Repair effect evaluation method for environmental restoration engineering

Abstract

The invention relates to the technical field of image processing, in particular to a restoration effect evaluation method for environmental restoration engineering, which comprises the following steps: acquiring an underground water image, and graying to obtain an underground water grayscale image; segmenting the groundwater grayscale image to obtain to-be-processed pixel points, and obtaining a plurality of windows of the to-be-processed pixel points; according to the box plot of each window of the to-be-processed pixel point and the number of abnormal pixel points in each window, obtaining the abnormal degree of the to-be-processed pixel point in the box plot of each window, and obtaining the noise intensity of the to-be-processed pixel point according to the abnormal degree; obtaining a noise intensity parameter sequence according to the noise intensity, and obtaining the optimization degree of each noise intensity parameter; and completing groundwater remediation evaluation according to the optimization degree and the noise intensity. According to the method, the influence that impurities and noisy points in underground water are relatively similar in gray level expression in the image is reduced, the accuracy of noisy point recognition is improved, and the robustness of the system is further improved.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and more specifically to a method for evaluating the restoration effect in environmental remediation projects. Background Technology

[0002] Groundwater is an important component of water resources and a vital source of water for agricultural irrigation, industrial and mining operations, and urban use. Groundwater remediation is a crucial aspect of environmental engineering remediation.

[0003] In existing technologies for groundwater remediation detection, the quality of groundwater images acquired is often poor due to the ambient light in the image acquisition area. Therefore, denoising is frequently required to enhance the image quality. Box plots are a method for noise identification, which identifies noise by analyzing the size and distribution of pixel values ​​within a local area, specifically identifying pixels with excessively deviating grayscale values. However, since impurities and noise in groundwater exhibit similar grayscale characteristics in images, noise identified solely by a single box plot may be limited and unpredictable, leading to errors in noise identification. This can result in the loss of detailed information in the image during denoising, ultimately affecting the accuracy and efficiency of subsequent groundwater remediation detection. Summary of the Invention

[0004] To address the above problems, this invention provides a method for evaluating the remediation effect in environmental remediation projects.

[0005] The present invention provides a method for evaluating the remediation effect in environmental remediation engineering, which adopts the following technical solution: One embodiment of the present invention provides a method for evaluating the remediation effect in environmental remediation engineering, the method comprising the following steps: Collect groundwater images and convert them to grayscale to obtain groundwater grayscale images; The groundwater grayscale image is segmented to obtain several pixels to be processed; any pixel to be processed is denoted as the target pixel to be processed; a window is constructed for the target pixel to be processed and the window is translated to obtain several windows of the target pixel to be processed; Based on the window of the target pixel to be processed, obtain the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window; based on the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window, obtain the degree of abnormality of the box plot of the target pixel to be processed in each window; based on the degree of abnormality and the distance between the target pixel to be processed and the center pixel of the window, obtain the noise intensity of the target pixel to be processed. A noise intensity parameter sequence is obtained based on the noise intensity, the noise intensity parameter sequence containing several noise intensity parameters; a first set and a second set are obtained based on the noise intensity parameter sequence; the regularity of the first set is obtained based on the distance between the noise intensity corresponding to the pixels to be processed in the first set; the regularity of the second set is obtained; the optimization degree of each noise intensity parameter is obtained based on the regularity of the first set and the regularity of the second set. The third and fourth sets are obtained based on the degree of optimization and noise intensity; based on the regularity of the third, fourth and first sets, a number of noise pixels and a number of impurity pixels in the groundwater grayscale image are obtained; based on the groundwater grayscale image and the noise pixels, the denoised groundwater grayscale image is obtained. Collect images of the remediated groundwater and conduct a groundwater remediation assessment based on the denoised grayscale images of the groundwater.

[0006] Furthermore, the specific steps for obtaining the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window are as follows: Let any window containing the target pixels be processed be designated as the first window. Arrange the gray values ​​of all pixels in the first window in ascending order to obtain a sequence, designated as the first sequence. Input the first sequence into the box plot algorithm and output a box plot, designated as the box plot of the first window. Calculate the number of abnormal pixels in the first window based on the box plot of the first window.

[0007] Furthermore, the specific steps for obtaining the degree of anomalousness of the box plot of the target pixel to be processed in each window, based on the box plot of each window and the number of anomalous pixels in each window, are as follows: In the formula, This represents the number of abnormal pixels in the first window. The grayscale value of the target pixel to be processed. The median of the box plot in the first window. To take the absolute value, It is an exponential function with the natural constant as its base. The degree of anomaly of the target pixel in the box plot of the first window.

[0008] Furthermore, the specific steps for obtaining the noise intensity of the target pixel based on the degree of anomaly and the distance between the target pixel and the center pixel of the window are as follows: In the formula, For the target pixel to be processed at the 1st The degree of anomaly in the box plot of each window. The number of windows containing the target pixels to be processed; For the target pixel to be processed The Euclidean distance between the center pixel of the window and the target pixel to be processed; It is an exponential function with the natural constant as its base; The variance of the anomaly degree of the target pixel across all windows in the box plot. For normalization function, The noise intensity of the target pixel to be processed.

[0009] Furthermore, the specific steps for obtaining the noise intensity parameter sequence based on the noise intensity are as follows: Obtain the noise intensity of each pixel to be processed, and find the maximum and minimum noise intensity values. Record the minimum noise intensity as the minimum noise intensity and the maximum noise intensity as the maximum noise intensity. Starting from the minimum noise intensity, increase the noise intensity each time. , The minimum noise intensity is set to a third value, and the noise intensity is increased until it is greater than or equal to the maximum noise intensity for the first time. Several noise intensity parameters are obtained. The minimum noise intensity, all noise intensity parameters and the maximum noise intensity are arranged in ascending order to obtain a sequence, which is denoted as the noise intensity parameter sequence.

[0010] Furthermore, the specific steps for obtaining the first set and the second set based on the noise intensity parameter sequence are as follows: Let any one of the noise intensity parameters in the noise intensity parameter sequence be denoted as the target noise intensity parameter; obtain the noise intensity of each pixel to be processed, and denote the set of all noise intensities less than or equal to the target noise intensity parameter as the first set, and the set of all noise intensities greater than the target noise intensity parameter as the second set.

[0011] Furthermore, the specific steps for obtaining the regularity of the first set based on the distance between the noise intensity and the pixels to be processed in the first set are as follows: In the formula, The regularity of the first set; The number of noise intensities in the first set. The number of combinations of any two noise intensities in the first set; For the first The pixel point to be processed corresponding to one of the noise intensities in the combination is denoted as the first pixel point; For the first The pixel point to be processed corresponding to the other noise intensity in the combination is denoted as the second pixel point; The Euclidean distance between the first pixel and the second pixel; The variance of the Euclidean distance between the pixels to be processed corresponding to all noise intensities in the first set; It is an exponential function with the natural constant as its base.

[0012] Furthermore, the specific steps for determining the optimality of each noise intensity parameter based on the regularity of the first set and the regularity of the second set are as follows: In the formula, The degree of optimization of the target noise intensity parameter; The regularity of the first set; The regularity of the second set; To take the absolute value.

[0013] Furthermore, the specific steps for obtaining several noise pixels and several impurity pixels of the groundwater grayscale image based on the regularity of the third set, the fourth set, and the first set are as follows: Obtain the regularity of the third set and the regularity of the fourth set. Among the regularities of the third set and the fourth set, the pixel to be processed corresponding to the noise intensity in the set with the smallest regularity is taken as the noise pixel; the pixel to be processed corresponding to the noise intensity in the set with the largest regularity is taken as the impurity pixel.

[0014] Furthermore, the specific steps for completing the groundwater remediation assessment based on the impurity pixels and the denoised groundwater grayscale image are as follows: The difference in the number of impurity pixels between the denoised and restored groundwater grayscale images is obtained. The ratio of the difference to the total number of pixels is compared with an empirical threshold to complete the groundwater remediation assessment.

[0015] The beneficial effects of the technical solution of this invention are as follows: After acquiring a grayscale image of groundwater, this invention segments the groundwater grayscale image to obtain several pixels to be processed. These pixels include pixels corresponding to groundwater impurities and noise pixels. By analyzing the degree of anomaly of the pixel to be processed in the box plots of different windows, the noise intensity of the pixel to be processed is obtained, which better reflects the noise characteristics of the pixel to be processed and reduces the influence of the similar grayscale appearance of impurities and noise in the image, resulting in better subsequent image denoising effect. This allows for effective and intuitive groundwater restoration, improving work efficiency and reducing labor costs. Then, the pixels in the groundwater grayscale image are classified into two sets by noise intensity. By analyzing different noise intensity parameters as classification thresholds, i.e., the optimality of noise intensity parameters, the noise pixels and impurity pixels in the groundwater grayscale image are more accurately distinguished, resulting in several noise pixels and several impurity pixels in the groundwater grayscale image. This effectively solves the randomness of traditional single box plot determination of noise level. Meanwhile, by utilizing the distribution characteristics of impurities and noise to adaptively set a threshold for noise levels, the robustness of the system is improved, noise can be identified, and the details of the image itself can be preserved, making groundwater remediation detection more intuitive and improving work efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art 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.

[0017] Figure 1 A flowchart illustrating the steps of a method for evaluating the remediation effect in an environmental remediation project, as provided in one embodiment of the present invention; Figure 2 A groundwater grayscale image provided as an embodiment of the present invention for evaluating the remediation effect of an environmental remediation project; Figure 3 This is a segmentation result diagram of a method for evaluating the remediation effect in an environmental remediation project, provided in an embodiment of the present invention. Detailed Implementation

[0018] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for evaluating the remediation effect in environmental remediation engineering according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0020] The following description, in conjunction with the accompanying drawings, details a specific scheme for evaluating the remediation effect of an environmental remediation project provided by this invention.

[0021] Please see Figure 1 The diagram illustrates a flowchart of a method for evaluating the remediation effect in environmental remediation engineering according to an embodiment of the present invention. The method includes the following steps: Step S001: Acquire groundwater images and convert them to grayscale to obtain groundwater grayscale images.

[0022] It should be noted that this embodiment combines the abnormal performance of a single pixel in multiple box plots to obtain the noise level of the pixel, and through the optimization of each noise level threshold, the noise points are accurately identified, thereby performing interpolation to denoise and enhance the image, which is convenient for subsequent groundwater remediation detection. Before starting the analysis, it is necessary to acquire the image first.

[0023] Specifically, images of groundwater are acquired using a high-resolution camera and denoted as groundwater images; these images are then converted to grayscale to obtain grayscale images, denoted as groundwater grayscale images. It should be noted that the groundwater images are RGB images; please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a grayscale image of groundwater in this embodiment. Figure 2 It contains impurities in the groundwater and several noise points, with the noise points being smaller than the impurities.

[0024] At this point, a grayscale image of the groundwater was obtained.

[0025] Step S002: Segment the groundwater grayscale image to obtain the pixels to be processed, and obtain several windows of the pixels to be processed.

[0026] It should be noted that because the anomalies identified by a single box plot are random and noise is relatively small compared to impurities, the noise level of a pixel can be obtained by combining multiple box plots containing pixels. Furthermore, after obtaining the noise level of a pixel, a specific noise level threshold can be determined by analyzing the distribution characteristics of noise and impurities to distinguish between noise and impurities.

[0027] It should be noted that since noise and impurities may appear as bright or dark spots in groundwater images, and their gray values ​​differ significantly from the background, the Otsu method can be used to segment impurities and noise. Then, only the segmented points are analyzed for noise levels to reduce computational load.

[0028] Specifically, the groundwater grayscale image is segmented to obtain several pixels to be processed, as follows: Otsu thresholding was applied to the groundwater grayscale image to obtain the optimal segmentation threshold. Pixels with grayscale values ​​less than the optimal threshold were set to 0, while pixels with grayscale values ​​greater than or equal to the threshold were set to 1, resulting in a segmentation image. Pixels with a grayscale value of 0 in the segmentation image were then designated as pixels to be processed. It should be noted that these pixels include those corresponding to noise and impurities; please refer to [link to relevant documentation]. Figure 3 , Figure 3 This is a segmentation result diagram of this embodiment.

[0029] It should be noted that, as described above, several pixels to be processed are obtained. By constructing different windows for each pixel, the anomaly of the current pixel in multiple windows is analyzed and weighted averaged to determine the noise point. The anomaly of the window is obtained by the deviation of the current pixel from the center of the window and the number of abnormal pixels. The weight is the distance of the current pixel from the center of the window.

[0030] Specifically, any pixel to be processed is denoted as the target pixel to be processed. A window is constructed for the target pixel to be processed, and the window is translated to obtain several windows of the target pixel to be processed, as follows: In the grayscale image of groundwater, a [structure / structure] is constructed centered on the target pixel to be processed. The window is denoted as the target window for the target pixel to be processed; the target window is translated horizontally to the right. Each time, the process shifts by one pixel to obtain the target pixel to be processed. One window; For a preset first value, As a preset second value, this embodiment uses , Describe the scene; pan the target window horizontally to the left. Each time, the process shifts by one pixel to obtain the target pixel to be processed. One window; move the target window vertically upwards. Each time, the process shifts by one pixel to obtain the target pixel to be processed. A window; move the target window vertically downwards. Each time, the process shifts by one pixel to obtain the target pixel to be processed. A window.

[0031] It should be noted that when constructing or translating the target window, it may exceed the boundary of the groundwater grayscale image. In this case, this embodiment uses quadratic linear interpolation to interpolate and fill the data in the part of the groundwater grayscale image that exceeds the boundary.

[0032] At this point, several windows of the target pixels to be processed are obtained.

[0033] Step S003: Based on the box plot of each window of the pixel to be processed and the number of abnormal pixels in each window, obtain the degree of abnormality of the box plot of the pixel to be processed in each window, and obtain the noise intensity of the pixel to be processed based on the degree of abnormality.

[0034] It should be noted that because noise points are usually relatively isolated points, there are fewer outliers (points outside the upper and lower boundaries of the box plot) in the box plot constructed within its window, and their deviation from the median will be large. Therefore, the degree of anomaly within a window can be represented by the number of outliers in the box plot and the degree of deviation of the gray value of the current pixel from the median in the box plot. The logical relationship is that the fewer the number of outliers and the greater the deviation, the higher the degree of anomaly.

[0035] Specifically, based on the window of the target pixel to be processed, the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window are obtained, as follows: Let any window containing the target pixels be processed be designated as the first window. Arrange the grayscale values ​​of all pixels in the first window in ascending order to obtain a sequence, designated as the first sequence. Input the first sequence into the box plot algorithm and output a box plot, designated as the box plot of the first window. Calculate the number of abnormal pixels in the first window based on the box plot of the first window. It should be noted that inputting the first sequence into the box plot algorithm, outputting a box plot, and calculating the number of abnormal pixels in the first window based on the box plot of the first window is an existing method of the box plot algorithm, which will not be elaborated upon in this embodiment.

[0036] Furthermore, based on the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window, the degree of abnormality of the box plot of the target pixel to be processed in each window is obtained, as follows: In the formula, This represents the number of abnormal pixels in the first window. The grayscale value of the target pixel to be processed. The median of the box plot in the first window. To take the absolute value, This embodiment uses an exponential function with the natural constant as its base. The model is used to represent the inverse proportional relationship. As input to the model, implementers can set an inverse proportional function according to the specific implementation situation. The degree of anomaly of the target pixel in the box plot of the first window.

[0037] It should be noted that, The box plot in the first window indicates the degree of deviation of the target pixel to be processed. The fewer abnormal pixels there are in the first window, the greater the degree of deviation of the target pixel to be processed, and the higher the degree of abnormality of the target pixel to be processed in the box plot in the first window.

[0038] It should be noted that since the pixels in different box plots are different, that is, the distance between different box plots and the target pixel to be processed is different, the importance of box plots at different distances is different. The logical relationship is that the closer the distance, the higher the importance, that is, the higher the weight. At the same time, for noise, it is usually an isolated point. Therefore, the more stable the anomalous points in its surrounding window are, the better. That is, the more stable the degree of anomalousness of the surrounding box plot is, the more isolated the pixel is, and the higher the probability that it is a noise pixel.

[0039] Specifically, the noise intensity of the target pixel is obtained based on the degree of anomaly and the distance between the target pixel and the center pixel of the window, as follows: In the formula, For the target pixel to be processed at the 1st The degree of anomaly in the box plot of each window. The number of windows representing the target pixels to be processed; it should be noted that in this embodiment, the number of windows representing the target pixels to be processed is 13, that is, the target window and 12 windows that are translated a total of 12 times in four directions respectively; For the target pixel to be processed The Euclidean distance between the center pixel of the window and the target pixel to be processed; This embodiment uses an exponential function with the natural constant as its base. The model is used to represent the inverse proportional relationship. As input to the model, implementers can set an inverse proportional function according to the specific implementation situation; The variance of the anomaly degree of the target pixel across all windows in the box plot. This is a linear normalization function, which normalizes all pixels to be processed. , The noise intensity of the target pixel to be processed.

[0040] It should be noted that, This represents the weighted average of the anomalies of the target pixel across all windows' boxplots. The weights are determined by the Euclidean distance between the center pixel of the window and the target pixel. The smaller the distance, the greater the weight, and the less relevant the anomaly level is. The smaller the variance of the anomaly level of the target pixel across all windows, the more stable the anomaly level of the target pixel is across different windows, indicating that the pixel is more isolated and the noise intensity of the target pixel is greater.

[0041] At this point, the noise intensity of the target pixel to be processed is obtained.

[0042] Step S004: Obtain the noise intensity parameter sequence based on the noise intensity, and determine the optimality of each noise intensity parameter.

[0043] It should be noted that, since the distribution of impurities in groundwater usually shows a trend of aggregation or diffusion (regularity), while noise is usually randomly distributed (irregularity), this embodiment divides the above-mentioned pixels to be processed into two categories by iterating the noise level threshold, and by calculating the degree of preference, an adaptive threshold is achieved to identify noise from the pixels to be processed.

[0044] Specifically, the noise intensity parameter sequence is obtained based on the noise intensity, as follows: Obtain the noise intensity of each pixel to be processed, and find the maximum and minimum noise intensity values. Record the minimum noise intensity as the minimum noise intensity and the maximum noise intensity as the maximum noise intensity. Starting from the minimum noise intensity, increase the noise intensity each time. , As a preset third value, this embodiment uses The process continues until the noise intensity is greater than or equal to the maximum noise intensity for the first time, resulting in several noise intensity parameters. The minimum noise intensity, all noise intensity parameters, and the maximum noise intensity are then arranged in ascending order to obtain a sequence, which is denoted as the noise intensity parameter sequence. It should be noted that the noise intensity parameter sequence contains several noise intensity parameters, and the minimum and maximum noise intensities are also noise intensity parameters.

[0045] It should be noted that each noise intensity parameter in the noise intensity parameter sequence can divide the noise intensity of all pixels to be processed into two categories, representing noise and impurities. For a good selection threshold, the more irregular the pixel position distribution in the noise category, the better, while the more regular the pixel distribution in the impurity category, the better. In this embodiment, the average distance between any two pixels in a pixel category is used to characterize the pixel clustering trend, where a smaller average value indicates greater clustering. Since pixels in the impurity category may also exhibit diffusion values, using only the average distance as a regularity criterion will have errors, while the distribution of noise is random, meaning the distance between its pixels is relatively discrete. In summary, the average distance and the dispersion of pixel distances can be used together to characterize the regularity of pixels. The smaller the average value and the smaller the dispersion, the stronger the regularity, and the higher the probability that the category belongs to the impurity category; conversely, the same applies. Furthermore, the difference in regularity between the two categories characterizes the selection degree. The larger the difference between the two categories, the better the current noise intensity parameter separates noise and impurities, and the higher its selection degree.

[0046] Specifically, the first set and the second set are obtained based on the noise intensity parameter sequence, as follows: Let any one of the noise intensity parameters in the noise intensity parameter sequence be denoted as the target noise intensity parameter; obtain the noise intensity of each pixel to be processed, and denote the set of all noise intensities less than or equal to the target noise intensity parameter as the first set, and the set of all noise intensities greater than the target noise intensity parameter as the second set.

[0047] Furthermore, based on the distance between the noise intensity and the pixels to be processed in the first set, the regularity of the first set is obtained, as follows: In the formula, The regularity of the first set; The number of noise intensities in the first set. The number of combinations of any two noise intensities in the first set; For the first The pixel point to be processed corresponding to one of the noise intensities in the combination is denoted as the first pixel point; For the first The pixel point to be processed corresponding to the other noise intensity in the combination is denoted as the second pixel point; The Euclidean distance between the first pixel and the second pixel; The variance of the Euclidean distance between the pixels to be processed corresponding to all noise intensities in the first set; This embodiment uses an exponential function with the natural constant as its base. The model is used to represent the inverse proportional relationship. As input to the model, implementers can set an inverse proportional function according to the specific implementation situation.

[0048] It should be noted that, This represents the average distance between the pixels to be processed corresponding to the noise intensity in the first set, characterizing the clustering trend of the pixels. The smaller the average value and the smaller the dispersion, the stronger the regularity.

[0049] Furthermore, based on the distance between the noise intensity and the pixels to be processed in the second set, the regularity of the second set is obtained, as follows: In the formula, The regularity of the second set; The number of noise intensities in the second set. The number of combinations of any two noise intensities in the second set; For the first The pixel point to be processed corresponding to one of the noise intensities in the combination is denoted as the third pixel point. For the first The pixel point to be processed corresponding to the other noise intensity in the combination is denoted as the fourth pixel point; The Euclidean distance between the third and fourth pixels; The variance of the Euclidean distance between the pixels to be processed corresponding to all noise intensities in the second set; This embodiment uses an exponential function with the natural constant as its base. The model is used to represent the inverse proportional relationship. As input to the model, implementers can set an inverse proportional function according to the specific implementation situation.

[0050] Furthermore, based on the regularities of the first set and the second set, the optimality of each noise intensity parameter is obtained, as follows: In the formula, The degree of optimization of the target noise intensity parameter; The regularity of the first set; The regularity of the second set; To take the absolute value.

[0051] Thus, the optimality of the target noise intensity parameters is obtained.

[0052] Step S005: Obtain the noise pixels and impurity pixels of the groundwater grayscale image according to the optimization degree and noise intensity, obtain the denoised groundwater grayscale image, and complete the groundwater remediation assessment based on the impurity pixels and the denoised groundwater grayscale image.

[0053] It should be noted that the degree of optimization is characterized by the regularity difference between the two sets. The greater the regularity difference between the two sets, the better the current noise intensity parameter separates noise and impurities, and the higher its degree of optimization as a threshold.

[0054] Furthermore, based on the degree of preference and noise intensity, the third and fourth sets are obtained, as follows: The optimization degree of each noise intensity parameter is obtained, and the noise intensity parameter corresponding to the maximum optimization degree is taken as the optimal threshold. The noise intensity of each pixel to be processed is obtained. The set of all noise intensities less than or equal to the optimal threshold is denoted as the third set, and the set of all noise intensities greater than the optimal threshold is denoted as the fourth set.

[0055] It should be noted that the noise level corresponding to the highest degree of optimization is the optimal threshold. Under this threshold, noise and impurities are best separated. Then, the regularity of the two types of pixels under the optimal threshold is calculated. The class with less regularity is the noise class, thus completing the identification of noise.

[0056] Specifically, based on the regularities of the third, fourth, and first sets, several noise pixels and several impurity pixels in the groundwater grayscale image are obtained, as follows: The regularity of the third set and the regularity of the fourth set are obtained. Among the regularities of the third set and the fourth set, the pixel point to be processed corresponding to the noise intensity in the set with the smallest regularity is taken as the noise pixel point; the pixel point to be processed corresponding to the noise intensity in the set with the largest regularity is taken as the impurity pixel point. It should be noted that the methods for obtaining the regularity of the third set and the fourth set are the same as those for obtaining the regularity of the first set, and will not be repeated in this embodiment.

[0057] Furthermore, based on the groundwater grayscale image and the noise pixels, a denoised groundwater grayscale image is obtained, as follows: Let any noise pixel be designated as the target noise pixel. In the groundwater grayscale image, the grayscale value of the center pixel of the four neighboring pixels of the target noise pixel is obtained by bilinear interpolation and designated as the first grayscale value. Replace the grayscale value of the target noise pixel with the first grayscale value. By replacing the grayscale value of each noise pixel, the denoised groundwater grayscale image is finally obtained.

[0058] Furthermore, a groundwater remediation assessment was conducted based on the denoised groundwater grayscale image, as detailed below: By detecting the impurity content in groundwater, appropriate adsorbents or activated carbon adsorbents are added based on the impurity content. Organic matter and heavy metal ions in the groundwater are adsorbed onto the material surface, thus removing the impurities. Then, a grayscale image of the groundwater after impurity removal is acquired and subjected to the aforementioned denoising process to obtain a restored grayscale image. The difference in the number of impurity pixels between the denoised and restored grayscale images is compared, thus effectively and intuitively performing groundwater restoration, improving work efficiency and reducing labor costs. In this embodiment, an empirical threshold of 0.8 is set. When the ratio of the difference in the number of impurity pixels to the total number of pixels exceeds the empirical threshold, the restoration effect is considered poor.

[0059] It should be noted that the method for obtaining the new denoised groundwater grayscale image is the same as the method for obtaining the denoised groundwater grayscale image, and will not be repeated in this embodiment. The impurity pixels in the denoised groundwater grayscale image are the impurity pixels in the groundwater grayscale image.

[0060] Thus, by denoising the grayscale image of the underground, the groundwater remediation assessment is completed.

[0061] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for evaluating the remediation effect in environmental remediation projects, characterized in that, The method includes the following steps: Collect groundwater images and convert them to grayscale to obtain groundwater grayscale images; The groundwater grayscale image is segmented to obtain several pixels to be processed; any pixel to be processed is denoted as the target pixel to be processed; a window is constructed for the target pixel to be processed and the window is translated to obtain several windows of the target pixel to be processed; Based on the window of the target pixel to be processed, obtain the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window; based on the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window, obtain the degree of abnormality of the box plot of the target pixel to be processed in each window; based on the degree of abnormality and the distance between the target pixel to be processed and the center pixel of the window, obtain the noise intensity of the target pixel to be processed. A noise intensity parameter sequence is obtained based on the noise intensity, the noise intensity parameter sequence containing several noise intensity parameters; a first set and a second set are obtained based on the noise intensity parameter sequence; the regularity of the first set is obtained based on the distance between the noise intensity corresponding to the pixels to be processed in the first set; the regularity of the second set is obtained; the optimization degree of each noise intensity parameter is obtained based on the regularity of the first set and the regularity of the second set. The third and fourth sets are obtained based on the degree of optimization and noise intensity; based on the regularity of the third, fourth and first sets, a number of noise pixels and a number of impurity pixels in the groundwater grayscale image are obtained; based on the groundwater grayscale image and the noise pixels, the denoised groundwater grayscale image is obtained. Collect images of the remediated groundwater and conduct a groundwater remediation assessment based on the denoised grayscale images of the groundwater.

2. The method for evaluating the remediation effect in environmental remediation engineering according to claim 1, characterized in that, The specific steps for obtaining the box plot of each window of the target pixel to be processed and the number of abnormal pixels in each window are as follows: Let any window containing the target pixels be processed be designated as the first window. Arrange the gray values ​​of all pixels in the first window in ascending order to obtain a sequence, designated as the first sequence. Input the first sequence into the box plot algorithm and output a box plot, designated as the box plot of the first window. Calculate the number of abnormal pixels in the first window based on the box plot of the first window.

3. The method for evaluating the remediation effect in environmental remediation engineering according to claim 2, characterized in that, The specific steps for determining the degree of anomalousness of the target pixel in each window's box plot based on the box plot of each window and the number of anomalous pixels in each window are as follows: In the formula, This represents the number of abnormal pixels in the first window. The grayscale value of the target pixel to be processed. The median of the box plot in the first window. To take the absolute value, It is an exponential function with the natural constant as its base. The degree of anomaly of the target pixel in the box plot of the first window.

4. The method for evaluating the remediation effect in environmental remediation engineering according to claim 1, characterized in that, The specific steps for obtaining the noise intensity of the target pixel based on the degree of anomaly and the distance between the target pixel and the center pixel of the window are as follows: In the formula, For the target pixel to be processed in the th The degree of anomaly in the box plot of each window. The number of windows containing the target pixels to be processed; For the target pixel to be processed The Euclidean distance between the center pixel of the window and the target pixel to be processed; It is an exponential function with the natural constant as its base; The variance of the anomaly degree of the target pixel across all windows in the box plot. For normalization function, The noise intensity of the target pixel to be processed.

5. The method for evaluating the remediation effect in environmental remediation engineering according to claim 1, characterized in that, The specific steps involved in obtaining the noise intensity parameter sequence based on noise intensity are as follows: Obtain the noise intensity of each pixel to be processed, obtain the maximum and minimum noise intensity, record the minimum noise intensity as the minimum noise intensity, and record the maximum noise intensity as the maximum noise intensity; Start with the minimum noise level, and increase it each time. , The minimum noise intensity is set to a third value, and the noise intensity is increased until it is greater than or equal to the maximum noise intensity for the first time. Several noise intensity parameters are obtained. The minimum noise intensity, all noise intensity parameters and the maximum noise intensity are arranged in ascending order to obtain a sequence, which is denoted as the noise intensity parameter sequence.

6. The method for evaluating the remediation effect in environmental remediation engineering according to claim 1, characterized in that, The specific steps for obtaining the first set and the second set based on the noise intensity parameter sequence are as follows: Let any one of the noise intensity parameters in the noise intensity parameter sequence be denoted as the target noise intensity parameter; obtain the noise intensity of each pixel to be processed, and denote the set of all noise intensities less than or equal to the target noise intensity parameter as the first set, and the set of all noise intensities greater than the target noise intensity parameter as the second set.

7. The method for evaluating the remediation effect in environmental remediation engineering according to claim 1, characterized in that, The specific steps for obtaining the regularity of the first set based on the distance between the noise intensity and the pixels to be processed in the first set are as follows: In the formula, The regularity of the first set; The number of noise intensities in the first set. The number of combinations of any two noise intensities in the first set; For the The pixel point to be processed corresponding to one of the noise intensities in the combination is denoted as the first pixel point; For the The pixel point to be processed corresponding to the other noise intensity in the combination is denoted as the second pixel point; The Euclidean distance between the first pixel and the second pixel; The variance of the Euclidean distance between the pixels to be processed corresponding to all noise intensities in the first set; It is an exponential function with the natural constant as its base.

8. The method for evaluating the remediation effect in environmental remediation engineering according to claim 6, characterized in that, The specific steps for determining the optimality of each noise intensity parameter based on the regularity of the first set and the regularity of the second set are as follows: In the formula, The degree of optimization of the target noise intensity parameter; The regularity of the first set; The regularity of the second set; To take the absolute value.

9. The method for evaluating the remediation effect in environmental remediation engineering according to claim 1, characterized in that, The specific steps for obtaining several noise pixels and several impurity pixels in the groundwater grayscale image based on the regularity of the third set, the fourth set, and the first set are as follows: Obtain the regularity of the third set and the regularity of the fourth set. Among the regularities of the third set and the fourth set, the pixel to be processed corresponding to the noise intensity in the set with the smallest regularity is taken as the noise pixel; the pixel to be processed corresponding to the noise intensity in the set with the largest regularity is taken as the impurity pixel.

10. The method for evaluating the remediation effect in environmental remediation engineering according to claim 1, characterized in that, The specific steps involved in completing the groundwater remediation assessment based on impurity pixels and the denoised groundwater grayscale image are as follows: The difference in the number of impurity pixels between the denoised and restored groundwater grayscale images is obtained. The ratio of the difference to the total number of pixels is compared with an empirical threshold to complete the groundwater remediation assessment.

Images