corresponding position in the th frame of the reference historical mountain image and the pixel in the current mountain image, is the noise factor of the pixel at the corresponding position in the th frame of the reference historical mountain image and the pixel in the current mountain image, is the first hyperparameter, is the second hyperparameter, is the standard normalization function, is the absolute value symbol.

[0022] The calculation of the weights in the present invention comprehensively considers the differences between the landslide factors in the current mountain image and those at the corresponding positions in the historical images, as well as the noise factors, enabling the weights to better reflect the similarity between the image and the historical data, so that the information similar to the current image can be more effectively highlighted during the weighting process; by introducing the tolerances of the landslide factors and the noise factors, the flexibility of the weighting process is enhanced, enabling more accurate selection of the reference historical information during the defogging process, thereby effectively improving the clarity and detail retention of the processed image; by incorporating the influence of the noise factors into the weight calculation, the incorrect weight assignment caused by noise can be effectively suppressed, ensuring that the influence of noise is reduced during image enhancement and making the image restoration more natural.

[0023] Further, the dark channel value is the minimum value of the values of the pixel and all pixel points within the adjacent range in the R, G, and B channels.

[0024] Further, the optimized dark channel value satisfies:

[0025] ; where is the optimized dark channel value of the pixel point in the current mountain image, is the number of reference historical mountain images for the pixel point in the current mountain image, is the weight of the dark channel value of the pixel point at the corresponding position in the th frame of the reference historical mountain image and the pixel point in the current mountain image during weighting, is the dark channel value of the pixel point at the corresponding position in the th frame of the reference historical mountain image and the pixel point

[0026] The optimized dark channel value of the present invention can effectively fuse the image information from different environments at multiple times through the weighted average of corresponding pixel points in historical mountain images, reflecting local features and global trends, making the final image enhancement effect more accurate; using the weighted average method of weights makes the more relevant and important information in historical images have a greater impact on the final result, improving the adaptability to influencing factors and enhancing the processing ability in complex scenarios; since the setting of weights takes into account the noise factor, the sensitivity of the optimized dark channel value to noise is reduced, so that useful information can be better isolated in scenes with more noise, improving the overall quality of the image; by combining the information of multiple frames of images, during the dark channel defogging process, the details and colors in the image can be better restored, making the final image more vivid and real, which is particularly crucial in geological risk assessment; the optimized dark channel value provides better basic data support for the defogging algorithm, and its high accuracy and reliability lay a solid foundation for subsequent processing steps such as reverse color restoration and contrast enhancement.

[0027] The present invention has the following beneficial effects:

[0028] (1) By determining the noise factor according to the gray value and each channel value of the target pixel point and the pixel points in the neighborhood, the noise pixel points in the image can be accurately identified. Based on the noise factor, the number of reference historical mountain images is determined, and then the dark channel values of the corresponding position pixel points in the historical images are weighted, which can effectively reduce the influence of noise pixel points on the accuracy of the dark channel value of a single pixel point, avoid the interference of the extremely small dark channel value of noise pixel points on the whole, improve the reliability of the dark channel value calculation, and make the dark channel defogging algorithm run more stably in the presence of noise.

[0029] (2) Accurately determining the optimized dark channel value of the target pixel point provides a more accurate input for the dark channel defogging algorithm. Due to removing the adverse effects of noise pixel points, the dark channel defogging algorithm can more accurately estimate the atmospheric light value and transmittance, so as to more effectively remove the fog in the mountain image, improve the clarity and contrast of the image, and make the enhanced mountain image more conducive to the exploration and analysis of geological disasters.

[0030] (3) Introducing the concept of the landslide factor, and determining the landslide factor by comprehensively considering the mean value of the values of the target pixel point and the pixel points in the surrounding area in the R channel, the mean value of the values of the pixel points in the current mountain image in the R channel, and the standard deviation of the gradient direction values of all pixel points with gradient changes between the target pixel point and the surrounding area. This not only helps to judge the characteristics of the area where the pixel point is located, but also takes into account the factors related to geological disasters such as landslides when weighting the dark channel values of the corresponding position pixel points in the historical images, making the enhanced image more in line with the actual needs of geological disaster exploration and providing more valuable information for the analysis of geological disasters.

[0031] (4) Determine the number of reference historical mountain images according to the noise factor, and determine the weights when weighting the dark channel values of the pixel points corresponding to each historical image in combination with the landslide factor and the noise factor. The information of the historical images is fully utilized, the advantages of multiple frames of images can be integrated, the accuracy and stability of the dark channel value can be further improved, the influence caused by the loss or abnormality of single-frame image data can be reduced at the same time, and the robustness of the image enhancement method is enhanced.

[0032] (5) It can adapt to the data loss or abnormal situation caused by signal interference or transmission error during the transmission of mountain images, and can still effectively enhance the image in a complex environment. Whether there is noise interference or data abnormality, the image quality can be improved through reasonable algorithm steps, providing reliable image data support for geological disaster exploration, and improving the practicability and adaptability. Description of the Drawings

[0033] Figure 1 It is a flowchart of the steps of a method for enhancing geological disaster exploration images according to an embodiment of the present invention. Detailed Embodiments

[0034] The technical solutions in the embodiments of the present invention will be clearly and completely described below. The described embodiments are part of the embodiments of the present invention. All other embodiments obtained by those skilled in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.

[0035] The following will describe in detail the specific embodiments of the present invention with reference to the drawings.

[0036] Please refer to Figure 1 , which shows a flowchart of the steps of a method for enhancing geological disaster exploration images provided by an embodiment of the present invention. The method includes the following steps:

[0037] S1: Obtain the values of the pixel points in the R, G, and B channels and the gray value of the pixel points in the current mountain image.

[0038] It should be noted that the present invention uses an unmanned aerial vehicle to continuously collect mountain images. Since the subsequent steps will use the historical mountain images of the current mountain image, the first continuously collected multiple frames of mountain images can be only used for reference without enhancement processing.

[0039] The implementer can set the number of continuously collected multiple frames of mountain images according to the specific implementation situation. For example, 10.

[0040] Specifically, the values in the R, G, and B channels are obtained by performing RGB separation processing on the current mountain image.

[0041] Specifically, the grayscale value is obtained by performing grayscale processing on the current mountain image.

[0042] S2: For the target pixel points among the pixel points in the current mountain image, determine the noise factor of the target pixel points.

[0043] It should be noted that by analyzing the grayscale value performance of each pixel point in the current mountain image, the noise factor of each pixel point is obtained; when analyzing the noise factor of each pixel point in the current mountain image, the greater the difference in grayscale value between each pixel point and the pixel points in its neighborhood, the greater the noise factor; however, when processing color images, the grayscale value analysis may not fully reflect the noise situation; therefore, continue to analyze the difference in the values of each pixel point in the current mountain image and the pixel points in its neighborhood in the R, G, and B channels, and the greater the difference, the greater the noise factor.

[0044] Determine the noise factor of the target pixel point according to the grayscale value of the target pixel point and the pixel points in its neighborhood, and the values of the target pixel point and the pixel points in its neighborhood in each channel.

[0045] Specifically, the noise factor satisfies:

[0046] ;

[0047] In the formula, is the noise factor of the pixel point in the current mountain image, is the number of pixel points in the neighborhood of the pixel point in the current mountain image, is the grayscale value of the pixel point in the current mountain image, is the pixel point in the current mountain image, is the grayscale value of the th pixel point in the neighborhood of the pixel point in the current mountain image, is the number of channels of the R, G, and B channels of the pixel point in the current mountain image, is the value of the th channel in the R, G, and B channels of the pixel point in the current mountain image, is the th pixel point in the neighborhood of the pixel point in the current mountain image, and

[0048] Implementers can set the range of the neighborhood according to the specific implementation situation. For example, an 8-neighborhood.

[0049] Among them, the larger it is, it indicates that the pixel points in the current mountain image have a greater difference in gray value with the pixel points in its 8-neighborhood, and the pixel points in the current mountain image are more likely to be noise pixel points, and then the noise factor is larger; the larger it is, it indicates that the pixel points in the current mountain image have a greater difference in the values in the R, G, and B channels with the pixel points in its 8-neighborhood. Then, the pixel points in the current mountain image will also have a greater difference in gray value with the pixel points in its 8-neighborhood. The pixel points in the current mountain image are more likely to be noise pixel points, and then the noise factor is larger.

[0050] S3: Determine the landslide factor of the target pixel point.

[0051] It should be noted that since the soil in the landslide area of the mountain usually shows a relatively red tone, the value of the pixel points in this kind of area in the R channel will be larger; therefore, the larger the value of the pixel points in the R channel in the area around a pixel point, it indicates that the area around this pixel point is more likely to be a landslide area, and the landslide factor of this pixel point will also be larger; however, the pixel points in the normal soil area exposed between the vegetation will also show the characteristic of having a larger value in the R channel, and the existence of this area will affect the judgment of the possibility that the area around a pixel point belongs to the landslide area; then through further scene investigation, it is found that landslide is a geological disaster caused by the action of gravity and the decline of the stability of soil or rock. In the area where landslide occurs, the movement and change of soil or rock often proceed along a specific direction, and this kind of material flow or displacement will cause a specific texture extension direction to appear in the image; therefore, if the gradient directions of all the pixel points with gradient changes in the area around a pixel point show stronger consistency, it indicates that the area around this pixel point is more likely to be a landslide area, and the landslide factor of this pixel point will also be larger.

[0052] Determine the landslide factor of the target pixel point according to the mean value of the values of the target pixel point and the pixel points in the surrounding area in the R channel, the mean value of the values of the pixel points in the current mountain image in the R channel, and the standard deviation of the gradient direction values of the target pixel point and all the pixel points with gradient changes in the surrounding area.

[0053] Specifically, the gradient direction value is obtained by using the Sobel operator.

[0054] Specifically, the landslide factor satisfies:

[0055] ;

[0056] In the formula, is the landslide factor of the pixel point in the current mountain image, is the average value of the values of the pixel point in the current mountain image and the pixel points in the surrounding area in the R channel, is the average value of the value of the pixel point in the current mountain image in the R channel, is the standard deviation of the gradient direction values of the pixel point in the current mountain image and all the pixel points with gradient changes in the surrounding area, is the first hyperparameter, is the standard normalization function.

[0057] Implementers can set the size of the surrounding area and the first hyperparameter according to the specific implementation situation. For example, the surrounding area is , and the first hyperparameter is 0.001; the existence of the first hyperparameter is to prevent from being 0, which may lead to meaningless calculation results.

[0058] Among them, the larger it is, the larger the relative size of the values of all pixel points in the R channel in the surrounding area of the pixel point in the current mountain image, which indicates that the greater the possibility that the pixel point in the current mountain image and the surrounding area belong to the landslide area, and the landslide factor of the pixel point in the current mountain image will also be larger; the smaller it is, the closer the gradient direction values of the pixel point in the current mountain image and all the pixel points with gradient changes in the surrounding area, which indicates that the stronger the consistency of the gradient directions of the pixel point in the current mountain image and all the pixel points with gradient changes in the surrounding area, which indicates that the greater the possibility that the pixel point in the current mountain image and the surrounding area belong to the landslide area, and the landslide factor of the pixel point in the current mountain image will also be larger.

[0059] S4: Determine the number of reference historical mountain images of the target pixel point.

[0060] It should be noted that after obtaining the noise factor of each pixel point in the current mountain image, according to the noise factor, for each pixel point in the current mountain image, determine the number of historical mountain images that each pixel point needs to refer to when calculating the dark channel value.

[0061] Determine the number of reference historical mountain images of the target pixel point according to the noise factor.

[0062] Specifically, the number of the reference historical mountain images satisfies:

[0063] ;

[0064] In the formula, is the pixel point in the current mountain image The number of reference historical mountain images, is the preset initial number, is the pixel point in the current mountain image The noise factor of, is the rounding function.

[0065] Implementers can set the initial number according to the specific implementation situation. For example, 10.

[0066] Among them, The larger, the worse the accuracy of the dark channel value at this pixel point. Then the demand for historical mountain images at this pixel point will be greater, and the number of reference historical mountain images at this pixel point will be larger.

[0067] S5: Determine the weight when weighting the dark channel values of the pixel points corresponding to the target pixel point in each frame of the reference historical mountain image.

[0068] It should be noted that the landslide factor reflects the possibility that a pixel point belongs to the landslide area with the surrounding area. Therefore, to a certain extent, the landslide factor can be used as the basis for weight calculation.

[0069] According to the landslide factor, the landslide factor of the pixel points corresponding to the target pixel point in each frame of the reference historical mountain image, and the noise factor, determine the weight when weighting the dark channel values of the pixel points corresponding to the target pixel point in each frame of the reference historical mountain image.

[0070] Specifically, the weight satisfies:

[0071] ;

[0072] In the formula, is the weight when weighting the dark channel value of the pixel point corresponding to the pixel point in the current mountain image in the corresponding position in the frame of the reference historical mountain image, is the landslide factor of the pixel point is the frame of the reference historical mountain image, and the landslide factor of the pixel point corresponding to the pixel point in the current mountain image, is the The noise factor of the pixel at the corresponding position in the frame reference historical mountain image and the pixel at the corresponding position in the current mountain image is the noise factor of the pixel at the corresponding position, is the first hyperparameter, is the second hyperparameter, is the standard normalization function, is the absolute value symbol.

[0073] Implementers can set the second hyperparameter according to the specific implementation situation. For example, 0.001; the existence of the first hyperparameter is to prevent when it is 0, a situation where the calculation result is meaningless occurs. The existence of the second hyperparameter is to prevent when it is 0, a situation where the calculation result is meaningless occurs.

[0074] Among them, The smaller it is, the greater the possibility that these two pixels are in the same area in the actual mountain body. Then, the reference value of the dark channel value of the pixel at the corresponding position in this frame of reference historical mountain image is greater, and its weight when weighted should be greater; The smaller it is, the more real the pixel at the corresponding position in this frame of reference historical mountain image is. Then, the weight of the dark channel value of the pixel at the corresponding position in this frame of reference historical mountain image when weighted will also be greater.

[0075] S6: Obtain the optimized dark channel value of the target pixel.

[0076] It should be noted that by relying on the difference in the landslide factor of the pixels at the corresponding positions in the current mountain image and all its reference historical mountain images, combined with the noise factors of the pixels at the corresponding positions in all its reference historical mountain images, the optimized dark channel value of each pixel in the current mountain image is calculated by weighted summation.

[0077] Weighted sum the dark channel values of the pixels at the corresponding positions in the historical mountain image and the target pixel according to the weight to obtain the optimized dark channel value of the target pixel.

[0078] Implementers can set the size of the adjacent area according to the specific implementation situation. For example, .

[0079] Specifically, the dark channel value is the minimum value of the values of the pixel and all pixels within the adjacent range in the R, G, and B channels.

[0080] Specifically, the optimized dark channel value satisfies:

[0081] ;

[0082] In the formula, is the optimized dark channel value of the pixel points within the current mountain image , is the number of reference historical mountain images for the pixel points within the current mountain image . is the weight when weighting the dark channel values of the pixel points at the corresponding positions in the th frame of the reference historical mountain image and the pixel points within the current mountain image is the dark channel value of the pixel points at the corresponding positions in the th frame of the reference historical mountain image and the pixel points within the current mountain image

[0083] S7: Based on the optimized dark channel value, use the dark channel dehazing algorithm to enhance the current mountain image

[0084] Implementers can set the constant in the formula for estimating the transmittance map of each pixel point in the dark channel dehazing algorithm according to the specific implementation situation. For example, 0.95

[0085] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention

Claims

1. A method for enhancing geological disaster exploration images, characterized in that: include: Get the values ​​of the pixels in the current mountain image in the R, G, B channels and the grayscale values ​​of the pixels; For a target pixel in the current mountain image, the noise factor of the target pixel is determined according to the grayscale values ​​of the target pixel and the pixels in the neighborhood, and the values ​​of the target pixel and the pixels in the neighborhood in each channel; Determine the landslide factor of the target pixel point according to the mean value of the target pixel point and the pixels in the surrounding area in the R channel, the mean value of the pixels in the current mountain image in the R channel, and the standard deviation of the gradient direction values ​​of the target pixel point and all the pixels with gradient changes in the surrounding area; According to the noise factor, the number of reference historical mountain images of the target pixel is determined; According to the landslide factor, the landslide factor of the pixel point corresponding to the target pixel point in each frame of the reference historical mountain image, and the noise factor, the weight of the dark channel value of the pixel point corresponding to the target pixel point in each frame of the reference historical mountain image is determined to satisfy: ； In the formula, For the Frame reference historical mountain image and current mountain image pixel points The weight of the dark channel value of the pixel at the corresponding position during weighting, is the pixel point in the current mountain image The landslide factor, For the Frame reference historical mountain image and current mountain image pixel points The landslide factor of the pixel point at the corresponding position, For the Frame reference historical mountain image and current mountain image pixel points The noise factor of the pixel at the corresponding position, is the first hyperparameter, is the second hyperparameter, is the standard normalization function, is the absolute value symbol; According to the weights, the dark channel values ​​of the pixels at the positions corresponding to the target pixels in the historical mountain images are weighted and summed to obtain the optimized dark channel value of the target pixel, which satisfies: ； In the formula, is the pixel point in the current mountain image The optimized dark channel value of is the pixel point in the current mountain image The number of reference historical mountain images, For the Frame reference historical mountain image and current mountain image pixel points The dark channel value of the pixel at the corresponding position; Based on the optimization of dark channel value, the dark channel dehazing algorithm is used to enhance the current mountain image.

2. A method for enhancing geological disaster exploration images according to claim 1, characterized in that: The values ​​in the R, G, and B channels are obtained by performing RGB separation processing on the current mountain image.

3. The method for enhancing geological disaster exploration images according to claim 1, characterized in that: The grayscale value is obtained by graying the current mountain image.

4. The method for enhancing geological disaster exploration images according to claim 1, characterized in that: The noise factor satisfies: ； In the formula, is the pixel point in the current mountain image The noise factor, is the pixel point in the current mountain image The number of pixels in the neighborhood of is the pixel point in the current mountain image The gray value of is the pixel point in the current mountain image In the neighborhood of The gray value of a pixel, is the pixel point in the current mountain image The number of channels of R, G, and B channels, is the pixel point in the current mountain image In the R, G, B channels The values ​​in the channels, is the pixel point in the current mountain image In the neighborhood of The pixel point in the R, G, B channels The values ​​in the channels, is the standard normalization function.

5. The method for enhancing geological disaster exploration images according to claim 1, characterized in that: The gradient direction value is obtained using the Sobel operator.

6. The method for enhancing geological disaster exploration images according to claim 1, characterized in that: The landslide factor satisfies: ； In the formula, is the pixel point in the current mountain image The landslide factor, is the pixel point in the current mountain image The mean value of the pixel points in the surrounding area in the R channel, is the mean value of the pixel points in the current mountain image in the R channel, is the pixel point in the current mountain image The standard deviation of the gradient direction values ​​of all pixels with gradient changes in the surrounding area, is the first hyperparameter, is the standard normalization function.

7. The method for enhancing geological disaster exploration images according to claim 1, characterized in that: The number of reference historical mountain images satisfies: ； In the formula, is the pixel point in the current mountain image The number of reference historical mountain images, is the preset initial quantity, is the pixel point in the current mountain image The noise factor, Is the rounding function.

8. The method for enhancing geological disaster exploration images according to claim 1, characterized in that: The dark channel value is the minimum value of the pixel point and all the pixels in the adjacent range in the R, G, and B channels.

Images