Soil pollution detection method and system based on image data

Abstract

The application relates to the technical field of data processing, in particular to a soil pollution detection method and system based on image data. The method comprises the following steps: obtaining the pollution degree of different sampling points in a to-be-detected area; determining the main diffusion direction of pollutants of each sampling point and the overall diffusion direction of each sub-area based on the pollution degree difference between each sampling point and the surrounding sampling points; obtaining the weight coefficient of the sampling points in the neighborhood of the to-be-detected point to the to-be-detected point according to the position of the sampling points in the neighborhood of the to-be-detected point and the main diffusion direction of the pollutants of the sampling points; obtaining the pollution degree of the to-be-detected point according to the consistency of the overall diffusion direction of the sub-area where the to-be-detected point is located and the sub-area where the sampling points in the neighborhood of the to-be-detected point are located, the distance between the to-be-detected point and the sampling points in the neighborhood of the to-be-detected point and the pollution degree of the sampling points in the neighborhood of the to-be-detected point; and comprehensively evaluating the soil pollution degree of the to-be-detected area according to the pollution degrees of the sampling points and the to-be-detected point. The application improves the accuracy of the soil pollution degree detection result.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to a method and system for detecting soil pollution based on image data. Background Technology

[0002] During the extraction and smelting of mineral resources, mining areas generate a large amount of pollutants, such as heavy metals. These pollutants enter the soil through atmospheric deposition, wastewater discharge, and waste accumulation, causing soil pollution in mining areas. Soil pollution in mining areas not only damages the soil ecosystem and affects plant growth, but also enters the human body through the food chain, endangering human health. Therefore, accurate and efficient detection of soil pollution in mining areas is of great significance.

[0003] Mining areas are divided into different zones due to mining activities, such as mining sites, ore processing plants, mining roads, and slag heaps. The degree of soil pollution varies among these zones due to differences in location, ore content, and intended use. In mine ecological restoration, the remediation measures taken for areas with different levels of pollution directly affect the final restoration and remediation results. Because existing soil pollution detection methods based on spatial difference do not consider the diffusion characteristics of soil pollution, the accuracy of the obtained soil pollution levels is insufficient, resulting in limited reference value for mine ecological restoration and remediation. Summary of the Invention

[0004] To address the issue of low accuracy in obtaining results from existing methods for monitoring soil pollution levels, the present invention aims to provide a soil pollution detection method and system based on image data. The specific technical solution adopted is as follows:

[0005] In a first aspect, the present invention provides a method for detecting soil pollution based on image data, the method comprising the following steps:

[0006] Obtain the contamination level at different sampling points within the area to be tested;

[0007] Based on the difference in pollution levels between each sampling point and its surrounding sampling points, the main direction of pollutant diffusion at each sampling point and the overall diffusion direction of each sub-region are determined. Based on the relative positional relationship between the point to be tested and its neighboring sampling points and the main direction of pollutant diffusion at the sampling points, the weight coefficients of the sampling points in the neighboring sampling points of the point to be tested are obtained.

[0008] The confidence level of the test point is obtained based on the consistency of the overall diffusion direction between the sub-region where the test point is located and the sub-region where the sampling points in the neighborhood of the test point are located, and the relative distance between the test point and the sampling points in the neighborhood. The pollution level of the test point is obtained by combining the weight coefficient of the sampling points in the neighborhood of the test point, the pollution level of the sampling points in the neighborhood of the test point, and the confidence level.

[0009] The degree of soil pollution in the area to be tested is evaluated by combining the pollution levels of all sampling points and all test points.

[0010] Preferably, based on the difference in pollution levels between each sampling point and its surrounding sampling points, the main direction of pollutant diffusion at each sampling point is determined, including:

[0011] For any sampling point;

[0012] Calculate the pollution level difference between any sampling point and each sampling point in its neighborhood; use the ratio of the pollution level difference to the relative distance between any sampling point and each sampling point in its neighborhood as the pollutant diffusion factor of any sampling point in the direction from any sampling point to each sampling point in its neighborhood.

[0013] The direction corresponding to the largest pollutant diffusion factor at any sampling point is determined as the main pollutant diffusion direction at that sampling point.

[0014] Preferably, obtaining the overall diffusion direction of each sub-region includes:

[0015] For any subregion:

[0016] The frequency of each pollutant diffusion direction at all sampling points within any sub-region is statistically analyzed, and the diffusion direction of the pollutant with the highest frequency is determined as the overall diffusion direction of any sub-region.

[0017] Preferably, the step of obtaining the weighting coefficients of the sampling points in the neighborhood of the test point based on the relative positional relationship between the test point and its neighboring sampling points and the main direction of pollutant diffusion of the sampling points includes:

[0018] For any point to be measured:

[0019] The degree of soil pollution diffusion attenuation between any test point and each sampling point in its neighborhood is obtained based on the distance between any test point and each sampling point in its neighborhood, and the first cosine value of half the angle between the direction from each sampling point in the neighborhood of any test point to the test point and the main direction of pollutant diffusion of each sampling point in the neighborhood of any test point.

[0020] The normalized result of the soil pollution diffusion attenuation degree of any test point and each sampling point in its neighborhood is determined as the weight coefficient of each sampling point in the neighborhood of any test point to any test point.

[0021] Preferably, the step of obtaining the confidence level of the test point based on the consistency of the overall diffusion direction between the sub-region where the test point is located and the sub-regions where the sampling points in its neighborhood are located, and the relative distance between the test point and its neighborhood sampling points, includes:

[0022] For any point to be measured:

[0023] The confidence level of any test point is obtained based on the second cosine value of the angle between the sub-region where the test point is located and the overall diffusion direction of the sub-region where the sampling points in the neighborhood of the test point are located, and the Euclidean distance between the center point of the sub-region where the test point is located and the center point of the sub-region where the sampling points in the neighborhood of the test point are located. The second cosine value is positively correlated with the confidence level, and the Euclidean distance is negatively correlated with the confidence level.

[0024] Preferably, the step of obtaining the confidence level of any test point based on the second cosine value of the angle between the sub-region where the test point is located and the sub-region where the sampling points in the neighborhood of the test point are located, and the Euclidean distance between the center point of the sub-region where the test point is located and the center point of the sub-region where the sampling points in the neighborhood of the test point are located, includes:

[0025] The cosine value between the overall diffusion direction of the sub-region where any test point is located and the sub-region where each neighboring sampling point is located is recorded as the second cosine value corresponding to each neighboring sampling point.

[0026] Calculate the sum of the Euclidean distance between the center point of the sub-region where any test point is located and the center point of the sub-region where each neighboring sampling point is located, and the preset first adjustment parameter, and record it as the first sum value corresponding to each neighboring sampling point;

[0027] The ratio between the second cosine value corresponding to each neighborhood sampling point and the corresponding first sum value is denoted as the first ratio of each neighborhood sampling point; the neighborhood sampling point is the sampling point within the neighborhood of any point to be measured;

[0028] The average of the first ratios of all neighboring sampling points of any given test point is taken as the confidence level of any given test point.

[0029] Preferably, the step of combining the weight coefficients of the sampling points in the neighborhood of the test point, the contamination degree of the sampling points in the neighborhood of the test point, and the confidence level to obtain the contamination degree of the test point includes:

[0030] For any point to be measured:

[0031] Using the weight coefficients of the sampling points in the neighborhood of any test point, the pollution levels of the sampling points in the neighborhood of any test point are weighted and summed to obtain a first weighted result;

[0032] The contamination level of any test point is obtained based on the first weighted result and the confidence level of any test point.

[0033] Preferably, obtaining the contamination level of any test point based on the first weighted result and the confidence level of any test point includes:

[0034] The normalized result of the product of the first weighted result and the confidence level of any test point is taken as the contamination level of any test point.

[0035] Preferably, the evaluation of the soil pollution level in the area to be tested, by comprehensively considering the pollution levels of all sampling points and all test points, includes:

[0036] The average pollution level of the soil in the area to be tested is determined by the average pollution level of all sampling points and all test points in the area to be tested.

[0037] Secondly, the present invention provides a soil pollution detection system based on image data, which is used to implement the above-mentioned method. The system includes:

[0038] Obtain the contamination level at different sampling points within the area to be tested;

[0039] Based on the difference in pollution levels between each sampling point and its surrounding sampling points, the main direction of pollutant diffusion at each sampling point and the overall diffusion direction of each sub-region are determined. Based on the relative positional relationship between the point to be tested and its neighboring sampling points and the main direction of pollutant diffusion at the sampling points, the weight coefficients of the sampling points in the neighboring sampling points of the point to be tested are obtained.

[0040] The confidence level of the test point is obtained based on the consistency of the overall diffusion direction between the sub-region where the test point is located and the sub-region where the sampling points in the neighborhood of the test point are located, and the relative distance between the test point and the sampling points in the neighborhood. The pollution level of the test point is obtained by combining the weight coefficient of the sampling points in the neighborhood of the test point, the pollution level of the sampling points in the neighborhood of the test point, and the confidence level.

[0041] The degree of soil pollution in the area to be tested is evaluated by combining the pollution levels of all sampling points and all test points.

[0042] The present invention has at least the following beneficial effects:

[0043] This invention first sets up sampling points within the area to be tested and collects the soil pollution level at each sampling point. The differences in pollution levels between sampling points within a sub-region and their surrounding sampling points are analyzed to quantify the soil pollution diffusion characteristics of different sub-regions, determining the main diffusion direction of pollutants at each sampling point and the overall diffusion direction of each sub-region. Then, based on the relative positional relationship between the test point and its neighboring sampling points and the main diffusion direction of pollutants at the sampling point, the influence of neighboring sampling points on the soil pollution level of the test point is evaluated. Higher weighting coefficients are assigned to points with greater influence, and lower weighting coefficients are assigned to points with less influence. Finally, the overall diffusion direction of the sub-region where the test point is located is considered in conjunction with the overall diffusion direction of the sub-regions where neighboring sampling points are located. The soil pollution level of the test point is determined by considering the consistency of the direction, the relative distance between the test point and its neighboring sampling points, and the pollution level of the neighboring sampling points. Then, the soil pollution level of the monitored area is evaluated by comprehensively considering the pollution levels of all sampling points and all test points within the monitored area. The method provided by this invention eliminates the need to test the soil pollution level at each test point, achieving rapid detection of soil pollution while improving the accuracy of soil pollution level detection. This provides a basis for implementing differentiated treatment measures for areas with different pollution levels in mine ecological restoration, avoiding adverse consequences such as poor treatment effects due to inappropriate treatment measures, and enhancing the targeting and efficiency of subsequent mine ecological restoration. Attached Figure Description

[0044] To more clearly illustrate the technical solutions and advantages 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.

[0045] Figure 1 A flowchart of the soil pollution detection method based on image data provided in an embodiment of the present invention;

[0046] Figure 2 This is a structural block diagram of a soil pollution detection system based on image data provided in an embodiment of the present invention. Detailed Implementation

[0047] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description of the soil pollution detection method and system based on image data proposed in accordance with the present invention is provided in conjunction with the accompanying drawings and preferred embodiments.

[0048] 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.

[0049] The specific solution of the image data-based soil pollution detection method and system provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0050] Example of a soil pollution detection method based on image data:

[0051] This embodiment addresses a specific scenario where mining activities create different areas such as mining sites, concentrators, mining roads, and slag heaps. Due to variations in location, ore content, and intended use, the degree of soil pollution differs in each area. In mine ecological restoration, the remediation measures taken for soils with varying degrees of pollution directly impact the final restoration outcome. Because these different areas exhibit significant differences in the degree, extent, material composition, and diffusion characteristics of soil pollution, their diffusion processes differ. Existing soil pollution detection methods based on spatial difference do not consider these diffusion characteristics, resulting in insufficient accuracy. Therefore, this embodiment quantifies the diffusion characteristics of regional soil pollution, comprehensively considering these characteristics to achieve rapid detection and improve the accuracy of the detection results.

[0052] This embodiment proposes a soil pollution detection method based on image data, such as Figure 1 As shown, the soil pollution detection method based on image data in this embodiment includes the following steps:

[0053] Step S1: Obtain the contamination level of different sampling points within the area to be tested.

[0054] Multiple sampling points are evenly distributed throughout the area to be tested. A concentration sensor is pre-embedded at each sampling point. The concentration sensors are used to detect the heavy metal concentration in the soil at each sampling point. The detected heavy metal concentration is used as the pollution level at each sampling point. The number of sampling points in the area to be tested is determined by the size of the area. In this embodiment, 25 sampling points are set per square kilometer. In specific applications, the implementer can adjust the number of sampling points according to specific circumstances. It should be noted that the pollution levels used in subsequent steps in this embodiment are dimensionless.

[0055] Thus, this embodiment has collected the contamination level of each sampling point in the area to be tested.

[0056] Step S2: Based on the difference in pollution levels between each sampling point and its surrounding sampling points, determine the main direction of pollutant diffusion at each sampling point and the overall diffusion direction of each sub-region; based on the relative positional relationship between the sampling point to be tested and its neighboring sampling points and the main direction of pollutant diffusion at the sampling point, obtain the weight coefficients of the sampling points in the neighboring sampling points of the sampling point to be tested.

[0057] During the mining process, mining activities create different areas such as mining sites, ore processing plants, mining roads, and slag heaps. Due to differences in location, ore content, and usage, the degree of soil pollution in the vicinity of each area varies, resulting in different characteristics of soil pollution diffusion in each area.

[0058] This embodiment addresses the different characteristics of soil pollution diffusion in different regions by quantifying the diffusion characteristics of soil pollution in the region (including regional relationships, diffusion direction, diffusion distance, etc.). Based on the quantified soil pollution diffusion characteristics, the soil pollution diffusion characteristics are determined, and the soil pollution degree of unknown points is obtained by combining the pollution degree of sampling points around unknown pollution points, thereby obtaining the soil pollution degree of the entire mining area.

[0059] Soil pollution spreads from high concentration to low concentration. Due to the complex topography and soil properties of the mining area, the diffusion rate varies in different directions. In this embodiment, the diffusion of pollutants in each direction is determined based on the pollution level of the sampling point and the pollution levels of multiple nearby sampling points, thereby obtaining the overall diffusion direction of each sub-region within the area to be tested.

[0060] This embodiment will now use a single sampling point as an example for explanation. The method provided in this embodiment can be used to process other sampling points as well.

[0061] Specifically, for any given sampling point;

[0062] The pollution level difference between the sampling point and each sampling point in its neighborhood is calculated. It should be noted that the pollution level difference is obtained by subtracting the pollution level of each sampling point in its neighborhood from the pollution level of the sampling point itself. The ratio of the pollution level difference to the relative distance between the sampling point and the corresponding sampling point in its neighborhood is taken as the pollutant diffusion factor of the sampling point in the direction from the sampling point to the corresponding sampling point in its neighborhood. There is a pollutant diffusion factor for each sampling point in the direction from the sampling point to each sampling point in its neighborhood. The direction corresponding to the maximum value of the pollutant diffusion factor in the direction from the sampling point to all sampling points in its neighborhood is determined as the main pollutant diffusion direction of the sampling point. For any sampling point, its neighborhood is a circular area centered on the sampling point with a preset length as its radius. In this embodiment, the preset length is 500 meters. In specific applications, the implementer can set the preset length according to the distribution of sampling points.

[0063] Due to differences in location, ore content, and usage within different areas of the mining area, the degree of soil pollution varies, resulting in different characteristics of soil pollution diffusion. For example, areas surrounding open-pit mines, ore dressing plants, and tailings ponds experience greater pollution due to dust settling and chemical leaks, while areas near transportation roads are relatively less polluted. The degree of diffusion is influenced by various factors, such as diffusion direction, diffusion rate, and regional characteristics. Traditional methods for calculating diffusion levels rely on spatial interpolation algorithms to directly obtain the pollution level of unknown areas, but they do not consider these diffusion characteristics, leading to insufficient accuracy in pollution level calculations. Therefore, this embodiment comprehensively considers multiple diffusion characteristics to determine the degree of soil pollution diffusion attenuation. By calculating the weight of the soil pollution diffusion attenuation degree at each sampling point, a more accurate degree of soil pollution in the mining area can be obtained.

[0064] First, the area to be detected is divided into multiple sub-regions of equal size. Each sub-region contains multiple sampling points. The number of sub-regions and the size of each sub-region are set by the implementer according to the specific situation, which will not be elaborated on here.

[0065] Next, this embodiment will be described using a sub-region as an example. The method provided in this embodiment can be used to process other sub-regions.

[0066] Specifically, for any sub-region: the frequency of occurrence of the main diffusion direction of each pollutant at all sampling points within the sub-region is calculated, and the main diffusion direction of the pollutant with the highest frequency is determined as the overall diffusion direction of the sub-region. It should be noted that if there is more than one main diffusion direction with the highest frequency, the average of all the main diffusion directions with the highest frequency is taken as the overall diffusion direction of the sub-region. Using this method, the overall diffusion direction of each sub-region can be obtained.

[0067] Multiple test points are randomly selected within the area to be tested. Test points are points other than sampling points, and the number of test points selected is much greater than the number of sampling points. In this embodiment, the number of test points is 10 times the number of sampling points. In other implementations, the number of test points is set according to the specific situation, which will not be elaborated here.

[0068] As the distance from pollutants increases, the degree of pollution gradually decreases, showing a negative correlation between pollution level and distance. The diffusion direction of the sampling point also affects the degree of soil pollution diffusion attenuation; the more consistent the diffusion direction of the sampling point is with the direction of the test point, the smaller the diffusion attenuation.

[0069] The following embodiment uses any test point as an example for explanation. The method provided in this embodiment can be used to process other test points.

[0070] Specifically, for any point to be measured:

[0071] The cosine of half the angle between the direction from each sampling point in the neighborhood of the test point to the test point and the main direction of pollutant diffusion from the same sampling point in the neighborhood of the test point is recorded as the first cosine value corresponding to each sampling point in the neighborhood of the test point. Then, based on the distance between the test point and each sampling point in its neighborhood, and the first cosine value corresponding to each sampling point in the neighborhood of the test point, the degree of soil pollution diffusion attenuation between the test point and each sampling point in its neighborhood is obtained.

[0072] In this embodiment, a specific formula for calculating the diffusion attenuation degree is given. The soil pollution diffusion attenuation degree between the j-th test point and the u-th sampling point in its neighborhood can be expressed as:

[0073] ;

[0074] in, This represents the degree of soil pollution diffusion attenuation between the j-th test point and the u-th sampling point in their neighborhood. This represents the Euclidean distance between the j-th test point and the u-th sampling point in its neighborhood. This represents the angle between the direction from the u-th sampling point in the neighborhood of the j-th sampling point to the j-th sampling point and the main direction of pollutant diffusion from the u-th sampling point in the neighborhood of the j-th sampling point. This represents the function for finding the cosine value. Let represent the first cosine value corresponding to the u-th sampling point within the neighborhood of the j-th test point.

[0075] The greater the distance between the j-th test point and the u-th sampling point in its neighborhood, the greater the attenuation of soil pollution. The first cosine value reflects the influence of different diffusion directions of sampling points near the test point on diffusion attenuation; the larger the value, the more consistent the directions, and the smaller the diffusion attenuation, i.e., the smaller the diffusion attenuation of soil pollution between the j-th test point and the u-th sampling point in its neighborhood. It should be noted that the method for obtaining the neighborhood of the test point and the neighborhood of the sampling point is the same in this embodiment; therefore, the specific process of obtaining the neighborhood of the test point will not be described in detail.

[0076] Using the above method, the degree of soil pollution diffusion attenuation at the test point and each sampling point in its neighborhood can be obtained. The smaller the degree of soil pollution diffusion attenuation, the greater the influence of the soil pollution level at the sampling point on the soil pollution level at the test point. This indicates that the soil pollution situation in the local area of ​​the mining area where the sampling point is located is more consistent, and therefore the more important the sampling point is, and thus its weight coefficient is larger.

[0077] Therefore, the normalized result of the soil pollution diffusion attenuation degree of the test point and each sampling point in its neighborhood is determined as the weight coefficient of each sampling point in the neighborhood of the test point to the test point. In this embodiment, the maximum-minimum value normalization method is used to normalize the soil pollution diffusion attenuation degree. As other implementation methods, other existing normalization methods can also be used for normalization, which will not be elaborated on here.

[0078] Thus, by using the above method, the weight coefficient of each sampling point in the neighborhood of the point to be tested within the detection area has been obtained.

[0079] Step S3: Based on the consistency of the overall diffusion direction between the sub-region where the test point is located and the sub-region where the sampling points in the neighborhood of the test point are located, and the relative distance between the test point and the sampling points in its neighborhood, the confidence level of the test point is obtained; combined with the weight coefficient of the sampling points in the neighborhood of the test point, the pollution level of the sampling points in the neighborhood of the test point, and the confidence level, the pollution level of the test point is obtained.

[0080] Since the contamination level of the sampling point is known and it may exist in multiple segmented regions, while the contamination level of the test point is unknown, there are three relationships between the sub-region where the test point is located and the sub-region where the sampling point is located: the same sub-region, different sub-regions, or across sub-regions. This regional relationship is used as the confidence level, that is, the confidence level is higher if the sub-region is the same and lower if the sub-region is different. Combined with the obtained overall diffusion direction of the region, the more the overall diffusion direction of the sub-region points to the same direction, the higher the confidence level.

[0081] For any point to be measured:

[0082] Calculate the cosine of the angle between the overall diffusion direction of the sub-region where the test point is located and the overall diffusion direction of the sub-region where each sampling point in the neighborhood of the test point is located. Record this cosine value as the second cosine value corresponding to each sampling point in the neighborhood of the test point. Based on the second cosine value corresponding to each sampling point in the neighborhood of the test point and the Euclidean distance between the center point of the sub-region where the test point is located and the center point of the sub-region where the sampling point in the neighborhood of the test point is located, obtain the confidence level of the test point. The second cosine value is positively correlated with the confidence level, and the Euclidean distance is negatively correlated with the confidence level.

[0083] Among them, a positive correlation means that the dependent variable increases as the independent variable increases, and the dependent variable decreases as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by practical application. A negative correlation means that the dependent variable decreases as the independent variable increases, and the dependent variable increases as the independent variable decreases. It can be a subtractive relationship, a division relationship, etc., which is determined by practical application.

[0084] As a specific example, the second cosine value between the overall diffusion direction of the sub-region where any test point is located and the sub-region where each neighboring sampling point is located is denoted as the second cosine value corresponding to each neighboring sampling point. The sum of the Euclidean distance between the center point of the sub-region where the test point is located and the center point of the sub-region where each neighboring sampling point is located, and a preset first adjustment parameter, is calculated and denoted as the first sum value corresponding to each neighboring sampling point. The ratio between the second cosine value corresponding to each neighboring sampling point and the corresponding first sum value is denoted as the first ratio value for each neighboring sampling point. The average of the first ratio values ​​of all neighboring sampling points of the test point is taken as the confidence level of the test point. Here, a neighboring sampling point is a sampling point within the neighborhood of the test point; the average of the first ratio values ​​of all neighboring sampling points of the test point is taken as the confidence level of the test point.

[0085] In this embodiment, a specific formula for calculating the confidence level is given. The confidence level of the t-th test point can be expressed as:

[0086] ;

[0087] in, Let be the confidence level of the t-th test point. This represents the number of sampling points in the neighborhood of the t-th test point. Let represent the Euclidean distance between the center point of the sub-region where the t-th test point is located and the center point of the sub-region where the a-th sampling point is located in the neighborhood. This represents the overall diffusion direction of the sub-region where the a-th sampling point is located within the neighborhood of the t-th test point. This indicates the overall diffusion direction of the sub-region where the t-th test point is located. Indicates the absolute value sign. This represents the function for finding the cosine value. express and The angle between them Represents the normalization function. This indicates the preset first adjustment parameter.

[0088] In this embodiment, a preset first adjustment parameter is introduced into the confidence calculation formula to prevent the denominator from being 0. In this embodiment, the preset first adjustment parameter is 0.01. In specific applications, the implementer can set it according to the specific situation.

[0089] It represents the cosine value between the overall diffusion direction of the sub-region where the t-th test point is located and the sub-region where the a-th sampling point is located in the neighborhood of the t-th test point, that is, the cosine value of the angle between these two directions, which is the second cosine value corresponding to the a-th sampling point in the neighborhood of the t-th test point. Indicates the first sum value. This represents the first ratio of the sampling points in the a-th neighborhood of the t-th test point.

[0090] The greater the distance between the sub-region where the t-th test point is located and the sub-region where the a-th sampling point is located in the neighboring sub-region, the smaller the influence of the sub-region where the a-th sampling point is located in the neighboring sub-region on the soil pollution level of the sub-region where the t-th test point is located, and the lower the confidence level. The more consistent the overall diffusion direction between the sub-region where the a-th sampling point is located and the sub-region where the t-th test point is located, the greater the likelihood that their sub-regions are affected by the same pollution source, and therefore the better the consistency of their diffusion trends, and the higher the confidence level.

[0091] For any test point: using the weight coefficients of the test point's neighboring sampling points, the pollution levels of the neighboring sampling points are weighted and summed to obtain the first weighted result; the normalized result of the product of the first weighted result and the confidence level of the test point is taken as the pollution level of the test point.

[0092] In this embodiment, a specific formula for calculating the contamination level of the test point is given. The contamination level of the t-th test point can be expressed as:

[0093] ;

[0094] in, This represents the pollution level at the t-th test point. This represents the confidence level of the t-th test point. This represents the number of sampling points in the neighborhood of the t-th test point. This represents the weight coefficient of the a-th sampling point within the neighborhood of the t-th test point. This represents the contamination level of the a-th sampling point within the neighborhood of the t-th sampling point.

[0095] This represents the first weighted result, which is obtained by weighting the pollution levels of sampling points near the t-th test point and combining them with the corresponding confidence levels. The larger the pollution level value of the t-th test point, the greater the degree of soil pollution at that location.

[0096] Using the above method, the degree of contamination at each test point can be obtained.

[0097] Step S4: Evaluate the degree of soil pollution in the area to be tested by combining the pollution levels of all sampling points and all test points.

[0098] In this embodiment, the pollution level of each test point was obtained in the above steps. Next, the pollution levels of all sampling points and all test points in the test area will be combined to evaluate the soil pollution level of the test area.

[0099] As a specific example, the average pollution level of all sampling points and all test points in the area to be tested can be used to determine the soil pollution level of the area to be tested; alternatively, the mode of the pollution levels of all sampling points and all test points in the area to be tested can be used to determine the soil pollution level of the area to be tested; furthermore, based on the location information of the sampling points and test points in the area to be tested, the pollution level data of all sampling points and all test points in the area to be tested can be mapped onto an image, and professionals can evaluate the soil pollution situation of the area to be tested based on these mapped data and their experience; other methods can also be used to evaluate the soil pollution level of the area to be tested.

[0100] Thus, the method provided in this embodiment has been used to evaluate the degree of soil pollution in the area to be tested, which will facilitate the formulation of appropriate ecological restoration measures based on the different degrees of soil pollution in the mining area.

[0101] This embodiment first sets up sampling points within the area to be tested and collects the soil pollution level at each sampling point. The differences in pollution levels between sampling points within a sub-region and their surrounding sampling points are analyzed to quantify the soil pollution diffusion characteristics of different sub-regions, determining the main diffusion direction of pollutants at each sampling point and the overall diffusion direction of each sub-region. Then, based on the relative position of the test point and its neighboring sampling points and the main diffusion direction of pollutants at the sampling points, the influence of neighboring sampling points on the soil pollution level of the test point is evaluated. Higher weighting coefficients are assigned to points with greater influence, and lower weighting coefficients are assigned to points with less influence. Finally, the overall diffusion direction of the sub-region where the test point is located is considered in conjunction with the overall diffusion direction of the sub-regions where neighboring sampling points are located. The soil pollution level of the test point is determined by considering the consistency of the direction, the relative distance between the test point and its neighboring sampling points, and the pollution level of the neighboring sampling points. Then, the soil pollution level of the monitored area is evaluated by comprehensively considering the pollution levels of all sampling points and all test points within the monitored area. The method provided in this embodiment does not require testing the soil pollution level at each test point location to obtain the soil pollution level, achieving rapid detection of soil pollution while improving the accuracy of soil pollution level detection. This provides a basis for implementing differentiated treatment measures for areas with different pollution levels in mine ecological restoration, avoiding adverse consequences such as poor treatment effects due to inappropriate treatment measures, and improving the targeting and efficiency of subsequent mine ecological restoration.

[0102] Example of an image-based soil pollution detection system:

[0103] See Figure 2The diagram illustrates a structural block diagram of a soil pollution detection system based on image data provided in an embodiment of the present invention. The system may include a data acquisition module, a weight determination module, a first evaluation module, and a comprehensive evaluation module.

[0104] The data acquisition module is used to acquire the contamination level of different sampling points within the area to be detected.

[0105] The weight determination module is used to determine the main direction of pollutant diffusion at each sampling point and the overall diffusion direction of each sub-region based on the difference in pollution levels between each sampling point and its surrounding sampling points. Based on the relative positional relationship between the sampling point to be tested and its neighboring sampling points and the main direction of pollutant diffusion at the sampling point, the weight coefficients of the sampling points in the neighboring sampling points of the sampling point to be tested are obtained.

[0106] The first evaluation module is used to obtain the confidence level of the test point based on the consistency of the overall diffusion direction between the sub-region where the test point is located and the sub-region where the sampling points in the neighborhood of the test point are located, and the relative distance between the test point and the sampling points in the neighborhood; and to obtain the pollution level of the test point by combining the weight coefficient of the sampling points in the neighborhood of the test point, the pollution level of the sampling points in the neighborhood of the test point, and the confidence level.

[0107] The comprehensive evaluation module is used to evaluate the degree of soil pollution in the area to be tested by integrating the pollution levels of all sampling points and all test points.

[0108] It should be understood that Figure 2 The structural block diagram and modules of the image-based soil pollution detection system shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by 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 an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-described methods and systems can be implemented using computer-executable instructions and / or included in processor control code, for example, 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 systems and modules of this specification can be implemented not only by hardware circuits 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., but also by software executed by various types of processors, or by a combination of the above-described hardware circuits and software (e.g., firmware).

[0109] For more details about the above modules, please refer to other parts of this manual; they will not be repeated here.

[0110] In other embodiments, a soil pollution detection device based on image data is also provided, including a memory and a processor. The memory stores executable program code, and the processor calls and runs the executable program code from the memory, causing the device to perform the aforementioned image data-based soil pollution detection method. Specifically, the device may be a chip, component, or module. The chip may include a connected processor and memory; wherein the memory stores instructions, and when the processor calls and executes the instructions, the chip can perform the image data-based soil pollution detection method provided in the above embodiments.

[0111] In other embodiments, a computer program product is also provided, which, when run on a computer, causes the computer to perform the aforementioned related steps to implement the image data-based soil pollution detection method provided in the above embodiments.

[0112] In other embodiments, a computer-readable storage medium is also provided, which stores computer program code. When the computer program code is run on a computer, it causes the computer to perform the above-described related method steps to implement the soil pollution detection method based on image data provided in the above embodiments.

[0113] The systems, electronic devices, computer program products, and computer-readable storage media provided are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0114] It should be noted that 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 detecting soil pollution, characterized in that, The method includes the following steps: The contamination level of different sampling points in the area to be detected is obtained. The area to be detected is divided into multiple sub-regions of equal size, and each sub-region contains multiple sampling points. Based on the differences in pollution levels between each sampling point and its surrounding sampling points, the main direction of pollutant diffusion at each sampling point and the overall diffusion direction of each sub-region are determined. Based on the relative positional relationship between the sampling point to be tested and its neighboring sampling points, and the main direction of pollutant diffusion at the sampling point, the weighting coefficients of the sampling points within the neighboring sampling points of the sampling point to be tested are obtained, including: For any point to be measured: The soil pollution diffusion attenuation degree between any test point and each sampling point in its neighborhood is obtained based on the distance between the test point and each sampling point in its neighborhood, and the first cosine value of half the angle between the direction from each sampling point in the neighborhood of the test point to the test point and the main direction of pollutant diffusion from each sampling point in the neighborhood of the test point. The soil pollution diffusion attenuation degree between the j-th test point and the u-th sampling point in its neighborhood is expressed as... : ； in, This represents the Euclidean distance between the j-th test point and the u-th sampling point in its neighborhood. This represents the angle between the direction from the u-th sampling point in the neighborhood of the j-th sampling point to the j-th sampling point and the main direction of pollutant diffusion from the u-th sampling point in the neighborhood of the j-th sampling point. This represents the function for finding the cosine value. This represents the first cosine value corresponding to the u-th sampling point within the neighborhood of the j-th test point; The normalized result of the soil pollution diffusion attenuation degree of any test point and each sampling point in its neighborhood is determined as the weight coefficient of each sampling point in the neighborhood of any test point to any test point. The confidence level of a test point is obtained based on the consistency of the overall diffusion direction between the sub-region where the test point is located and the sub-regions where neighboring sampling points are located, and the relative distance between the test point and its neighboring sampling points. This includes: for any test point, the confidence level is obtained based on the second cosine of the angle between the overall diffusion direction of the sub-region where the test point is located and the sub-regions where neighboring sampling points are located, and the Euclidean distance between the center point of the sub-region where the test point is located and the center point of the sub-region where neighboring sampling points are located. The second cosine value is positively correlated with the confidence level, and the Euclidean distance between the center point of the sub-region where the test point is located and the center point of the sub-region where neighboring sampling points are located is negatively correlated with the confidence level. The contamination level of the test point is obtained by combining the weight coefficients of the sampling points in the neighborhood of the test point, the contamination level of the sampling points in the neighborhood of the test point, and the confidence level. The degree of soil pollution in the area to be tested is evaluated by combining the pollution levels of all sampling points and all test points.

2. The soil pollution detection method according to claim 1, characterized in that, Based on the differences in contamination levels between each sampling point and its surrounding sampling points, the main direction of pollutant diffusion at each sampling point was determined, including: For any sampling point; Calculate the pollution level difference between any sampling point and each sampling point in its neighborhood; use the ratio of the pollution level difference to the relative distance between any sampling point and each sampling point in its neighborhood as the pollutant diffusion factor of any sampling point in the direction from any sampling point to each sampling point in its neighborhood. The direction corresponding to the largest pollutant diffusion factor at any sampling point is determined as the main pollutant diffusion direction at that sampling point.

3. The soil pollution detection method according to claim 1, characterized in that, Obtaining the overall diffusion direction of each sub-region includes: For any subregion: The frequency of each pollutant diffusion direction at all sampling points within any sub-region is statistically analyzed, and the diffusion direction of the pollutant with the highest frequency is determined as the overall diffusion direction of any sub-region.

4. The soil pollution detection method according to claim 1, characterized in that, The confidence level of any test point is obtained based on the second cosine of the angle between the sub-region where the test point is located and the sub-region where the neighboring sampling points are located, and the Euclidean distance between the center point of the sub-region where the test point is located and the center point of the sub-region where the neighboring sampling points are located. This includes: The cosine value between the overall diffusion direction of the sub-region where any test point is located and the sub-region where each neighboring sampling point is located is recorded as the second cosine value corresponding to each neighboring sampling point. Calculate the sum of the Euclidean distance between the center point of the sub-region where any test point is located and the center point of the sub-region where each neighboring sampling point is located, and the preset first adjustment parameter, and record it as the first sum value corresponding to each neighboring sampling point; The ratio between the second cosine value corresponding to each neighborhood sampling point and the corresponding first sum value is denoted as the first ratio of each neighborhood sampling point; the neighborhood sampling point is the sampling point within the neighborhood of any point to be measured; The average of the first ratios of all neighboring sampling points of any given test point is taken as the confidence level of any given test point.

5. The soil pollution detection method according to claim 1, characterized in that, The process of combining the weight coefficients of the sampling points in the neighborhood of the test point, the contamination level of the sampling points in the neighborhood of the test point, and the confidence level to obtain the contamination level of the test point includes: For any point to be measured: Using the weight coefficients of the sampling points in the neighborhood of any test point, the pollution levels of the sampling points in the neighborhood of any test point are weighted and summed to obtain a first weighted result; The contamination level of any test point is obtained based on the first weighted result and the confidence level of any test point.

6. The soil pollution detection method according to claim 5, characterized in that, The step of obtaining the contamination level of any test point based on the first weighted result and the confidence level of any test point includes: The normalized result of the product of the first weighted result and the confidence level of any test point is taken as the contamination level of any test point.

7. The soil pollution detection method according to claim 1, characterized in that, The evaluation of soil pollution levels in the area to be tested is based on the combined pollution levels of all sampling points and all test points, including: The average pollution level of the soil in the area to be tested is determined by the average pollution level of all sampling points and all test points in the area to be tested.

8. A soil pollution detection system, said system being used to implement the method of claim 1, characterized in that, The system includes: The data acquisition module is used to acquire the contamination level at different sampling points within the area to be tested; The weight determination module is used to determine the main direction of pollutant diffusion at each sampling point and the overall diffusion direction of each sub-region based on the difference in pollution levels between each sampling point and its surrounding sampling points. Based on the relative positional relationship between the sampling point to be tested and its neighboring sampling points and the main direction of pollutant diffusion at the sampling point, the weight coefficients of the sampling points in the neighboring sampling points of the sampling point to be tested are obtained. The first evaluation module is used to obtain the confidence level of the test point based on the consistency of the overall diffusion direction between the sub-region where the test point is located and the sub-region where the sampling points in the neighborhood of the test point are located, and the relative distance between the test point and the sampling points in the neighborhood; and to obtain the pollution level of the test point by combining the weight coefficient of the sampling points in the neighborhood of the test point, the pollution level of the sampling points in the neighborhood of the test point, and the confidence level. The comprehensive evaluation module is used to evaluate the degree of soil pollution in the area to be tested by integrating the pollution levels of all sampling points and all test points.

Images