Mine ecological restoration effect evaluation system and method

Abstract

The invention belongs to the technical field of image processing, and particularly relates to a mine ecological restoration effect evaluation system and method. The system comprises a multi-source remote sensing data fusion part, a data processing and analysis part and an ecological restoration effect evaluation part, the multi-source remote sensing data fusion part is used for acquiring multi-source remote sensing image data including a plurality of source images in a target mine area; the data processing and analyzing part is used for performing multi-scale fractal analysis on the fused remote sensing image data to obtain fractal dimensions related to the scale of the target mine area; and the ecological restoration effect evaluation part is used for obtaining the ecological restoration degree of the mine according to the relationship between the multispectral adaptive vegetation index in the historical data and the ecological restoration of the mine. According to the method, the accuracy and comprehensiveness of mine ecological restoration effect evaluation are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a system and method for evaluating the effectiveness of mine ecological restoration. Background Art

[0002] Mine ecological restoration refers to the restoration of the ecosystem destroyed by mining through engineering, biological, chemical and management measures to restore it to a certain stable, healthy and sustainable state. With the exploitation of mineral resources, the ecological environment in the mining area has been severely damaged, vegetation has been destroyed, soil erosion, land degradation, ecosystem imbalance, and environmental pollution have intensified. Therefore, how to effectively carry out mine ecological restoration has become an important topic of concern to governments and academia.

[0003] The evaluation of the effectiveness of mine ecological restoration is an important part of mine environmental management. With the increase of mining activities, the ecological system in the mining area has been severely damaged, and problems such as vegetation reduction, soil erosion, and soil and water loss have become increasingly prominent. In order to effectively restore the ecological environment of the mine, it is essential to implement scientific and reasonable ecological restoration measures. In order to evaluate the effectiveness of these measures, it is necessary to rely on an accurate ecological restoration effectiveness evaluation system.

[0004] At present, remote sensing technology has been widely used in ecological environment monitoring. By acquiring remote sensing images of different bands, the changes of ecological elements such as surface vegetation, soil and water bodies can be analyzed and evaluated. The advantage of remote sensing technology is that it can provide large-scale and continuous spatial information, which is suitable for ecological monitoring of large areas such as mines. However, there are still some problems in the evaluation of the effectiveness of mine ecological restoration using existing remote sensing monitoring technology. First, traditional vegetation indices such as the normalized difference vegetation index (NDVI) and the enhanced vegetation index (EVI) have limitations in some cases. NDVI is calculated by the reflectivity of the near-infrared and red light bands. Although it can reflect the vegetation coverage and health status, it performs poorly under high and low vegetation coverage and is easily affected by soil background, lighting conditions and atmospheric conditions. EVI has improved the limitations of NDVI to a certain extent, but it still cannot provide sufficiently accurate evaluation results in the case of complex mine ecological environment. Secondly, the existing remote sensing data processing methods are insufficient in information extraction and comprehensive analysis. Traditional single-band or multi-band analysis methods cannot fully utilize the multispectral information of remote sensing data and tend to ignore the correlation and complementarity between bands. In addition, simple linear combination and weighted processing cannot accurately reflect the complex ecological characteristics of the surface, resulting in insufficient accuracy and reliability of the evaluation results. Summary of the invention

[0005] In view of this, the main purpose of the present invention is to provide a system and method for evaluating the effectiveness of mine ecological restoration, which significantly improves the accuracy and comprehensiveness of the evaluation of the effectiveness of mine ecological restoration. The system has achieved all-round improvement in data acquisition, processing and analysis, and effect evaluation, providing strong technical support for scientific decision-making and optimal resource allocation.

[0006] The technical solution adopted by the present invention is as follows:

[0007] A mine ecological restoration effectiveness evaluation system, the system comprising: a multi-source remote sensing data fusion part, a data processing and analysis part and an ecological restoration effect evaluation part; the multi-source remote sensing data fusion part is used to obtain multi-source remote sensing image data containing multiple source images of a target mine area, perform spatial detail enhancement and frequency domain fusion based on wavelet transform, and obtain fused remote sensing image data; the data processing and analysis part is used to perform multi-scale fractal analysis on the fused remote sensing image data, obtain the scale-related fractal dimension of the target mine area, and then based on the reflectivity of each band in the fused remote sensing image data , calculate the preliminary multispectral adaptive vegetation index; adjust the preliminary multispectral adaptive vegetation index according to the fractal dimension to obtain the adjusted multispectral adaptive vegetation index; the ecological restoration effect evaluation part is used to establish the multispectral adaptive vegetation index standard interval for mine ecological restoration according to the relationship between the multispectral adaptive vegetation index and mine ecological restoration in historical data, each multispectral adaptive vegetation index standard interval corresponds to a degree of mine ecological restoration, and the degree of ecological restoration of the mine is obtained according to the multispectral adaptive vegetation index standard interval in which the adjusted multispectral adaptive vegetation index is located.

[0008] Furthermore, the multi-source remote sensing data fusion part includes: a data acquisition unit, which is used to acquire multi-source remote sensing image data including high-resolution panchromatic images and multispectral images when acquiring multi-source remote sensing image data of a target mining area containing multiple source images; a data processing unit, which is used to perform nonlinear enhancement on the high-frequency sub-bands of the high-resolution panchromatic image, perform PCA transformation on the multispectral image, and then perform non-subsampled contourlet transformation on the first principal component of the high-resolution panchromatic image and the multispectral image, and then perform adaptive fusion to obtain a fused intermediate result, and then use total variation regularization to denoise and edge-maintain the fused intermediate result to obtain fused remote sensing image data.

[0009] Furthermore, the formula for adaptive fusion is as follows:

[0010]

[0011] ω MS =1-ω PAN ;

[0012] Among them, Fj,l is the fused coefficient; the subscript j indicates the decomposition level, and l indicates the directional subband; this coefficient is the weighted sum of the corresponding coefficients of the high-resolution panchromatic image and the multispectral image, representing the characteristics of the fused image at a specific scale and direction; It is the coefficient obtained after the high-resolution panchromatic image is transformed by non-subsampled contourlet transform, which represents the high-frequency detail information of the high-resolution panchromatic image in the jth layer and the lth direction; It is the coefficient obtained after the multispectral image is transformed by non-subsampled contourlet transform, which represents the high-frequency detail information of the multispectral image in the jth layer and the lth direction; ω PAN is the weight assigned to the coefficients of the high-resolution full-color image; ω MS are the weights assigned to the multispectral image coefficients; is the variance of the high-resolution panchromatic image in the local window, which reflects the detail richness of the high-resolution panchromatic image in this area; It is the variance of the multispectral image in the local window, which reflects the detail richness of the multispectral image in this area; is the variance of the coefficient differences and is used to control the decay rate of the exponential term.

[0013] Furthermore, when total variation regularization is used to denoise and preserve the edges of the fused intermediate results, the objective function is:

[0014]

[0015]

[0016] Among them, u is the fused remote sensing image data; p is the position variable, which is a two-dimensional variable containing the X-axis coordinate and the Y-axis coordinate; || is the absolute value operation; I fused is the fusion intermediate result; Ω is the image domain, which represents the area of ​​the entire fusion intermediate result; It is the first-order gradient of the fused remote sensing image data u, which is used to capture the edge information of the image; It is the second-order gradient of the image fusion remote sensing image data u, which is used to capture the curvature information of the image; is the penalty function of the gradient, This is a smooth approximation to the total variation, where ∈ is defined as a positive number less than 1; TV β (u) is the total anisotropic variation, defined as:

[0017]

[0018] in, is the first-order gradient of the fused remote sensing image data u in the X-axis direction; is the first-order gradient of the fused remote sensing image data u in the Y-axis direction.

[0019] Furthermore, in the data processing and analysis part, multi-scale fractal analysis is performed on the fused remote sensing image data to obtain the scale-related fractal dimension of the target mining area. The specific process includes: assuming (x, y) is the pixel coordinate in the fused remote sensing image data u, x is the X-axis coordinate, and y is the Y-axis coordinate; using non-subsampled contourlet transform to perform multi-scale decomposition on the fused remote sensing image data u:

[0020] NSCT{u}={c J (x,y)}∪{d j,l (x,y):j∈[1,J],l∈[1,L j ]};

[0021] Among them, c J (x,y) is the low frequency subband, d j,l (x, y) is the directional subband, J is the number of decomposition levels, L j is the number of directions in the jth layer; j is the serial index; the local multifractal spectrum τ is calculated for each directional subband j,l (q,x,y):

[0022]

[0023] Where q is the multifractal moment, B ∈ (x,y) is a sphere with radius ∈ centered at (x,y); (x ′ ,y ′ ) is the pixel coordinate, x ′ is the X-axis coordinate; y ′ is the Y-axis coordinate; based on the local multifractal spectrum, the generalized Hurst index H(q,x,y) is calculated, and the multifractal spectrum and local singularity index are calculated using Legendre transform; then the scale-related fractal dimension is calculated based on the multifractal spectrum and local singularity index.

[0024] Furthermore, the generalized Hurst exponent is calculated based on the local multifractal spectrum using the following formula:

[0025]

[0026] Among them, H(q,x,y) is the generalized Hurst index; the multifractal spectrum and local singularity index are calculated using the Legendre transform through the following formula:

[0027]

[0028] f(α(q,x,y),x,y)=qα(q,x,y)-qH(q,x,y)+2;

[0029] Among them, α(q,x,y) is the local singularity index; f(α,x,y) is the multifractal spectrum.

[0030] Furthermore, the scale-dependent fractal dimension D(s,x,y) is calculated based on the multifractal spectrum and the local singularity index by the following formula:

[0031]

[0032] where s is the scale parameter and α0 is the reference local singularity index.

[0033] Furthermore, the preliminary multispectral adaptive vegetation index MSAVI is calculated based on the reflectance of each band in the fused remote sensing image data using the following formula: initial :

[0034]

[0035] Among them, α NIR is the reflectivity in the near-infrared band; α RED is the reflectivity of the red light band; α SWIR1 is the reflectivity of the short-wave infrared 1 band; α SWIR2 is the reflectance of the shortwave infrared 2 band; NDVI is the normalized vegetation index, which is defined as: β and γ are the first adjustment coefficient and the second adjustment coefficient respectively; w i is the weight of the i-th band; n is the total number of bands in the fused remote sensing image data; where λ i is the central wavelength of the ith band, λ NIR is the central wavelength of the near-infrared band; σ is the third adjustment coefficient.

[0036] Furthermore, the following formula is used to adjust the preliminary multispectral adaptive vegetation index according to the fractal dimension to obtain the adjusted multispectral adaptive vegetation index MSAVI: final :

[0037]

[0038] Among them, D threshold is the fractal dimension threshold.

[0039] By adopting the above technical scheme, the present invention produces the following beneficial effects: the present invention significantly improves the quality and information richness of image data by fusing multi-source remote sensing data. Traditional remote sensing data processing methods usually rely on data from a single platform or a single band. This method is often limited by spatial resolution and spectral information, and it is difficult to fully reflect the actual situation of the surface. The present invention adopts the fusion technology of high-resolution panchromatic images and multi-spectral images, and generates high-quality fused remote sensing image data through wavelet transform and frequency domain fusion. Wavelet transform can effectively enhance the spatial details of the image, and frequency domain fusion integrates the spectral characteristics of different bands, so that the fused image has both high-resolution detail information and rich spectral information. The application of this technology enables the system to have a higher starting point in the data acquisition link, providing a solid foundation for subsequent analysis. Secondly, the present invention adopts a multi-scale fractal analysis method in the data processing and analysis part, which greatly improves the ability to capture the ecological characteristics of the mining area. Traditional ecological restoration effect evaluation methods often rely on single-scale analysis, which is difficult to fully reflect the complex structure and change trend of the ecosystem. The present invention performs multi-scale decomposition of fused remote sensing image data by non-subsampled contourlet transform (NSCT) to obtain low-frequency sub-bands and multiple directional sub-bands, and then combines the calculation of local multi-fractal spectrum and generalized Hurst index to fully reveal the detailed changes of the image at different scales. Multi-scale fractal analysis can not only reflect the complex structure of vegetation and soil, but also quantify the self-similarity and singularity of these structures, providing a strong mathematical basis for the scientific evaluation of ecological restoration effects. The present invention also introduces a multi-spectral adaptive vegetation index (MSAVI) adjustment method based on fractal dimension, making the calculation of vegetation index more accurate and sensitive. Traditional vegetation indices such as NDVI and EVI perform poorly under high vegetation coverage and low vegetation coverage, and are easily affected by soil background and lighting conditions. The present invention significantly improves the sensitivity of vegetation index to different vegetation conditions by introducing the correction of reflectivity and standard deviation index (NDVI) of short-wave infrared band. At the same time, the system adjusts the preliminary MSAVI according to the fractal dimension, so that the final MSAVI not only reflects the coverage and health of vegetation, but also integrates the complexity and recovery of the surface structure. The adjusted MSAVI can more accurately reflect the actual ecological recovery of the mining area and provide a more reliable evaluation basis for decision makers. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of the system structure of a mine ecological restoration effectiveness evaluation system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] All features disclosed in this specification, or steps in all methods or processes disclosed, except mutually exclusive features and / or steps, can be combined in any manner.

[0042] Any feature disclosed in this specification (including any additional claims and abstract), unless otherwise stated, may be replaced by other equivalent or alternative features having similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

[0043] Example 1: Reference Figure 1 A mine ecological restoration effectiveness evaluation system, the system includes: a multi-source remote sensing data fusion part, a data processing and analysis part and an ecological restoration effect evaluation part; the multi-source remote sensing data fusion part is used to obtain multi-source remote sensing image data containing multiple source images of the target mine area, perform spatial detail enhancement and frequency domain fusion based on wavelet transform, and obtain fused remote sensing image data; the data processing and analysis part is used to perform multi-scale fractal analysis on the fused remote sensing image data to obtain the scale-related fractal dimension of the target mine area, and then based on the reflection of each band in the fused remote sensing image data rate, calculate the preliminary multispectral adaptive vegetation index; adjust the preliminary multispectral adaptive vegetation index according to the fractal dimension to obtain the adjusted multispectral adaptive vegetation index; the ecological restoration effect evaluation part is used to establish the multispectral adaptive vegetation index standard interval for mine ecological restoration according to the relationship between the multispectral adaptive vegetation index and mine ecological restoration in historical data, each multispectral adaptive vegetation index standard interval corresponds to a degree of mine ecological restoration, and the degree of ecological restoration of the mine is obtained according to the multispectral adaptive vegetation index standard interval in which the adjusted multispectral adaptive vegetation index is located.

[0044] Specifically, in this system, the multi-source remote sensing data fusion part first needs to obtain multi-source remote sensing image data of the target mining area. Specifically, these data can come from different platforms such as satellite images, drone images, and aerial images, covering multiple bands such as visible light, near infrared, and thermal infrared. These data have their own characteristics in spatial resolution, temporal resolution, and spectral resolution, and can provide information in different dimensions. For example, satellite images usually have a wide coverage and a long time series, which are suitable for monitoring macro changes; while drone images have a higher spatial resolution and can provide more detailed surface detail information. After obtaining multi-source data, the system needs to pre-process these data to eliminate the geometric and radiation differences between different data sources. This step includes operations such as geometric correction, radiation correction, and atmospheric correction, which aims to align images from different data sources to the same spatial coordinate system and make their radiation values ​​comparable. In geometric correction, geographic reference points or high-precision digital elevation models (DEMs) are usually used for correction to ensure the spatial consistency of the image; while radiation correction converts the radiation value of the image into the reflectivity of the ground object through standardization processing, thereby eliminating the radiation differences between different sensors. After preprocessing, the system uses wavelet transform technology to enhance the spatial details of multi-source remote sensing images. Wavelet transform is a multi-resolution analysis method that can effectively decompose the different frequency components in the image and enhance the high-frequency details. Specifically, wavelet transform can decompose the image into low-frequency and high-frequency parts, where the low-frequency part retains the overall structural information of the image, while the high-frequency part contains the details such as the edge and texture of the image. By properly enhancing the high-frequency part, the spatial resolution of the image can be improved, making its details clearer, which is more conducive to the subsequent evaluation of the ecological restoration effect.

[0045] On the basis of spatial detail enhancement, the system further fuses multi-source remote sensing images in the frequency domain. The frequency domain fusion method combines the frequency components of each source image and integrates the advantages of different data sources to generate high-quality fused remote sensing image data. This fusion method can effectively retain and extract the feature information of each source image, thereby improving the overall quality of the fused image. Specifically, frequency domain fusion usually includes operations such as Fourier transform or discrete cosine transform (DCT). By performing spectral analysis on the image, the spatial information of the image is converted into frequency domain information, and fusion processing is performed in the frequency domain. The fused image not only retains the advantages of multi-source data, but also improves the details and contrast of the image, thereby providing a high-quality data basis for subsequent data processing and analysis. Through the above steps, the multi-source remote sensing data fusion part can generate high-quality fused remote sensing image data, providing reliable data support for the evaluation of the effectiveness of mine ecological restoration. This fusion technology not only improves the spatial resolution and detail information of remote sensing data, but also improves the comprehensive quality and information utilization of data by integrating the advantages of different data sources. Compared with the traditional single data source method, multi-source remote sensing data fusion has obvious advantages and can provide more comprehensive and detailed information on the target mining area, thus providing a more scientific and accurate basis for the evaluation of ecological restoration effectiveness.

[0046] The data processing and analysis part is one of the core links of the mine ecological restoration effectiveness evaluation system. Its main task is to conduct in-depth analysis and processing of the fused multi-source remote sensing image data, so as to provide a scientific basis for the evaluation of the ecological restoration effect. First, the system performs multi-scale fractal analysis on the fused remote sensing image data. This process aims to reveal the surface characteristics and complexity of the mining area. Fractal analysis is a mathematical method that describes the geometric complexity and spatial structure characteristics of the surface by calculating the fractal dimension. In the evaluation of the effectiveness of mine ecological restoration, the fractal dimension can reflect the restoration of surface vegetation and soil, because natural ecosystems often show certain fractal characteristics. Through multi-scale fractal analysis, the system can obtain the fractal dimension of the target mining area at different scales, so as to comprehensively evaluate its ecological restoration degree. Another important role of multi-scale fractal analysis is to help identify the details and changing trends of mine ecological restoration. By calculating the fractal dimension at different scales, the system can capture the changes in surface details, such as changes in the density of vegetation cover and improvements in soil structure. This information is crucial for evaluating the effectiveness of ecological restoration, because changes in details can often provide information about ecological restoration progress that cannot be revealed by macroscopic changes. Through multi-scale fractal analysis, the system can provide basic data for subsequent vegetation index calculations, thereby improving the accuracy of evaluation results.

[0047] After obtaining the multi-scale fractal dimension, the system uses the reflectance of each band in the fused remote sensing image data to calculate the preliminary multi-spectral adaptive vegetation index. The multi-spectral adaptive vegetation index is a vegetation index based on multi-spectral remote sensing data, which can reflect the coverage and health of surface vegetation. By calculating the ratio of reflectances of different bands, the system can preliminarily estimate the vegetation coverage of the mining area. However, relying solely on the preliminary vegetation index calculation may not fully reflect the true situation of ecological restoration, so further adjustment and optimization are needed. In order to improve the accuracy of the multi-spectral adaptive vegetation index, the system introduces an adjustment mechanism for the fractal dimension. Specifically, the system adjusts the preliminary multi-spectral adaptive vegetation index according to the fractal dimension obtained by the aforementioned multi-scale fractal analysis. The fractal dimension can reflect the geometric complexity of the surface and the detailed changes of ecological restoration. Therefore, by introducing it into the calculation of the vegetation index, the actual situation of mine ecological restoration can be more accurately reflected. This adjustment mechanism not only improves the accuracy of the vegetation index, but also can eliminate the noise and errors in the remote sensing data to a certain extent, making the evaluation results more reliable. After completing the adjustment of the vegetation index, the system uses the adjusted multispectral adaptive vegetation index to evaluate the effect of ecological restoration. Specifically, the system establishes a set of standard intervals for the multispectral adaptive vegetation index based on the relationship between the multispectral adaptive vegetation index and the ecological restoration effect of the mine in historical data. Each standard interval corresponds to a specific degree of ecological restoration effect, such as unrecovered, partially recovered, and fully recovered. By comparing the adjusted multispectral adaptive vegetation index with these standard intervals, the system can quantitatively evaluate the degree of ecological restoration of the mine. This evaluation method based on standard intervals is highly scientific and operational, and can not only provide clear evaluation results, but also provide guidance and reference for ecological restoration work.

[0048] The ecological restoration effect evaluation part is the final link of the mine ecological restoration effectiveness evaluation system and the key to the entire system. Its core task is to use the processed and analyzed data to conduct a scientific, systematic and comprehensive evaluation of the effectiveness of mine ecological restoration. First, this part establishes a set of standard intervals of multispectral adaptive vegetation index based on the relationship between multispectral adaptive vegetation index and mine ecological restoration effect in historical data. These standard intervals form the vegetation index range corresponding to different degrees of ecological restoration through the analysis and mining of a large amount of historical data. Each standard interval represents a specific degree of ecological restoration, from never restored to fully restored, covering all stages of mine ecological restoration. In actual operation, after obtaining the adjusted multispectral adaptive vegetation index, the system will compare the index with the pre-established standard interval. This process is similar to matching the current data with the standard interval, and the degree of ecological restoration of the mine can be quickly determined. Such an evaluation method is not only scientific, but also efficient. Through this quantitative method, the system can avoid the subjectivity and uncertainty in traditional evaluation methods and provide more objective and accurate evaluation results. In addition, the ecological restoration effect evaluation part also takes into account the complexity and diversity of the ecosystem. Mine ecological restoration not only involves the restoration of vegetation, but also includes improvements in soil structure, hydrological characteristics, biodiversity and other aspects. Therefore, when establishing the standard interval, the system not only relies on the vegetation index, but also takes into account a variety of ecological indicators. Through the comprehensive analysis of these indicators, the system can provide a more comprehensive evaluation of the effect of ecological restoration. For example, while considering vegetation restoration, the system will also evaluate the improvement of soil, the restoration of water sources and the increase of biodiversity. In this way, through a comprehensive evaluation of multiple dimensions and multiple indicators, the restoration effect of the mine ecosystem can be fully reflected.

[0049] When evaluating, the system will also combine spatial analysis technology to conduct zoning evaluation of different locations in the mining area. Mine ecological restoration is often a staged and regional process, and the restoration effects in different areas may vary significantly. Therefore, through spatial analysis of remote sensing images, the system can divide the mining area into multiple evaluation units and evaluate the restoration effect of each unit separately. In this way, not only can the overall restoration effect be understood, but also the restoration progress of specific areas can be grasped, providing precise guidance for further restoration work. During the evaluation process, the system will also use time series analysis methods to dynamically monitor and evaluate the ecological restoration effect. Ecological restoration is a long-term process, and it takes time for the restoration effect to appear. Therefore, by analyzing remote sensing data from different periods, the system can track the progress of ecological restoration and understand the changing trend of restoration effects. This dynamic monitoring not only helps to timely discover problems in the restoration process, but also provides a scientific basis for adjusting restoration strategies. For example, if the restoration effect of a certain area is stagnant for a long time, the system can issue a timely warning and recommend corresponding improvement measures. It is worth noting that the ecological restoration effect evaluation part also takes into account the impact of external factors such as climate change. The restoration of the mine ecosystem depends not only on human intervention, but also on natural environmental conditions. The system analyzes climate data to assess the potential impact of climate change on restoration results, ensuring the scientificity and reliability of the evaluation results. For example, when evaluating the effect of vegetation restoration, the system will take into account changes in climate factors such as precipitation and temperature to avoid misjudgments due to abnormal climate conditions.

[0050] Before the ecological restoration project was carried out in a mining area, due to long-term ore mining, the surface vegetation was severely damaged, the soil structure was damaged, the water source was exhausted, and the biodiversity decreased significantly. After the restoration project was implemented, through a series of measures such as vegetation reconstruction, soil improvement and water source restoration, the ecological environment of the area has gradually improved. In order to scientifically evaluate the restoration effect, the mining area adopted a mine ecological restoration effectiveness evaluation system.

[0051] The system first collected multi-source remote sensing image data before and after the restoration of the mining area. These data include satellite images, drone images and aerial images at different time points, covering multiple bands such as visible light, near infrared and thermal infrared. By performing geometric correction, radiation correction and atmospheric correction on these data, the system eliminates the geometric and radiation differences between different data sources to ensure the consistency and comparability of the data. The system uses wavelet transform technology to enhance the spatial details of multi-source remote sensing images and fuses the images in the frequency domain to generate high-quality fused remote sensing image data. This step improves the spatial resolution and detail information of the image, providing a high-quality data basis for subsequent data processing and analysis. The system performs multi-scale fractal analysis on the fused remote sensing image data and calculates the fractal dimensions of the target mining area at different scales. These fractal dimensions reflect the complexity and spatial structure characteristics of the surface vegetation, and provide an important reference for evaluating the effect of ecological restoration. In this example, the change in fractal dimension shows the gradual recovery of vegetation coverage in the mining area, the improvement of soil structure and the increase in the complexity of the ecosystem.

[0052] Based on the reflectivity of each band in the fused remote sensing image data, the system calculated the preliminary multispectral adaptive vegetation index (MAVI). In order to improve the accuracy of the index, the system adjusted the preliminary MAVI according to the fractal dimension to obtain a more accurate adjusted MAVI. These adjusted indices can more truly reflect the actual situation of mine ecological restoration. Based on the relationship between MAVI and the effect of mine ecological restoration in historical data, the system established a set of standard intervals for MAVI. For example, the system divides the MAVI value into the following intervals:

[0053] MAVI < 0.2: Not recovered

[0054] 0.2≤MAVI<0.4: Initial recovery

[0055] 0.4≤MAVI<0.6: Partial recovery

[0056] 0.6≤MAVI<0.8: Significant recovery

[0057] MAVI ≥ 0.8: Full recovery

[0058] By comparing the adjusted MAVI with these standard intervals, the system can quickly determine the degree of ecological restoration in the mining area. In this example, the adjusted MAVI value is 0.65, which indicates that the ecological restoration effect of the mining area has reached the level of significant recovery. The system further combines spatial analysis technology to conduct zoning evaluation of different areas of the mining area, and found that the restoration effect in the central and eastern areas of the mining area is better, and the MAVI value is generally above 0.7, which belongs to the category of significant recovery to complete recovery; while the restoration effect in the western and northern areas of the mining area is relatively poor, and the MAVI value is between 0.4 and 0.6, which belongs to the category of partial recovery. Such zoning evaluation results provide a scientific basis for further optimization of restoration projects.

[0059] Embodiment 2: The multi-source remote sensing data fusion part includes: a data acquisition unit, which is used to acquire multi-source remote sensing image data including high-resolution panchromatic images and multispectral images when acquiring multi-source remote sensing image data of a target mining area containing multiple source images; a data processing unit, which is used to perform nonlinear enhancement on the high-frequency sub-bands of the high-resolution panchromatic image, perform PCA transformation on the multispectral image, and then perform non-subsampled contourlet transformation on the first principal component of the high-resolution panchromatic image and the multispectral image, and then perform adaptive fusion to obtain a fused intermediate result, and then use total variation regularization to denoise and edge-maintain the fused intermediate result to obtain fused remote sensing image data.

[0060] Specifically, first, the data acquisition unit of the system is responsible for collecting multi-source remote sensing image data of the target mining area. These data include high-resolution panchromatic images and multispectral images. High-resolution panchromatic images have high spatial resolution and can provide detailed surface detail information; while multispectral images cover information from multiple bands and can reflect the spectral characteristics of the surface. The combination of these two types of images can provide a rich source of information for the comprehensive evaluation of the ecological restoration effect of mines. Next, the data processing unit preprocesses and processes the acquired remote sensing image data. First, the high-frequency subbands of the high-resolution panchromatic image are nonlinearly enhanced. The high-frequency subband contains the edge and detail information in the image. Through nonlinear enhancement, these details can be highlighted, so that the image has better clarity and resolution after fusion. Nonlinear enhancement methods usually use adaptive enhancement functions to avoid noise amplification caused by over-enhancement while maintaining image details. While processing the high-resolution panchromatic image, the system also performs principal component analysis (PCA) transformation on the multispectral image. PCA transformation is a dimensionality reduction method that can simplify the complexity of data processing while retaining the main information in the image by converting the information in the multispectral image into a few principal components. The first principal component usually contains most of the image information, so in the subsequent processing process, focusing on the first principal component can effectively improve the processing efficiency.

[0061] Then, the system performs non-subsampled contourlet transform (NSCT) on the first principal component of the high-resolution panchromatic image and the multispectral image. NSCT is a multi-scale and multi-directional image transformation method that can decompose images at different scales and directions to capture the details and structural features in the image. Through the NSCT transformation, the main features of the panchromatic image and the multispectral image can be decomposed into multiple sub-bands, providing a data basis for subsequent adaptive fusion. After completing the NSCT transformation, the system performs adaptive fusion. The adaptive fusion method adaptively selects the fusion strategy according to the characteristics of different sub-bands to maximize the retention of the dominant information of each image. Specifically, adaptive fusion can dynamically adjust the fusion weights according to the local features of the image, such as gradients and textures, so that the fused image can retain high-resolution details and multi-spectral spectral information in different regions. In this way, the generated fusion intermediate result has both high-resolution details and rich spectral information, which can fully reflect the ecological characteristics of the mining area. However, the intermediate result obtained after direct adaptive fusion may contain some noise and unnecessary details. In order to further improve the image quality, the system uses total variation regularization to denoise and edge-preserve the fused intermediate result. Total variation regularization is a commonly used method for image denoising. By minimizing the total variation of the image, it can effectively remove noise while retaining the edges and important details of the image. Specifically, total variation regularization obtains the denoised image by solving the variational problem. The edge and structural features of the image are maintained during the denoising process, so that the final generated fused remote sensing image data has higher quality and clarity.

[0062] Embodiment 3: The formula for performing adaptive fusion is as follows:

[0063]

[0064] ω MS =1-ω PAN ;

[0065] Among them, F j,l is the fused coefficient; the subscript j indicates the decomposition level, and l indicates the directional subband; this coefficient is the weighted sum of the corresponding coefficients of the high-resolution panchromatic image and the multispectral image, representing the characteristics of the fused image at a specific scale and direction; It is the coefficient obtained after the high-resolution panchromatic image is transformed by non-subsampled contourlet transform, which represents the high-frequency detail information of the high-resolution panchromatic image in the jth layer and the lth direction; It is the coefficient obtained after the multispectral image is transformed by non-subsampled contourlet transform, which represents the high-frequency detail information of the multispectral image in the jth layer and the lth direction; ω PAN is the weight assigned to the coefficients of the high-resolution full-color image; ω MSare the weights assigned to the multispectral image coefficients; is the variance of the high-resolution panchromatic image in the local window, which reflects the detail richness of the high-resolution panchromatic image in this area; It is the variance of the multispectral image in the local window, which reflects the detail richness of the multispectral image in this area; is the variance of the coefficient differences and is used to control the decay rate of the exponential term.

[0066] Specifically, the fusion coefficient F j,l is through the high-resolution full-color image coefficient and multispectral image coefficients The calculation of this weighted sum depends on two weight parameters ω PAN and ω MS , where ω PAN and ω MS Represent the weights of high-resolution panchromatic image and multispectral image in the fusion process. Formula definition ω MS =1-ω PAN , ensuring that the sum of the two weights is 1, thus ensuring the stability and consistency of the fusion process. PAN The calculation of contains two main parts: local variance ratio and difference exponential decay. The local variance ratio part is determined by comparing the variance of the high-resolution panchromatic image and the multispectral image within a local window. Specifically, the weight ω PAN is the local variance of the high-resolution panchromatic image and the local variance of the multispectral image This ratio reflects the richness of details in the local area of ​​the image. If the high-resolution panchromatic image has richer details (i.e., the local variance is larger), its weight will increase accordingly, and vice versa. The difference exponential decay part calculates the difference between the high-resolution panchromatic image coefficients and the multispectral image coefficients, and uses an exponential decay function to process the difference, thereby further adjusting the weight. Specifically, the weight ω PAN Contains an exponential term in represents the coefficient difference between high-resolution panchromatic and multispectral images, is a parameter that controls the exponential decay rate. The introduction of this exponential term can reduce the weight of the high-resolution panchromatic image in areas with large coefficient differences, thereby reducing artifacts and inconsistencies that may appear in the fused image. Specifically, when the coefficients of the high-resolution panchromatic image and the multispectral image differ greatly, the value of the exponential term decreases, thereby reducing ω PAN The value of increases the weight of the multispectral image. On the contrary, when the difference between the coefficients of the two is small, the value of the exponential term is large, ω PANThe value of is relatively high, and the high-resolution panchromatic image occupies a larger proportion in the fusion process. Through this adaptive adjustment mechanism, the fusion formula can dynamically balance the contribution of the two images, so that the fused image can retain detailed spatial information in different regions and reflect the true spectral characteristics.

[0067] Example 4: When total variation regularization is used to denoise and preserve edges of the fused intermediate results, the objective function is:

[0068]

[0069] Among them, u is the fused remote sensing image data; p is the position variable, which is a two-dimensional variable containing the X-axis coordinate and the Y-axis coordinate; || is the absolute value operation; I fused is the fusion intermediate result; Ω is the image domain, which represents the area of ​​the entire fusion intermediate result; It is the first-order gradient of the fused remote sensing image data u, which is used to capture the edge information of the image; It is the second-order gradient of the image fusion remote sensing image data u, which is used to capture the curvature information of the image; is the penalty function of the gradient, This is a smooth approximation to the total variation, where ∈ is defined as a positive number less than 1; TV β (u) is the total anisotropic variation, defined as:

[0070]

[0071] in, is the first-order gradient of the fused remote sensing image data u in the X-axis direction; is the first-order gradient of the fused remote sensing image data u in the Y-axis direction.

[0072] Specifically, in the mine ecological restoration effectiveness evaluation system, total variation regularization (TV) is a key image processing technology used to denoise and preserve the edges of the fused intermediate results. Total variation regularization converts the requirements of denoising and edge preservation into an optimization problem by constructing a complex objective function, thereby generating high-quality fused remote sensing image data. This objective function comprehensively considers multiple factors such as data fidelity, gradient penalty, second-order gradient, gradient square ratio, and total anisotropic variation. First, the data fidelity term in the objective function is expressed in integral form, that is, Where u represents the final fused remote sensing image data, I fused is the intermediate result of fusion. is the average weight of the high-resolution panchromatic image and the multispectral image. This part ensures the similarity between the fused image and the original fusion result, so that the denoised image can maintain the characteristics and details of the original data. By minimizing this term, the optimization process can retain the characteristic information of the original image to the greatest extent. Secondly, the gradient penalty term It is the core part of total variation regularization. Used to smooth image gradients, is the gradient of the image. The gradient penalty term avoids the loss of details caused by over-smoothing by penalizing the gradient of the image, while effectively removing noise from the image. This term is particularly suitable for maintaining the edge information of the image, because the gradient can capture the edges and details in the image. ∈ is a positive number less than 1, which is used to avoid the situation where the gradient is zero, thereby improving the stability of numerical calculations. Third, the second-order gradient term in the objective function By penalizing the second-order gradient of the image, the curvature information of the image is captured, further smoothing the image while retaining its main structure. This term is particularly effective for removing high-frequency noise in the image, because high-frequency noise usually appears as a large second-order gradient value. By penalizing the second-order gradient, the optimization process can generate a more natural and smooth image while reducing noise. In addition, the gradient square ratio term By controlling the ratio of the squared gradient, the details of the image are further smoothed. This item is designed to balance the contradiction between denoising and detail preservation. By minimizing this item, the system can retain the edge information of the image to the greatest extent while removing noise, so that the edge area will not be blurred by denoising. This is particularly important in the evaluation of the ecological restoration effect of mines, because edge information is crucial to identifying and analyzing ecological changes in mining areas. Finally, the anisotropic total variation term TV included in the objective function β (u) measures the gradient change of the image in the X-axis and Y-axis directions. and Penalization is performed to ensure smooth processing of the image in different directions. The total anisotropic variation is expressed as This term reduces the impact of anisotropic noise while maintaining the overall structure and edge details of the image, further improving the image quality. Total variation regularization optimizes the fusion intermediate results by constructing an objective function containing multiple constraints and penalties, thereby achieving image denoising and edge preservation. The data fidelity term ensures that the original features of the image are not destroyed. The gradient penalty term and the second-order gradient term effectively remove noise by penalizing the gradient and second-order gradient of the image, while retaining the edge information of the image. The gradient square ratio term further balances the needs of denoising and detail preservation, while the anisotropic total variation term ensures the overall smoothness and structural integrity of the image by controlling the gradient changes of the image in different directions.

[0073] Embodiment 5: Data processing and analysis part, performing multi-scale fractal analysis on the fused remote sensing image data to obtain the scale-related fractal dimension of the target mining area specifically includes: assuming (x, y) is the pixel coordinate in the fused remote sensing image data u, x is the X-axis coordinate, and y is the Y-axis coordinate; using non-subsampled contourlet transform to perform multi-scale decomposition on the fused remote sensing image data u:

[0074] NSCT{u}={c J (x,y)}∪{d j,l (x,y):j∈[1,J],l∈[1,L j ]};

[0075] Among them, c J (x,y) is the low frequency subband, d j,l (x, y) is the directional subband, J is the number of decomposition levels, L j is the number of directions in the jth layer; j is the serial index; the local multifractal spectrum τ is calculated for each directional subband j,l (q,x,y):

[0076]

[0077] Where q is the multifractal moment, B ∈ (x,y) is a sphere with radius ∈ centered at (x,y); (x ′ ,y ′ ) is the pixel coordinate, x ′ is the X-axis coordinate; y ′ is the Y-axis coordinate; based on the local multifractal spectrum, the generalized Hurst index H(q,x,y) is calculated, and the multifractal spectrum and local singularity index are calculated using Legendre transform; then the scale-related fractal dimension is calculated based on the multifractal spectrum and local singularity index.

[0078] Specifically, in the mine ecological restoration effectiveness evaluation system, the multi-scale fractal analysis process of the data processing and analysis part can comprehensively reveal the geometric structure and ecological changes of the target mining area by performing fine decomposition and complex mathematical processing on the fused remote sensing image data. The core steps involve non-subsampled contourlet transform, multi-fractal spectrum calculation and analysis of the generalized Hurst index, and finally the scale-related fractal dimension is obtained. Behind these steps are profound mathematical principles and image processing technology support, which will be elaborated in detail below. First, the non-subsampled contourlet transform (NSCT) is performed on the fused remote sensing image data u to achieve multi-scale decomposition of the image. NSCT is an advanced image transformation method that can effectively capture the details and edge information of the image while maintaining the spatial consistency of the image. Through NSCT, the image is decomposed into low-frequency sub-bands c J(x,y) and multiple directional subbands d j,l (x, y). The low-frequency subband mainly contains the overall structure of the image, while the directional subband reflects the high-frequency details of the image in different directions and scales. This decomposition method can represent the complex information of the image in a hierarchical manner, which is convenient for subsequent multi-scale analysis. After completing the multi-scale decomposition of the image, the system performs a multi-scale analysis on each directional subband d. j,l (x,y) performs local multifractal spectrum τ j,l (q,x,y). The calculation of the local multifractal spectrum is to analyze the distribution of pixel intensity to reveal the detailed changes of the image at different scales. Specifically, the multifractal spectrum reflects the complexity and self-similarity of the image by measuring the moments at different q values. Here, q is a multifractal moment, which indicates the sensitivity to different scales. By gradually reducing the neighborhood radius ∈, the pixel intensity |d j,l (x ′ ,y ′ )| q The cumulative sum of τ and the logarithmic relationship are finally obtained. j,l (q,x,y).

[0079] The calculation of the multifractal spectrum reflects the local complexity and detail changes of the image at different scales. For example, for the mining area after ecological restoration, different vegetation cover types and soil structures will show different fractal characteristics. Through the multifractal spectrum, these changes can be quantitatively analyzed to reveal the specific effects of ecological restoration. After obtaining the local multifractal spectrum, the system further calculates the generalized Hurst index H(q,x,y). The generalized Hurst index is an indicator used to describe the self-similarity and roughness of data. By calculating the generalized Hurst index, the changing trend of the image at different scales can be quantified. Specifically, the generalized Hurst index is calculated by multifractal spectrum τ j,l Legendre transform (q,x,y) to get:

[0080]

[0081] Legendre transform can convert multifractal spectrum into generalized Hurst index and local singularity index, thus revealing the self-similarity and detail characteristics of the image at different scales. The calculation of generalized Hurst index can help understand the ecological changes in mining areas. For example, an increase in generalized Hurst index usually indicates the recovery of vegetation cover and soil structure, because the geometric structure of these areas becomes more complex and rich. On the contrary, if the generalized Hurst index does not change significantly, it may mean that the ecological restoration effect is not obvious. The change of generalized Hurst index H(q,x,y) can quantify the recovery of the ecosystem. For example, in the process of vegetation restoration, different vegetation types and cover densities will show different Hurst index values. By comparing the Hurst index of different regions, the effect and progress of ecological restoration can be evaluated, providing a scientific basis for further optimizing restoration measures. Finally, based on the generalized Hurst index and multifractal spectrum, the scale-related fractal dimension is systematically calculated. Fractal dimension is an important indicator for describing complex geometric morphology, which can quantify the complexity and detail of images at different scales. In the evaluation of the effectiveness of mine ecological restoration, the change of fractal dimension can intuitively reflect the recovery of the ecosystem. For example, the increase in fractal dimension means that the vegetation coverage is richer and the soil structure is more complex, indicating that the ecological restoration measures have achieved remarkable results. Specifically, the fractal dimension quantifies the restoration of vegetation and soil by analyzing the detailed changes of the image at different scales, and provides an important quantitative indicator for the scientific evaluation of the ecological restoration effect. Through this multi-scale fractal analysis method, the system can fully reveal the ecological changes in the mining area and provide a scientific basis for the quantitative evaluation of the ecological restoration effect. Compared with the traditional single-scale analysis method, multi-scale fractal analysis not only considers the detailed changes at different scales, but also can provide more comprehensive and accurate evaluation results through multiple indicators such as generalized Hurst index and fractal dimension. This is of great significance for guiding the ecological restoration work of mines and optimizing restoration measures. For example, if the fractal dimension of a certain area increases significantly, the system can identify that the ecological restoration effect of the area is good, and then promote the restoration measures used in the area to other areas; on the contrary, if the fractal dimension of some areas does not change significantly, the system can prompt the need to strengthen the restoration efforts or adjust the restoration strategy. The data processing and analysis part systematically performs multi-scale fractal analysis on the fused remote sensing image data through the calculation of non-subsampled contourlet transform, multi-fractal spectrum and generalized Hurst index, and obtains the scale-related fractal dimension of the target mining area. This process not only reveals the complex geometric structure and ecological changes in the mining area, but also provides important quantitative indicators for the scientific evaluation of the ecological restoration effect. Through this method, the system can more accurately evaluate the effectiveness of mine ecological restoration, provide a scientific basis for the optimization and improvement of ecological restoration work, and promote the sustainable development of the mining ecological environment.

[0082] Example 6: The generalized Hurst index is calculated based on the local multifractal spectrum using the following formula:

[0083]

[0084] Among them, H(q,x,y) is the generalized Hurst index; the multifractal spectrum and local singularity index are calculated using the Legendre transform through the following formula:

[0085]

[0086] f(α(q,x,y),x,y)=qα(q,x,y)-qH(q,x,y)+2;

[0087] Among them, α(q,x,y) is the local singularity index; f(α,x,y) is the multifractal spectrum.

[0088] Specifically, the core of the calculation formula of the generalized Hurst index H(q,x,y) is to use the local multifractal spectrum τ j,l (q,x,y) to quantify the self-similarity and roughness of the image at different scales. In the formula, H(q,x,y) is calculated by the limit operation lim j→∞ and logarithm operation log2 to capture the behavior of the image at a large scale, thereby revealing the overall characteristics. Specifically, the molecule and the denominator Represent the accumulation of multifractal spectra at the current scale level and the previous level respectively. By comparing these accumulated values, the changing trend of the image at different scales can be identified. The principle of this method is to use multifractal analysis to process image data. Multifractal analysis is a mathematical tool that can capture the complexity of images, and is particularly suitable for dealing with heterogeneity in natural landscapes and ecosystems. For the mine ecological restoration effectiveness evaluation system, this method can reveal the ecological restoration of the mine area at different scales. For example, changes in vegetation coverage and restoration of soil structure can be reflected by the generalized Hurst index. The higher the Hurst index, the more complex and healthy the ecosystem in the area is, and the better the restoration effect is. After obtaining the generalized Hurst index, the system further uses Legendre transform to calculate the local singularity index α(q,x,y) and the multifractal spectrum f(α,x,y). Legendre transform is a mathematical tool borrowed from thermodynamics, which is used to convert the generalized Hurst index into more physically meaningful parameters. By taking the derivative of qH(q,x,y), the local singularity index α(q,x,y) is obtained, which reflects the detail changes of the image in the local area. This index can quantify the complexity changes in a certain area and provide support for the fine analysis of the ecological restoration effect. The calculation formula of the multifractal spectrum f(α,x,y) further utilizes the relationship between α(q,x,y) and the generalized Hurst index H(q,x,y). By calculating qα(q,x,y)-qH(q,x,y)+2, the self-similarity and singularity of the image at different scales are revealed. This process can refine the complexity of the image to the local scale, so that the evaluation system can identify small changes in the ecological restoration of the mine. For example, different types of vegetation coverage and soil remediation effects will show different characteristics in the multifractal spectrum, which can help decision makers more accurately evaluate the effectiveness of remediation measures. Overall, the calculation method of the generalized Hurst index, local singularity index and multifractal spectrum provides a powerful data analysis tool for the mine ecological restoration effectiveness evaluation system. Through these mathematical methods, the system can finely capture the progress and effects of mine ecological restoration, and provide quantitative indicators to evaluate the effectiveness and efficiency of restoration measures. Especially when processing remote sensing image data, these methods can effectively integrate multi-source data and reveal details of ecological changes that cannot be directly observed by the naked eye. Through the above analysis methods, the system can not only provide an evaluation of the current ecological restoration effect, but also predict future restoration progress trends. This is of great significance for scientific decision-making and optimal resource allocation. For example, if the generalized Hurst index and multifractal spectrum of a certain area show a significant positive change trend, it can be considered that the restoration measures in the area are effective and can continue to be used or promoted in other areas. If the indicators in a certain area do not change significantly, the restoration strategy needs to be re-evaluated, and it may be necessary to increase investment or change the restoration method.

[0089] Embodiment 7: The scale-dependent fractal dimension D(s, x, y) is calculated according to the multifractal spectrum and the local singularity index by the following formula:

[0090]

[0091] where s is the scale parameter and α0 is the reference local singularity index.

[0092] Specifically, the core idea of ​​this formula is to weigh the multi-fractal spectra under different local singularity indices through integration, and finally obtain a comprehensive scale-dependent fractal dimension D(s,x,y). The integral part of the formula is and In the weight function The introduction of is the key. This weight function is a Gaussian function, whose center is located at the reference local singularity index α0, and the scale parameter s controls the width of the Gaussian function. The role of the weight function is to weight different local singularity indices, so that the values ​​close to α0 have a larger weight, while the values ​​far from α0 have a smaller weight. Through this weighting, the formula can effectively highlight those local singularity indices close to the reference value α0, thereby more accurately reflecting the fractal characteristics of the image at this scale. This processing method helps to capture subtle structural changes in complex ecosystems, especially in the process of mine ecological restoration, where vegetation restoration and soil improvement in different regions may have significant differences. In the evaluation of ecological restoration effectiveness, the scale parameter s plays an important role. The choice of scale parameter s directly affects the width of the weight function, thereby controlling the contribution of different local singularity indices in the integration process. A smaller s value means that the weight function is more concentrated, emphasizing those local singularity indices that are very close to α0, which helps to highlight details and local features; a larger s value makes the weight function more dispersed, which can comprehensively consider more local singularity indices and is suitable for capturing overall structural changes. In the process of mine ecological restoration, by adjusting the s value, the recovery of the ecosystem can be flexibly evaluated according to different analysis needs.

[0093] The multifractal spectrum f(α, x, y) in the formula is a function that measures the complexity and detail richness of an image at different local singularity indices. By multiplying the multifractal spectrum with the weight function and integrating it, a comprehensive scale-dependent fractal dimension D(s, x, y) can be calculated. This process not only considers the characteristics of the image at a single scale, but also covers the changes at different scales through integration, thus providing a more comprehensive evaluation index. The mine ecological restoration effectiveness evaluation system uses the scale-dependent fractal dimension D(s, x, y) to quantify and evaluate the ecological restoration effect of the mine area. For example, areas with good vegetation restoration usually show higher fractal dimensions because the geometric structures of these areas are more complex and rich. On the contrary, areas with less obvious restoration effects may show lower fractal dimensions. This quantitative evaluation index can not only intuitively reflect the effect of ecological restoration, but also help decision makers identify areas that need further restoration and improvement. In addition, by analyzing the changes in fractal dimensions at different scales, the system can provide a more in-depth understanding of ecological restoration. For example, comparing the fractal dimensions of the same area at different time points can reveal the progress of ecological restoration. If the fractal dimension increases significantly over time, it means that the restoration measures have achieved good results; if the fractal dimension does not change much, it may be necessary to re-evaluate and adjust the restoration strategy.

[0094] Example 8: The preliminary multispectral adaptive vegetation index MSAVI is calculated based on the reflectance of each band in the fused remote sensing image data using the following formula: initial :

[0095]

[0096] Among them, α NIR is the reflectivity in the near-infrared band; α REd is the reflectivity of the red light band; α SWIR1 is the reflectivity of the short-wave infrared 1 band; α SWIR2 is the reflectance of the shortwave infrared 2 band; NDVI is the normalized vegetation index, which is defined as: β and γ are the first adjustment coefficient and the second adjustment coefficient respectively; w i is the weight of the i-th band; n is the total number of bands in the fused remote sensing image data;

[0097] where λ i is the central wavelength of the ith band, λ NIR is the central wavelength of the near-infrared band; σ is the third adjustment coefficient.

[0098] Specifically, the calculation formula of MSAVI contains an expression based on the reflectance of the near-infrared band and the red light band. The core part of this expression can be regarded as an improvement on the traditional vegetation index (such as NDVI). Specifically, part of the formula By introducing square root terms and linear combinations, the reflectance difference between the near-infrared and red bands is further adjusted to more accurately reflect the actual condition of vegetation. NIR ) and the reflectivity (α RED ) are the two most commonly used parameters in vegetation index calculation. This is because healthy vegetation has a higher reflectivity in the near-infrared band and a lower reflectivity in the red band. By combining the reflectivity of these two bands, vegetation cover and bare land can be effectively distinguished. In the formula, through the above complex expressions, higher sensitivity can be provided under different vegetation conditions, reducing errors caused by changes in soil background and lighting conditions. Secondly, the second part of the formula introduces a multi-band weighting mechanism to comprehensively consider the impact of reflectivity in different bands on the vegetation index. The expression of this part is where α i Represents the reflectivity of other bands, w i is the weight of the corresponding band. This weighting mechanism calculates the weight through the Gaussian distribution function, that is, where λ i is the central wavelength of the ith band, λ NIR is the central wavelength of the near-infrared band, and σ is an adjustment factor. The introduction of the Gaussian distribution function makes the weight w i It is more sensitive to bands whose central wavelengths are close to the near-infrared band. This means that bands adjacent to the near-infrared band have a greater weight in the calculation of the vegetation index because these bands have similar reflectance characteristics to the near-infrared band and can more accurately reflect the vegetation condition. In this way, the formula can integrate information from different bands and increase sensitivity to vegetation health. In addition, a correction term based on NDVI and the reflectance of the shortwave infrared bands (SWIR1 and SWIR2) is introduced into the formula. NDVI is a commonly used vegetation index, expressed as In the formula, NDVI is adjusted by a sine function and multiplied by an adjustment factor β to increase its sensitivity to different vegetation cover conditions. The specific expression is This adjustment allows the vegetation index to more accurately reflect vegetation changes in different seasons and growth stages. The reflectance of the shortwave infrared bands (SWIR1 and SWIR2) is corrected by an exponential decay function. The expression for this part is Among them, γ is a regulating factor. The reflectivity of the short-wave infrared band can reflect the moisture content of vegetation and soil moisture. By comparing the reflectivity difference between the two short-wave infrared bands, the sensitivity of the vegetation index to the ecological status can be further improved. The design of the formula enables MSAVI to not only capture the health of vegetation, but also make sensitive adjustments to soil moisture and other environmental factors. This multi-dimensional consideration makes MSAVI more accurate and reliable in evaluating the ecological restoration effect of mines. For example, under drought conditions, the moisture content of vegetation decreases, and the reflectivity of the short-wave infrared band changes significantly. By introducing the correction term of the short-wave infrared band, the formula can more accurately reflect this change. MSAVI can provide a comprehensive vegetation index for quantifying the vegetation restoration in the mining area. In practical applications, the system can generate detailed vegetation restoration reports using MSAVI to help decision makers scientifically evaluate the restoration effect. For example, when the MSAVI value of a certain area increases significantly, it means that the vegetation in the area has recovered well, and the current restoration measures can be further promoted; while for those areas where the MSAVI value does not change much, it may be necessary to re-evaluate the restoration strategy, increase resource investment or adopt new technical means.

[0099] Example 9: Using the following formula, the preliminary multispectral adaptive vegetation index is adjusted according to the fractal dimension to obtain the adjusted multispectral adaptive vegetation index MSAVI final :

[0100]

[0101] Among them, D threshold is the fractal dimension threshold.

[0102] Specifically, the initial multispectral adaptive vegetation index (MSAVI_initial) is calculated based on the reflectance of each band in the fused remote sensing image data. This index can provide preliminary information about vegetation coverage and health status. However, in order to more accurately reflect the effect of ecological restoration, it needs to be further adjusted in combination with the fractal dimension. The fractal dimension D (s, x, y) is an important parameter for describing the complexity of terrain and vegetation. In the evaluation of ecological restoration effectiveness, the fractal dimension can reflect the geometric complexity of vegetation and surface features. By introducing the fractal dimension threshold D threshold , which can effectively distinguish areas with different degrees of recovery. When the fractal dimension is higher than the threshold, it means that the ecosystem structure in the area is more complex and rich, otherwise it may indicate that the ecosystem recovery is insufficient. The core part of the adjustment formula is a nonlinear adjustment function This function is a Sigmoid function, which is used to relate the fractal dimension to the adjustment factor. The form of the Sigmoid function is Its characteristic is that it can smoothly map the input value to the range between 0 and 1. In this formula, the input value is By adjusting the parameters β and γ, the smoothness and turning point position of the function can be controlled. Specifically, when the fractal dimension D(s,x,y) is higher than the threshold D threshold When the fractal dimension is below the threshold, the input value is positive, and the Sigmoid function output is close to 1. This means that in areas with higher ecosystem complexity, the values ​​of the preliminary MSAVI will be amplified, reflecting higher vegetation health. Conversely, when the fractal dimension is below the threshold, the input value is negative, the Sigmoid function output is close to 0, and the values ​​of the preliminary MSAVI will be compressed, reflecting lower vegetation health. The operation of subtracting 0.5 in the formula is used to adjust the output range of the Sigmoid function from 0 to 1 to -0.5 to 0.5. This step ensures that the center value of the adjustment factor is 0, avoiding excessive amplification or reduction of the preliminary MSAVI. At the same time, this processing method also makes the formula more mathematically symmetrical, which is easier to understand and calculate. Finally, the adjusted multispectral adaptive vegetation index MSAVI final It is obtained by multiplying the initial MSAVI by the adjustment factor. The formula is:

[0103]

[0104] This adjustment formula ensures that MSAVI can more accurately reflect the ecological restoration effect of the mining area. For example, in areas with good vegetation coverage, the fractal dimension is usually high, and the adjusted MSAVI value will also increase accordingly, thus accurately reflecting the health status of the area. Conversely, in areas where vegetation restoration is insufficient, the fractal dimension is low, and the adjusted MSAVI value will be compressed to reflect the actual restoration situation. In this way, the adjusted MSAVI not only retains the advantages of the preliminary MSAVI, but also combines the spatial information of the fractal dimension to improve the accuracy and reliability of the index. For the mine ecological restoration effectiveness evaluation system, this adjustment method can provide a more scientific and comprehensive vegetation restoration assessment, which helps decision makers to formulate and optimize restoration strategies. For example, when the adjusted MSAVI value of a certain area is significantly improved, it can be confirmed that the current restoration measures are effective and further promoted to other areas; while for those areas where the adjusted MSAVI value does not change much, it is necessary to re-evaluate and adjust the restoration strategy, which may require increased resource investment or the adoption of new technical means.

[0105] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that these specific embodiments are only illustrative, and those skilled in the art may omit, replace, and change the details of the above methods and systems in various ways without departing from the principles and essence of the present invention. For example, merging the above method steps so as to perform substantially the same functions in substantially the same manner to achieve substantially the same results is within the scope of the present invention. Therefore, the scope of the present invention is limited only by the appended claims.

Claims

1. A mine ecological restoration effectiveness evaluation system, characterized in that: The system comprises: a multi-source remote sensing data fusion part, a data processing and analysis part and an ecological restoration effect evaluation part; the multi-source remote sensing data fusion part is used to obtain multi-source remote sensing image data containing multiple source images of the target mine area, perform spatial detail enhancement and frequency domain fusion based on wavelet transform, and obtain fused remote sensing image data; the data processing and analysis part is used to perform multi-scale fractal analysis on the fused remote sensing image data to obtain the scale-related fractal dimension of the target mine area, and then calculate the preliminary multi-spectral adaptive vegetation index based on the reflectivity of each band in the fused remote sensing image data; adjust the preliminary multi-spectral adaptive vegetation index according to the fractal dimension to obtain the adjusted multi-spectral adaptive vegetation index; the ecological restoration effect evaluation part is used to establish a standard interval of the multi-spectral adaptive vegetation index for mine ecological restoration according to the relationship between the multi-spectral adaptive vegetation index and mine ecological restoration in historical data, each multi-spectral adaptive vegetation index standard interval corresponds to a degree of mine ecological restoration, and the degree of ecological restoration of the mine is obtained according to the multi-spectral adaptive vegetation index standard interval in which the adjusted multi-spectral adaptive vegetation index is located.

2. The mine ecological restoration effectiveness evaluation system according to claim 1, characterized in that: The multi-source remote sensing data fusion part includes: a data acquisition unit, which is used to acquire multi-source remote sensing image data including high-resolution panchromatic images and multispectral images when acquiring multi-source remote sensing image data of a target mining area containing multiple source images; a data processing unit, which is used to perform nonlinear enhancement on the high-frequency sub-bands of the high-resolution panchromatic image, perform PCA transformation on the multispectral image, and then perform non-subsampled contourlet transformation on the first principal component of the high-resolution panchromatic image and the multispectral image, and then perform adaptive fusion to obtain a fused intermediate result, and then use total variation regularization to denoise and edge-maintain the fused intermediate result to obtain fused remote sensing image data.

3. The mine ecological restoration effectiveness evaluation system according to claim 2, characterized in that: The formula for adaptive fusion is as follows: oh MS =1-h PAN ; Among them, F j,l is the fused coefficient; the subscript j indicates the decomposition level, and l indicates the directional subband; this coefficient is the weighted sum of the corresponding coefficients of the high-resolution panchromatic image and the multispectral image, representing the characteristics of the fused image at a specific scale and direction; It is the coefficient obtained after the high-resolution panchromatic image is transformed by non-subsampled contourlet transform, which represents the high-frequency detail information of the high-resolution panchromatic image in the jth layer and the lth direction; It is the coefficient obtained after the non-subsampled contourlet transform of the multispectral image, which represents the high-frequency detail information of the multispectral image in the jth layer and the lth direction; ω PAN is the weight assigned to the coefficients of the high-resolution full-color image; ω MS are the weights assigned to the multispectral image coefficients; is the variance of the high-resolution panchromatic image in the local window, which reflects the detail richness of the high-resolution panchromatic image in this area; It is the variance of the multispectral image in the local window, which reflects the detail richness of the multispectral image in this area; is the variance of the coefficient differences and is used to control the decay rate of the exponential term.

4. The mine ecological restoration effectiveness evaluation system according to claim 3, characterized in that: When using total variation regularization to denoise and preserve edges on the fused intermediate results, the objective function is: Among them, u is the fused remote sensing image data; p is the position variable, which is a two-dimensional variable containing the X-axis coordinate and the Y-axis coordinate; || is the absolute value operation; I fused is the fusion intermediate result; Ω is the image domain, which represents the area of ​​the entire fusion intermediate result; It is the first-order gradient of the fused remote sensing image data u, which is used to capture the edge information of the image; It is the second-order gradient of the image fusion remote sensing image data u, which is used to capture the curvature information of the image; is the penalty function of the gradient, This is a smooth approximation to the total variation, where ∈ is defined as a positive number less than 1; TV β (u) is the total anisotropic variation, defined as: in, is the first-order gradient of the fused remote sensing image data u in the X-axis direction; is the first-order gradient of the fused remote sensing image data u in the Y-axis direction.

5. The mine ecological restoration effectiveness evaluation system according to claim 4, characterized in that: In the data processing and analysis part, multi-scale fractal analysis is performed on the fused remote sensing image data to obtain the scale-related fractal dimension of the target mining area. The specific process includes: assuming (x, y) is the pixel coordinate in the fused remote sensing image data u, x is the X-axis coordinate, and y is the Y-axis coordinate; using non-subsampled contourlet transform to perform multi-scale decomposition on the fused remote sensing image data u: NSCT{u}={c J (x,y)}∪{d j,l (x,y):j∈[1,H],l∈[1,L j ]}; Among them, c J (x,y) is the low frequency subband, d j,l (x, y) is the directional subband, J is the number of decomposition levels, L j is the number of directions in the jth layer; j is the serial index; the local multifractal spectrum τ is calculated for each directional subband j,l (q,x,y): Where q is the multifractal moment, B ∈ (x,y) is a sphere with radius ∈ centered at (x,y); (x ′ ,y ′ ) is the pixel coordinate, x ′ is the X-axis coordinate; y ′ is the Y-axis coordinate; based on the local multifractal spectrum, the generalized Hurst index H(q,x,y) is calculated, and the multifractal spectrum and local singularity index are calculated using Legendre transform; then the scale-related fractal dimension is calculated based on the multifractal spectrum and local singularity index.

6. The mine ecological restoration effectiveness evaluation system according to claim 5, characterized in that: The generalized Hurst exponent is calculated based on the local multifractal spectrum using the following formula: Among them, H(q,x,y) is the generalized Hurst index; the multifractal spectrum and local singularity index are calculated using the Legendre transform through the following formula: f(α(q,x,y),x,y)=qα(q,x,y)-qH(q,x,y)+2; Among them, α(q,x,y) is the local singularity index; f(α,x,y) is the multifractal spectrum.

7. The mine ecological restoration effectiveness evaluation system according to claim 6, characterized in that: The scale-dependent fractal dimension D(s,x,y) is calculated from the multifractal spectrum and the local singularity index using the following formula: where s is the scale parameter and α0 is the reference local singularity index.

8. The mine ecological restoration effectiveness evaluation system according to claim 7, characterized in that: The preliminary multispectral adaptive vegetation index MSAVI is calculated based on the reflectance of each band in the fused remote sensing image data using the following formula: initial : Among them, α NIR is the reflectivity in the near-infrared band; α RED is the reflectivity of the red light band; α SWIR1 is the reflectivity of the short-wave infrared 1 band; α SWIR2 is the reflectance of the shortwave infrared 2 band; NDVI is the normalized vegetation index, which is defined as: β and γ are the first adjustment coefficient and the second adjustment coefficient respectively; w i is the weight of the i-th band; n is the total number of bands in the fused remote sensing image data; where λ i is the central wavelength of the ith band, λ NIR is the central wavelength of the near-infrared band; σ is the third adjustment coefficient.

9. The mine ecological restoration effectiveness evaluation system according to claim 8, characterized in that: Use the following formula to adjust the preliminary multispectral adaptive vegetation index according to the fractal dimension to obtain the adjusted multispectral adaptive vegetation index MSAVI final : Among them, D threshold is the fractal dimension threshold.

Images