Coal exploration area identification method, system and equipment

Abstract

The present application provides a method, system, and device for identifying coal exploration areas. The method first collects multiple remote sensing images of the target exploration area; then, semantic segmentation is performed on each remote sensing image to obtain the contour features of different surface objects within each remote sensing image; further, the semantic association relationships between different surface objects within each remote sensing image are determined; and then, based on the spectral reflectance characteristics of each remote sensing image and all the semantic association relationships, the recognition contribution of each remote sensing image is determined; then, the regional edge of coal distribution is extracted from all thermal infrared band remote sensing images using the temperature constraint of each thermal infrared band remote sensing image; and further, the credible exploration area of ​​coal distribution is determined based on the regional edge of coal distribution and the recognition contribution of each remote sensing image. The solution of the present application can reduce the impact of the reflectance characteristics of coal seam mineral components on the identification of potential mining areas, thereby improving the accuracy of identifying the distribution of coal exploration areas.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and more specifically, to a method, system and device for identifying coal exploration areas. Background Art

[0002] Image recognition uses artificial intelligence technology to automatically identify and classify objects, scenes, or activities by analyzing and processing information in images. In the coal mining industry, image recognition technology is widely used in mine monitoring, coal seam detection, equipment maintenance, and other fields. Through images taken by cameras or drones installed in the mine area, combined with deep learning and pattern recognition algorithms, the system can automatically identify changes in the mining environment, equipment failures, the distribution of coal seams, and potential safety hazards. This not only improves the production efficiency of coal mines, but also effectively reduces the safety risks of manual operations and promotes the intelligent development of coal mines.

[0003] Existing coal exploration area identification relies on remote sensing technology. Commonly used technologies include optical remote sensing, infrared remote sensing, radar remote sensing and lidar. By analyzing remote sensing data, the differences between coal and the surrounding environment can be identified. At the same time, thermal infrared remote sensing images can detect spontaneous combustion in coal mines or abnormal surface temperatures, helping to identify potential mining areas. However, coal seams are often accompanied by a variety of minerals, such as mudstone, sandstone, gypsum, etc. The reflective characteristics of these minerals may be very close to those of coal, making it difficult to effectively distinguish remote sensing images. Especially when using short-wave infrared bands and mid-infrared bands for mineral analysis, the similarity between mineral components may affect the accuracy of the analysis, resulting in the inability to accurately identify the distribution of coal exploration areas. Therefore, how to reduce the impact of the reflective characteristics of coal seam mineral components on the identification of potential mining areas, thereby improving the accuracy of identifying the distribution of coal exploration areas. Summary of the Invention

[0004] The present application provides a method, system and device for identifying coal exploration areas, which can reduce the influence of the reflectance characteristics of coal seam mineral components on the identification of potential mining areas, thereby improving the accuracy of identifying the distribution of coal exploration areas.

[0005] In a first aspect, the present application provides a method for identifying a coal exploration region, comprising the following steps:

[0006] Collect multiple remote sensing images of the target exploration area in different bands;

[0007] Perform semantic segmentation on each remote sensing image based on a preset image semantic segmentation model, and then obtain the contour features of different surface objects in each remote sensing image;

[0008] Determining semantic associations between different surface objects in each remote sensing image based on semantic differences and contour features of different surface objects, and determining recognition contributions of each remote sensing image in the exploration area recognition process based on spectral reflectance features of each remote sensing image in the same band and all semantic associations;

[0009] Acquire thermal infrared band remote sensing images in different time periods, and extract regional edges of coal distribution within the target exploration area from all thermal infrared band remote sensing images by using temperature constraints of each thermal infrared band remote sensing image;

[0010] The credible exploration area of ​​the coal distribution in the target exploration area is determined according to the regional edge of the coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process.

[0011] In some embodiments, semantic segmentation is performed on each remote sensing image based on a preset image semantic segmentation model, thereby obtaining contour features of different surface objects in each remote sensing image, specifically including:

[0012] Preprocessing all remote sensing images to obtain multiple preprocessed remote sensing images;

[0013] Initialize the image semantic segmentation model;

[0014] Segment each pre-processed remote sensing image according to the preset image semantic segmentation model to obtain pixel labels of different surface objects in each pre-processed remote sensing image;

[0015] Edge features are extracted from the pixel labels of different surface objects in each preprocessed remote sensing image to obtain the contour features of different surface objects in each remote sensing image.

[0016] In some embodiments, determining the semantic association relationship between different surface objects in each remote sensing image based on the semantic differences between different surface objects and the contour features of different surface objects specifically includes:

[0017] Selecting a remote sensing image as a selected remote sensing image;

[0018] Determine semantic differences between different surface objects within a selected remote sensing image;

[0019] Extract the semantic relevance between each surface object and coal in the selected remote sensing image based on a large-scale pre-trained language model;

[0020] Determine the semantic association relationship between different surface objects in the selected remote sensing image by selecting the semantic relevance between each surface object and coal, the semantic difference between different surface objects in the remote sensing image, and the contour features of different surface objects in the selected remote sensing image;

[0021] Continue to determine the semantic association relationships between different surface objects in the remaining remote sensing images.

[0022] In some embodiments, determining the recognition contribution of each remote sensing image in the exploration area recognition process based on the spectral reflectance characteristics of each remote sensing image in the same band and all semantic association relationships specifically includes:

[0023] Select remote sensing images in the same band from remote sensing images in all bands;

[0024] Determine the spectral difference between remote sensing images in the same band based on the spectral reflectance characteristics of all remote sensing images in the same band;

[0025] The correlation confidence value of each remote sensing image in the exploration area identification process is determined through the spectral differences and all semantic correlation relationships between the remote sensing images in all the same bands;

[0026] The recognition contribution of each remote sensing image in the exploration area recognition process is determined according to the associated confidence value of each remote sensing image in the exploration area recognition process.

[0027] In some embodiments, extracting the regional edge of coal distribution in the target exploration area from all thermal infrared band remote sensing images by using the temperature constraint of each thermal infrared band remote sensing image specifically includes:

[0028] The temperature constraint of each remote sensing image in the thermal infrared band within the same time period is determined according to the brightness temperature of all remote sensing images in the thermal infrared band within the same time period, and then the temperature constraint of each remote sensing image in the thermal infrared band within different time periods is obtained;

[0029] Based on the preset coal mine area edge detection model, the edge contour of the coal distribution area in each thermal infrared band remote sensing image is extracted;

[0030] Smoothing the edge contour of the coal distribution area in each thermal infrared band remote sensing image according to the temperature constraint of each remote sensing image in the thermal infrared band in different time periods, thereby obtaining the edge smooth contour of the coal distribution area in each thermal infrared band remote sensing image;

[0031] The smooth edge contours of the coal distribution areas in all thermal infrared band remote sensing images are fused to obtain the regional edge of the coal distribution in the target exploration area.

[0032] In some embodiments, determining a credible exploration area for coal distribution within the target exploration area based on the regional edge of coal distribution within the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process specifically includes:

[0033] Perform linear fitting on the recognition contribution of all remote sensing images in the exploration area recognition process to obtain the fitting curve of the recognition contribution;

[0034] A credible exploration area of ​​coal distribution in the target exploration area is determined according to the fitting curve of the recognition contribution and the regional edge of coal distribution in the target exploration area.

[0035] In some embodiments, the wavelength band includes a visible light band, a near infrared band, a short-wave infrared band, a thermal infrared band, and a mid-wave infrared band.

[0036] In a second aspect, the present application provides a coal exploration area identification system, comprising:

[0037] Acquisition module, used to collect multiple remote sensing images of the target exploration area in different bands;

[0038] A processing module is used to perform semantic segmentation on each remote sensing image based on a preset image semantic segmentation model, thereby obtaining contour features of different surface objects in each remote sensing image;

[0039] The processing module is further configured to determine semantic associations between different surface objects in each remote sensing image based on semantic differences between different surface objects and contour features of different surface objects, and to determine recognition contributions of each remote sensing image in the exploration area recognition process based on spectral reflectance features of each remote sensing image in the same band and all semantic associations;

[0040] The processing module is further used to obtain thermal infrared band remote sensing images in different time periods, and extract the regional edge of coal distribution in the target exploration area from all thermal infrared band remote sensing images through the temperature constraint of each thermal infrared band remote sensing image;

[0041] The execution module is used to determine a credible exploration area of ​​coal distribution in the target exploration area according to the regional edge of coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process.

[0042] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned coal exploration area identification method.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which implements the above-mentioned coal exploration area identification method when executed by a processor.

[0044] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0045] In the coal exploration area identification method, system and equipment provided in the present application, multiple remote sensing images of the target exploration area in different bands are first collected; semantic segmentation is performed on each remote sensing image based on a preset image semantic segmentation model, and then the contour features of different surface objects in each remote sensing image are obtained; the semantic association relationship between different surface objects in each remote sensing image is determined based on the semantic differences between different surface objects in each remote sensing image and the contour features of different surface objects, and the recognition contribution of each remote sensing image in the exploration area identification process is determined based on the spectral reflectance characteristics of each remote sensing image in the same band and all semantic association relationships; remote sensing images of thermal infrared bands in different time periods are obtained, and the regional edge of the coal distribution in the target exploration area is extracted from all thermal infrared band remote sensing images through the temperature constraint of each thermal infrared band remote sensing image; and a credible exploration area for coal distribution in the target exploration area is determined based on the regional edge of the coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area identification process.

[0046] It can be seen that in this application, the credible exploration area of ​​coal distribution in the target exploration area can be determined based on the regional edge of the coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area identification process; wherein, first, by collecting multiple remote sensing images of different bands, the collection of images of different bands not only provides different reflection characteristic information for the classification of ground objects; secondly, each remote sensing image is processed using a preset image semantic segmentation model to extract the contour features of different surface objects, and analyze their semantic associations based on the semantic differences of the surface objects. Through this step, the reflection features of coal and other ground objects can be effectively distinguished from the image, eliminating the interference of mineral composition on regional identification. Semantic segmentation not only improves the recognition accuracy, but also helps to avoid misjudgment caused by similar reflection characteristics of ore layers by distinguishing different ground objects, ensuring that the coal area can be accurately identified; then, on this basis, combined with the spectral reflectance features and semantic associations of each remote sensing image, the recognition contribution of each image in the coal exploration area identification process is calculated. This quantitative analysis method helps to measure the importance of different bands to coal area identification. The contribution of each remote sensing image is reasonably weighted to further optimize the precise positioning of the coal area. Through the comprehensive analysis of multi-band images, the recognition deviation that may be caused by differences in mineral reflection characteristics is reduced. In addition, by obtaining thermal infrared band remote sensing images of different time periods and extracting the edge of the target exploration area from them using temperature constraints, the boundary recognition accuracy of the coal area is further improved. The application of thermal infrared band remote sensing images helps to clearly distinguish the coal area from the surrounding objects, especially at night or when the temperature difference is large. It can more effectively identify the thermal characteristics of the coal area, thereby effectively enhancing the accuracy of the edge of the coal area and reducing the interference of thermal reflection errors on the recognition results. Finally, the regional edge of the target exploration area and the recognition contribution of each image are comprehensively analyzed to obtain the recognition credibility of the coal area. This comprehensive evaluation process ensures that the positioning results of the coal area have a high credibility, reduces the recognition error that may be caused by the reflection characteristics of the coal seam mineral composition, and improves the accuracy of the distribution of the coal exploration area. In summary, the scheme of the present application can reduce the impact of the reflection characteristics of the coal seam mineral composition on the identification of potential mining areas, thereby improving the accuracy of identifying the distribution of coal exploration areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is an exemplary flow chart of a method for identifying a coal exploration region according to some embodiments of the present application;

[0048] Figure 2 is a schematic diagram of a process for determining contour features according to some embodiments of the present application;

[0049] Figure 3 is a schematic diagram of a process for determining recognition contribution according to some embodiments of the present application;

[0050] Figure 4 is a schematic structural diagram of a coal exploration area identification system according to some embodiments of the present application;

[0051] Figure 5 It is a structural diagram of a computer device for implementing a method for identifying a coal exploration area according to some embodiments of the present application. DETAILED DESCRIPTION

[0052] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0053] refer to Figure 1 , which is an exemplary flow chart of a method for identifying a coal exploration region according to some embodiments of the present application. The method 100 for identifying a coal exploration region mainly includes the following steps:

[0054] In step 101, a plurality of remote sensing images of a target exploration area in different bands are collected.

[0055] In specific implementation, multiple remote sensing images of the target exploration area in different bands are collected through the remote sensing equipment carried by the UAV.

[0056] It should be noted that the wavelengths described in this application include visible light wavelengths, near infrared wavelengths, short-wave infrared wavelengths, thermal infrared wavelengths and medium-wave infrared wavelengths.

[0057] In step 102, semantic segmentation is performed on each remote sensing image based on a preset image semantic segmentation model, thereby obtaining contour features of different surface objects in each remote sensing image.

[0058] In some embodiments, reference Figure 2 As shown in FIG, this figure is a schematic diagram of the process of determining contour features in some embodiments of the present application. In this embodiment, semantic segmentation is performed on each remote sensing image based on a preset image semantic segmentation model, and the contour features of different surface objects in each remote sensing image are obtained by the following steps:

[0059] First, in step 1021, all remote sensing images are preprocessed to obtain a plurality of preprocessed remote sensing images;

[0060] Next, in step 1022, the image semantic segmentation model is initialized;

[0061] Then, in step 1023, each pre-processed remote sensing image is segmented according to a preset image semantic segmentation model to obtain pixel labels of different surface objects in each pre-processed remote sensing image;

[0062] Finally, in step 1024, edge features are extracted from the pixel labels of different surface objects in each pre-processed remote sensing image to obtain contour features of different surface objects in each remote sensing image.

[0063] It should be noted that the image semantic segmentation model in this application can adopt a semantic segmentation model (such as FCN, U-Net, DeepLabV3+ and other models, not limited here), and obtain training data by annotating different surface objects in historical remote sensing images. The semantic segmentation model after training is then used as the image semantic segmentation model to complete the initialization of the image semantic segmentation model, wherein the surface objects include: mountain fold areas, mountain fault areas, sedimentary basins, mountain fault lines, rivers, lakes, wetlands, vegetation, ore rock formations, soil, coal mine waste, coal blocks, thermal infrared anomaly areas, coal distribution areas and other different types.

[0064] In the specific implementation, first, all remote sensing images are preprocessed, where the preprocessing includes denoising (such as Gaussian blur denoising), normalization, contrast enhancement (such as contrast stretching) and cropping and scaling, and the remote sensing images obtained after preprocessing are all used as preprocessed remote sensing images; secondly, each preprocessed remote sensing image is input into the preset image semantic segmentation model, and each preprocessed remote sensing image is semantically segmented by the image semantic segmentation model to obtain different surface objects in each preprocessed remote sensing image, and then the image semantic segmentation model is used to output different surface objects in each preprocessed remote sensing image. , where the pixel label represents a vector consisting of the category to which the pixel point belongs; then, edge extraction is performed on the pixel labels of different surface objects in each preprocessed remote sensing image using an edge detection algorithm (such as Canny edge detection) to obtain edge contours of different surface objects in each preprocessed remote sensing image; further, Hu moments are calculated for the edge contours of different surface objects in each preprocessed remote sensing image, and the calculated values ​​are used as contour features of different surface objects in each preprocessed remote sensing image. Other methods may also be used in other embodiments, which will not be described in detail here.

[0065] It should be noted that the contour features described in this application represent the geometric features of the boundaries of surface objects in remote sensing images.

[0066] In step 103, the semantic association relationships between different surface objects in each remote sensing image are determined based on the semantic differences between different surface objects in each remote sensing image and the contour features of different surface objects. The recognition contribution of each remote sensing image in the exploration area recognition process is determined based on the spectral reflectance characteristics of each remote sensing image in the same band and all the semantic association relationships.

[0067] In some embodiments, determining the semantic association relationship between different surface objects in each remote sensing image based on the semantic differences between different surface objects and the contour features of different surface objects can be achieved by using the following steps:

[0068] Selecting a remote sensing image as a selected remote sensing image;

[0069] Determine semantic differences between different surface objects within a selected remote sensing image;

[0070] Extract the semantic relevance between each surface object and coal in the selected remote sensing image based on a large-scale pre-trained language model;

[0071] Determine the semantic association relationship between different surface objects in the selected remote sensing image by selecting the semantic relevance between each surface object and coal, the semantic difference between different surface objects in the remote sensing image, and the contour features of different surface objects in the selected remote sensing image;

[0072] Continue to determine the semantic association relationships between different surface objects in the remaining remote sensing images.

[0073] It should be noted that the large-scale pre-trained language model used in this application is the GPT-4 language model. In addition, it should be noted that the semantic difference described in this application represents the parameters that show semantic differences between surface objects with similar names in remote sensing images.

[0074] In the specific implementation, first, the word embedding technology (such as Word2Vec) is used to convert the names of different surface objects in the selected remote sensing image into vectors, and the obtained vectors are used as the name vectors of different surface objects in the selected remote sensing image, and then the Euclidean distance between the name vectors of every two surface objects in the selected remote sensing image is calculated, and then the smallest Euclidean distance among all Euclidean distances is used as the semantic difference between different surface objects in the selected remote sensing image; secondly, the name of coal is input into a large-scale pre-trained language model, and the keywords closest to the name of coal are extracted through the large-scale pre-trained language model, and the keywords are converted into The keyword vector is further calculated, and the cosine similarity between the keyword vector and the name vector of each surface object in the selected remote sensing image is used, and the obtained cosine similarities are used as the semantic relevance between each surface object in the selected remote sensing image and the coal; then, the contour features of each surface object in the selected remote sensing image are multiplied by the semantic relevance between each surface object in the selected remote sensing image and the coal, and then all the multiplied values ​​are summed up, and the summed value is further divided by the semantic difference between different surface objects in the selected remote sensing image, and the divided value is used as the semantic association relationship between different surface objects in the selected remote sensing image.

[0075] It should be noted that the semantic relevance described in this application represents the strength of association between surface objects and coal in remote sensing images at the semantic level. In addition, the semantic association relationship represents the mutual correlation characteristics of the semantics of each surface object in the remote sensing image in the process of identifying coal exploration areas. Through the semantic association relationship, it is possible to identify which surface objects have a strong semantic correlation with the coal exploration area, thereby reducing the interference of irrelevant objects (such as limestone, desert, etc.) and avoiding misidentification as potential coal mining areas.

[0076] In some embodiments, reference Figure 3 As shown in FIG, this figure is a schematic diagram of the process of determining the recognition contribution in some embodiments of the present application. In this embodiment, the recognition contribution of each remote sensing image in the exploration area recognition process is determined based on the spectral reflectance characteristics and all semantic associations of each remote sensing image in the same band. The following steps can be used to achieve this:

[0077] Select remote sensing images in the same band from remote sensing images in all bands;

[0078] Determine the spectral difference between remote sensing images in the same band based on the spectral reflectance characteristics of all remote sensing images in the same band;

[0079] The correlation confidence value of each remote sensing image in the exploration area identification process is determined through the spectral differences and all semantic correlation relationships between the remote sensing images in all the same bands;

[0080] The recognition contribution of each remote sensing image in the exploration area recognition process is determined according to the associated confidence value of each remote sensing image in the exploration area recognition process.

[0081] It should be noted that the spectral reflectance characteristics described in this application represent the distribution characteristics of electromagnetic wave reflection of surface objects in the remote sensing image in a specific band. The spectral reflectance characteristics of the remote sensing image in this application can be described by the reflectivity of the specific band.

[0082] In the specific implementation, first, the spectral reflectance characteristics of all remote sensing images in the same band are differentially processed, and then the values ​​obtained by all differences are summed, and the summed value is used as the spectral difference between each remote sensing image in the same band, and the spectral difference represents the degree of difference between the spectral reflectance characteristics of each remote sensing image in the same band; secondly, the spectral difference between each remote sensing image in the same band is calculated with a negative exponential function with the natural logarithm e as the base, and then the values ​​obtained after calculating the negative exponential function with the natural logarithm e as the base are multiplied by the semantic association relationship between different surface objects in each remote sensing image in the same band, and the multiplied values ​​are used as the semantic association relationship between different surface objects in the same band. The associated confidence value of each remote sensing image in the exploration area identification process is obtained by performing the same processing on the remote sensing images in all bands, thereby obtaining the associated confidence value of each remote sensing image in the exploration area identification process, wherein the associated confidence value represents an indicator for evaluating the degree of credibility of the association between the remote sensing image and the coal distribution; then, the associated confidence value of each remote sensing image in the exploration area identification process is divided by the sum of the associated confidence values ​​of all remote sensing images in the exploration area identification process, and the values ​​obtained by the division are all used as the recognition contribution of each remote sensing image in the exploration area identification process. In other embodiments, other methods can also be used to achieve this, which will not be repeated here.

[0083] It should be noted that the recognition contribution described in this application represents the degree of influence of remote sensing images on the recognition results of coal distribution areas during the identification process of coal exploration areas. The greater the recognition contribution, the higher the degree of influence of remote sensing images on the recognition results of coal distribution areas during the identification process of coal exploration areas, and vice versa. The recognition contribution can reduce the interference of the reflection characteristics of mineral components on the exploration results, thereby improving the recognition accuracy of coal areas.

[0084] In step 104, remote sensing images of thermal infrared bands in different time periods are acquired, and the regional edge of coal distribution in the target exploration area is extracted from all thermal infrared band remote sensing images by temperature constraints of each thermal infrared band remote sensing image.

[0085] In the specific implementation, multiple remote sensing images of the thermal infrared band are collected during the daytime (10:00-16:00) and nighttime (18:00-02:00) in summer and winter respectively. It should be noted that in this application, remote sensing images need to be collected at different time points at the same location.

[0086] In some embodiments, extracting the regional edge of coal distribution in the target exploration area from all thermal infrared band remote sensing images by using the temperature constraint of each thermal infrared band remote sensing image can be achieved by the following steps:

[0087] The temperature constraint of each remote sensing image in the thermal infrared band within the same time period is determined according to the brightness temperature of all remote sensing images in the thermal infrared band within the same time period, and then the temperature constraint of each remote sensing image in the thermal infrared band within different time periods is obtained;

[0088] Based on the preset coal mine area edge detection model, the edge contour of the coal distribution area in each thermal infrared band remote sensing image is extracted;

[0089] Smoothing the edge contour of the coal distribution area in each thermal infrared band remote sensing image according to the temperature constraint of each remote sensing image in the thermal infrared band in different time periods, thereby obtaining the edge smooth contour of the coal distribution area in each thermal infrared band remote sensing image;

[0090] The smooth edge contours of the coal distribution areas in all thermal infrared band remote sensing images are fused to obtain the regional edge of the coal distribution in the target exploration area.

[0091] It should be noted that the temperature constraint described in this application represents the parameter value that limits the temperature change of the coal distribution area in the thermal infrared band remote sensing image. In addition, it should be noted that the coal mine area edge detection model described in this application adopts the U-Net deep learning model, which can be trained through multiple infrared band remote sensing images marked with coal exploration areas. Among them, the coal mine area edge detection model can output the edge contour of the coal distribution area in each infrared band remote sensing image.

[0092] In the specific implementation, first, the radiation transfer model (such as Moderate Resolution Atmospheric Transmission, MODTRAN) is used to convert the radiation brightness of all remote sensing images in the thermal infrared band within the same time period into brightness temperature, so as to obtain the brightness temperature of all remote sensing images in the thermal infrared band within the same time period, wherein the pixel value of the thermal infrared band remote sensing image represents the radiation brightness of the surface, and the maximum brightness temperature and the minimum brightness temperature are selected from the brightness temperatures of all remote sensing images in the thermal infrared band within the same time period, and the difference between the maximum brightness temperature and the minimum brightness temperature is used as the temperature constraint of each remote sensing image in the thermal infrared band within the same time period, thereby obtaining the temperature constraint of each remote sensing image in the thermal infrared band within different time periods; secondly, each thermal infrared band remote sensing image is input into the preset coal mine area edge detection model, and the coal mine area edge is detected. The output result of the detection model is used as the edge contour of the coal distribution area in each thermal infrared band remote sensing image; then, the edge contour of the coal distribution area in each thermal infrared band remote sensing image is smoothed by using a Gaussian filtering algorithm, thereby obtaining the edge smooth contour of the coal distribution area in each thermal infrared band remote sensing image, wherein, when processing each thermal infrared band remote sensing image, the standard deviation of the Gaussian filtering algorithm is set to the quotient between the average brightness of the thermal infrared band remote sensing image and the temperature constraint of the thermal infrared band remote sensing image; finally, OpenCV is used to perform a logical AND operation on the edge smooth contours of the coal distribution areas in all thermal infrared band remote sensing images, and the result obtained after the logical AND operation is used as the regional edge of the coal distribution in the target exploration area. In other embodiments, other methods can also be used to achieve this, which will not be repeated here.

[0093] It should be noted that the edge smoothing contour described in this application represents the contour obtained after smoothing the edge contour of the coal distribution area in the thermal infrared band remote sensing image; in addition, it should also be noted that the area edge described in this application represents the edge distribution of the coal area in the image of the target exploration area.

[0094] In step 105 , a credible exploration area of ​​coal distribution in the target exploration area is determined based on the regional edge of coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process.

[0095] In some embodiments, determining a credible exploration area for coal distribution within the target exploration area based on the regional edge of coal distribution within the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process can be achieved by the following steps:

[0096] Perform linear fitting on the recognition contribution of all remote sensing images in the exploration area recognition process to obtain the fitting curve of the recognition contribution;

[0097] A credible exploration area of ​​coal distribution in the target exploration area is determined according to the fitting curve of the recognition contribution and the regional edge of coal distribution in the target exploration area.

[0098] In the specific implementation, first, the existing linear fitting algorithm (such as the least squares support vector machine algorithm) is used to perform linear fitting on the recognition contribution of all remote sensing images in the process of exploration area recognition, and the curve obtained by fitting is used as the fitting curve of the recognition contribution, wherein each value on the fitting curve is used as the recognition contribution fitting value, and each recognition contribution fitting value corresponds to an recognition contribution, and each recognition contribution corresponds to a remote sensing image; secondly, all remote sensing images of thermal infrared bands are screened out from the remote sensing images of different bands obtained in step 101, and all remote sensing images of thermal infrared bands are used as contributing remote sensing images, and the recognition contribution fitting value corresponding to each contributing remote sensing image is screened out from the fitting curve of the recognition contribution (wherein, each contributing remote sensing image corresponds to a recognition contribution). Identification contribution, each identification contribution corresponds to an identification contribution fitting value, that is, each contribution remote sensing image corresponds to an identification contribution fitting value on the fitting curve). For each identified contribution fitting value screened out, the identification contribution corresponding to the identification contribution fitting value is subtracted from the identification contribution fitting value, and then the absolute value of the subtracted value is taken, and the value obtained after taking the absolute value is used as the edge adjustment factor, and then multiple edge adjustment factors are obtained. All edge adjustment factors are further summed, and the summed value is used as the scaling factor of the regional edge of the coal distribution in the target exploration area. OpenCV is then used to scale the regional edge of the coal distribution in the target exploration area, and the area obtained after the scaling process is used as the credible exploration area of ​​the coal distribution in the target exploration area.

[0099] It should be noted that the credible exploration area mentioned in this application refers to an area within the target exploration area where the coal distribution is more credible.

[0100] In addition, in another aspect of the present application, in some embodiments, the present application provides a coal exploration area identification system, referring to Figure 4 , which is a schematic diagram of the structure of a coal exploration region identification system according to some embodiments of the present application. The coal exploration region identification system 400 includes: a collection module 401, a processing module 402, and an execution module 403, which are described as follows:

[0101] Acquisition module 401, in this application, acquisition module 401 is mainly used to acquire multiple remote sensing images of the target exploration area in different bands;

[0102] Processing module 402, in this application, is used to perform semantic segmentation on each remote sensing image based on a preset image semantic segmentation model, thereby obtaining contour features of different surface objects in each remote sensing image;

[0103] It should be noted that the processing module 402 in the present application is further configured to determine the semantic association relationships between different surface objects in each remote sensing image based on the semantic differences between different surface objects and the contour features of different surface objects, and to determine the recognition contribution of each remote sensing image in the exploration area recognition process based on the spectral reflectance features of each remote sensing image in the same band and all the semantic association relationships;

[0104] In addition, the processing module 402 in the present application is further used to obtain thermal infrared band remote sensing images in different time periods, and extract the regional edge of coal distribution in the target exploration area from all thermal infrared band remote sensing images through the temperature constraint of each thermal infrared band remote sensing image;

[0105] Execution module 403, in this application, execution module 403 is mainly used to determine the credible exploration area of ​​coal distribution in the target exploration area based on the regional edge of coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area identification process.

[0106] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned coal exploration area identification method.

[0107] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a method for identifying a coal exploration area according to some embodiments of the present application. The method for identifying a coal exploration area in the above embodiment can be performed by Figure 5 The computer device 500 shown in FIG. 5 is implemented as shown in FIG. 5 . The computer device 500 includes at least one processor 501 , a communication bus 502 , a memory 503 , and at least one communication interface 504 .

[0108] The processor 501 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of the coal exploration region identification method in the present application.

[0109] The communication bus 502 may be used to transmit information between the aforementioned components.

[0110] The memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory 503 may be independent and connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0111] The memory 503 is used to store program code for executing the solution of the present application, and is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The method described in the above method embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0112] The communication interface 504 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0113] In a specific implementation, as an example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0114] The aforementioned computer device can be a general-purpose computer device or a dedicated computer device. In a specific implementation, the computer device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer device.

[0115] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned coal exploration area identification method.

[0116] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0117] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for identifying a coal exploration area, characterized in that: The steps include: Collect multiple remote sensing images of the target exploration area in different bands; Perform semantic segmentation on each remote sensing image based on a preset image semantic segmentation model, and then obtain the contour features of different surface objects in each remote sensing image; Determining semantic associations between different surface objects in each remote sensing image based on semantic differences and contour features of different surface objects, and determining recognition contributions of each remote sensing image in the exploration area recognition process based on spectral reflectance features of each remote sensing image in the same band and all semantic associations; Acquire thermal infrared band remote sensing images in different time periods, and extract regional edges of coal distribution within the target exploration area from all thermal infrared band remote sensing images by using temperature constraints of each thermal infrared band remote sensing image; Determining a credible exploration area for coal distribution within the target exploration area based on the regional edge of coal distribution within the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process; The determining of the semantic association relationship between different surface objects in each remote sensing image based on the semantic differences between different surface objects and the contour features of different surface objects specifically includes: Selecting a remote sensing image as a selected remote sensing image; Determine semantic differences between different surface objects within a selected remote sensing image; Extract the semantic relevance between each surface object and coal in the selected remote sensing image based on a large-scale pre-trained language model; Determine the semantic association relationship between different surface objects in the selected remote sensing image by selecting the semantic relevance between each surface object and coal, the semantic difference between different surface objects in the remote sensing image, and the contour features of different surface objects in the selected remote sensing image; Continue to determine the semantic association relationships between different surface objects in the remaining remote sensing images.

2. The method according to claim 1, wherein Based on the preset image semantic segmentation model, each remote sensing image is semantically segmented, and the contour features of different surface objects in each remote sensing image are obtained, including: Preprocessing all remote sensing images to obtain multiple preprocessed remote sensing images; Initialize the image semantic segmentation model; Segment each pre-processed remote sensing image according to the preset image semantic segmentation model to obtain pixel labels of different surface objects in each pre-processed remote sensing image; Edge features are extracted from the pixel labels of different surface objects in each preprocessed remote sensing image to obtain the contour features of different surface objects in each remote sensing image.

3. The method according to claim 1, wherein The recognition contribution of each remote sensing image in the exploration area recognition process is determined based on the spectral reflectance characteristics and all semantic associations of each remote sensing image in the same band. Specifically, the following are included: Select remote sensing images in the same band from remote sensing images in all bands; Determine the spectral difference between remote sensing images in the same band based on the spectral reflectance characteristics of all remote sensing images in the same band; The correlation confidence value of each remote sensing image in the exploration area identification process is determined through the spectral differences and all semantic correlation relationships between the remote sensing images in all the same bands; The recognition contribution of each remote sensing image in the exploration area recognition process is determined according to the associated confidence value of each remote sensing image in the exploration area recognition process.

4. The method according to claim 1, wherein Extracting the regional edge of coal distribution in the target exploration area from all thermal infrared band remote sensing images by temperature constraint of each thermal infrared band remote sensing image specifically includes: The temperature constraint of each remote sensing image in the thermal infrared band within the same time period is determined according to the brightness temperature of all remote sensing images in the thermal infrared band within the same time period, and then the temperature constraint of each remote sensing image in the thermal infrared band within different time periods is obtained; Based on the preset coal mine area edge detection model, the edge contour of the coal distribution area in each thermal infrared band remote sensing image is extracted; Smoothing the edge contour of the coal distribution area in each thermal infrared band remote sensing image according to the temperature constraint of each remote sensing image in the thermal infrared band in different time periods, thereby obtaining the edge smooth contour of the coal distribution area in each thermal infrared band remote sensing image; The smooth edge contours of the coal distribution areas in all thermal infrared band remote sensing images are fused to obtain the regional edge of the coal distribution in the target exploration area.

5. The method according to claim 1, wherein Determining the credible exploration area of ​​coal distribution in the target exploration area based on the regional edge of coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process specifically includes: Perform linear fitting on the recognition contribution of all remote sensing images in the exploration area recognition process to obtain the fitting curve of the recognition contribution; A credible exploration area of ​​coal distribution in the target exploration area is determined according to the fitting curve of the recognition contribution and the regional edge of the coal distribution in the target exploration area.

6. The method according to claim 1, wherein The wavebands include visible light waveband, near infrared waveband, short-wave infrared waveband, thermal infrared waveband and medium-wave infrared waveband.

7. A coal exploration area identification system, which uses the method according to any one of claims 1 to 6 to identify coal exploration areas, characterized in that: The system includes: Acquisition module, used to collect multiple remote sensing images of the target exploration area in different bands; A processing module is used to perform semantic segmentation on each remote sensing image based on a preset image semantic segmentation model, thereby obtaining contour features of different surface objects in each remote sensing image; The processing module is further configured to determine semantic associations between different surface objects in each remote sensing image based on semantic differences between different surface objects and contour features of different surface objects, and to determine recognition contributions of each remote sensing image in the exploration area recognition process based on spectral reflectance features of each remote sensing image in the same band and all semantic associations; The processing module is further used to obtain thermal infrared band remote sensing images in different time periods, and extract the regional edge of coal distribution in the target exploration area from all thermal infrared band remote sensing images through the temperature constraint of each thermal infrared band remote sensing image; The execution module is used to determine a credible exploration area of ​​coal distribution in the target exploration area according to the regional edge of coal distribution in the target exploration area and the recognition contribution of each remote sensing image in the exploration area recognition process.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method for identifying a coal exploration area according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying a coal exploration area according to any one of claims 1 to 6 is implemented.

Images