A Remote Sensing Identification Method for Ground Fissures in Complex Mining Areas

Abstract

The present invention provides a method for remotely sensing and identifying ground fissures in complex mining areas, including: filtering non-shadow areas based on a sliding window, brightening the shadows in the mining area based on HSV color compensation to eliminate the interference of solar shadows on the identification of ground fissures; filtering ground fissure noise based on ground fissure evaluation indicators of linear index and shape index to identify initial ground fissures; combining morphological processing and regional connectivity analysis to establish a comprehensive evaluation and determination mechanism to accurately restore the true shape of ground fissures hierarchically and multi-scale; based on multi-spatial scale threshold segmentation iteration, considering the length, end trend, inter-domain distance and angle of the connected domain, performing hierarchical threshold growth, and combining the automatic extraction mechanism to eliminate small noises to complete the accurate identification of ground fissures. The present invention improves the accuracy of crack extraction in complex mining areas and provides a new technical support for the identification of ground fissures in complex mining areas.

Description

Technical Field

[0001] The present invention relates to the technical field of extraction of ground fissures in complex mining areas, and particularly relates to a method for remotely sensing and identifying ground fissures in complex mining areas. Background Art

[0002] The continuous exploitation of underground coal resources will lead to a series of geological environment problems such as surface subsidence in mining areas and ground fissures generated under the action of external forces. The above problems seriously affect ground buildings, land production capacity, and the safety of the lives and property of the surrounding people. Therefore, effective identification of ground fissures in mining areas has important theoretical and practical significance for ensuring national life and property safety, and the governance and restoration of green mines.

[0003] However, traditional on-site detection has relatively high costs, low efficiency, and it is difficult to obtain fine features of ground fissures; using satellite remote sensing data for ground fissure detection is affected by resolution and timeliness, and only large-width ground fissures can be identified; in recent years, with the rapid development of unmanned aerial vehicle (UAV) and airborne light detection and ranging (LiDAR) technologies, their application in mine ecological restoration has been widely used. UAV remote sensing technology can obtain various remote sensing data such as three-dimensional point clouds, digital surface models (DSM), and digital orthophoto maps (DOM) that clearly show ground fissure features, with low costs, high precision, and high efficiency, which reflects the superiority of UAV remote sensing technology in ground fissure identification. However, due to the easy influence of complex terrain and noisy backgrounds during the extraction of ground fissures in mining areas, only manual visual interpretation is time-consuming and laborious and prone to omissions, and digital image processing technology, machine learning algorithms, etc. are often needed to achieve the automatic extraction of ground fissures in complex mining areas.

[0004] At present, automatic extraction of fissures based on digital image processing technology is one of the most commonly used methods, and a large number of achievements have been made in the extraction of single-background fissures such as concrete roads, buried pipelines, and house walls. For mining areas with complex surface environments and large terrain undulations, relying solely on two-dimensional UAV images for automatic extraction of ground fissures is relatively limited. There are mainly background noises such as shrubs, snow, and lighting shadows that affect the accuracy of ground fissure extraction. With the continuous development of computer vision technology, automatic identification of fissures based on machine learning algorithms has become the research focus of many scholars. For example, convolutional neural networks (CNNs) can effectively capture the grid-like topological structure of images and better identify fine fissures without being affected by noise. However, automatic identification of fissures requires a large amount of labeled data, and the accuracy of deep learning results is greatly affected by the accuracy of labels, which has certain limitations. Summary of the Invention

[0005] The object of the present invention is: aiming at the deficiencies in the above background art, to provide a solution that can further improve the accuracy of identifying ground fissures in complex mining areas.

[0006] To achieve the above object, the present invention provides a remote sensing identification method for ground fissures in complex mining areas, comprising the following steps:

[0007] S1, performing non-shadow area filtering based on a sliding window, brightening the mining area shadows based on HSV color compensation, and eliminating the interference of solar shadows on the identification of ground fissures;

[0008] S2, filtering out ground fissure noise based on the ground fissure evaluation indexes of the linear index and the shape index, and identifying the initial ground fissures;

[0009] S3, combining morphological processing and regional connectivity analysis, establishing a comprehensive evaluation and determination mechanism, and accurately restoring the true shape of the ground fissures hierarchically and multi-scale;

[0010] S4, based on multi-spatial scale threshold segmentation iteration, considering the length, end trend, inter-domain distance and angle of the connected domain, performing hierarchical threshold growth, and combining the automatic extraction mechanism to eliminate small noises to complete the accurate identification of the ground fissures.

[0011] Further, S1 includes the following sub-steps:

[0012] S11, setting the size of the sliding window, counting the number of pixels in each window when the sliding window is gradually moved, and suppressing small-scale noises according to the morphological characteristics of the non-shadow area to retain large shadow areas;

[0013] S12, performing brightening of the mining area shadows based on HSV color compensation for the shadow areas that meet the conditions, using the V channel in the HSV space for shadow brightening, and then locally filtering the H and S channels to make the color effect of the shadow area closer to the real color.

[0014] Further, S11 is represented by the following formula:

[0015] ;

[0016] where, is the retained pixel value, is the pixel value of the input image, is the number of black pixels within, is the empirical threshold, when the above conditions are met, the pixels of are covered with white, the black pixel value is 0, and the white pixel value is 255, is specifically defined as:

[0017] ;

[0018] where, represents centered on with a size of The sliding window, represents the sliding window for each pixel point, is an indicator function.

[0019] Furthermore, the linear exponent in S2 is given by which is expressed as:

[0020] ;

[0021] wherein, and respectively represent the length and width of the minimum circumscribed rectangle of the connected domain where the ground fissure is located. The connected domain is the image area composed of the points of the pixels identified as ground fissures in the image;

[0022] The shape exponent is given by which is expressed as:

[0023] ;

[0024] wherein, represents the area of the circumscribed circle of the minimum circumscribed rectangle of the connected domain where the ground fissure is located.

[0025] Furthermore, in S3, the continuity assumption is set as follows: is the gray level of the background pixel, is the average gray value of the initial ground fissure pixel. If is satisfied, this pixel is determined as a ground fissure object;

[0026] If the above conditions are not met, the following linear assumption is executed: Set a ground fissure compensation template that satisfies the ground fissure relationship. If the determined pixel matches one of the defined templates, then the condition is further checked, where , are thresholds. The threshold > threshold . If satisfied, the background pixel is classified as an initial ground fissure pixel.

[0027] Furthermore, in S4, starting from each initial pixel of the ground fissure that satisfies the linear and length conditions, the ground fissure pixels are traced along the main direction of the connected domain, and the last bright pixel endpoint traced is defined as the seed point;

[0028] Subsequently, starting from the seed point, a search is performed and the Bresenham algorithm is used for growth to achieve the gap connection of the ground fissure pixels. The search conditions include the radius of the search area, the angle and the length of the connected domain where the ground fissure is located. The ground fissure extraction condition includes the length of the ground fissure after gap connection.

[0029] Further, for the search conditions,

[0030] ;

[0031] ;

[0032] ;

[0033] ;

[0034] Among them, , , respectively represent the initial constraint values of the radius, length, and angle of the search area, is the condition for the extraction length of ground fissures, , , are all iteration thresholds, is the iteration termination condition, represents the number of iterations.

[0035] The above solution of the present invention has the following beneficial effects:

[0036] The remote sensing identification method for ground fissures in complex mining areas provided by the present invention, on the one hand, brightens the mining area shadows, compensates the hue based on the HSV hue difference between the shadow area and the real image, and excludes the interference of solar shadows on the extraction of ground fissures; on the other hand, two ground fissure evaluation indicators are proposed and combined with connected region analysis to filter out noise, the true crack morphology is restored based on crack morphology processing under the assumptions of continuity and linearity, multi-spatial scale threshold segmentation iteration is considered, threshold hierarchical growth is carried out considering the length of the connected domain, the end orientation, and the distance and angle between connected domains, and automatic extraction is set, realizing noise elimination and complete identification of ground fissures, providing a new technical support for the identification of ground fissures in complex mining areas;

[0037] Other beneficial effects of the present invention will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is the flow chart of the method steps of the present invention;

[0039] Figure 2 is the schematic diagram of the accuracy result of the identification of ground fissures in complex mining areas in the specific case of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0040] The following describes the embodiments of the present disclosure through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope of protection of the present disclosure.

[0041] It should be noted that the following describes various aspects of embodiments within the scope of the appended claims. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement a device and / or practice a method. Additionally, this device and / or this method can be implemented using other structures and / or functionality in addition to one or more of the aspects described herein.

[0042] It also should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present disclosure in a schematic manner. The diagrams only show the components related to the present disclosure, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and proportion of each component in its actual implementation can be an arbitrary change, and the component layout type may also be more complex. Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0043] As Figure 1 shown, an embodiment of the present invention provides a method for remote sensing identification of ground fissures in complex mining areas, which specifically includes the following steps:

[0044] S1, perform non-shadow area filtering based on a sliding window, brighten the mining area shadows based on HSV color compensation, and exclude the interference of solar shadows on the identification of ground fissures.

[0045] This step specifically includes the following sub-steps:

[0046] S11. Set a certain sliding window size. When gradually sliding the window, count the number of pixels in each window, and effectively suppress small-scale noise according to the morphological characteristics of the non-shadow area to retain large shadow areas. The specific expression is as follows:

[0047] ;

[0048] Among them, is the retained pixel value, is the pixel value of the input image, is the number of black pixels within, is the empirical threshold. When the above conditions are met, cover the pixels of with white. Among them, the black pixel value is 0, and the white pixel value is 255. Specifically defined as:

[0049] ;

[0050] Among them, represents a sliding window centered on with a size of , represents each pixel point of the sliding window , is the indicator function.

[0051] For example, in one specific implementation of this embodiment, the sliding window size can be set to 15, and the number of black pixels can be set to 65.

[0052] S12. After completing the non-shadow area filtering, perform mine area shadow brightening based on HSV color compensation for the shadow areas that meet the conditions. Specifically, use the V channel in the HSV space for shadow brightening, and then locally filter the H and S channels to make the color effect of the shadow area closer to the real color.

[0053] S2. Based on the ground fissure evaluation index of the linear index and the shape index, filter out the ground fissure noise, and then identify the initial ground fissures.

[0054] In this step, the linear index is represented by , and the specific expression is as follows:

[0055] ;

[0056] Among them, and respectively represent the length and width of the minimum circumscribed rectangle of the connected domain where the ground fissure is located. The connected domain refers to the image area composed of the points of the pixels identified as ground fissures in the image.

[0057] The shape index is represented by and the specific expression is as follows:

[0058] ;

[0059] where represents the area of the circumscribed circle of the minimum circumscribed rectangle of the connected domain where the ground fissure is located.

[0060] It should be noted that the larger the linear index, the more obvious the linear characteristics it presents, and it is judged as a ground fissure; the smaller the linear index, the more obvious the blocky characteristics it presents, and it is judged as noise; the smaller the shape index, the closer the area is to being linear, which means that this area is very likely to be a longitudinal or transverse ground fissure.

[0061] The area of the ground fissure region after preliminary segmentation processing is relatively large compared to small speckle noise. By combining the area size with the linear index and shape index of the ground fissure and setting a certain threshold, linear ground fissures can be effectively distinguished from blocky and small-area noise, facilitating more accurate identification of ground fissures in the subsequent process. Therefore, in this embodiment, the object pixels identified in this step are called initial ground fissures.

[0062] S3. Combine morphological processing and regional connectivity analysis to establish a comprehensive evaluation and determination mechanism to accurately restore the true shape of the ground fissure at different levels and multi-scales.

[0063] In this step, a continuity hypothesis is set: is the gray level of the background pixel, is the average gray value of the initial ground fissure pixel. If is satisfied, this pixel is determined as a ground fissure object.

[0064] If the above conditions are not met, the following linear hypothesis is executed to accurately restore the true shape of the ground fissure at different levels and multi-scales: Set a ground fissure compensation template that satisfies the ground fissure relationship. If the determined pixel matches one of the defined templates, then further check the condition where , are thresholds, and the threshold > threshold . If this condition is satisfied, the background pixel is classified as an initial ground fissure pixel.

[0065] S4. Based on multi-spatial scale threshold segmentation iteration, considering the length, end orientation, and inter-domain distance and angle of the connected domain, perform hierarchical threshold growth, and combine the automatic extraction mechanism to eliminate small noise to complete the accurate identification of ground fissures.

[0066] It should be noted that the multi - spatial - scale threshold segmentation iteration is mainly to solve the problem of incomplete filtering of fine noise. It is necessary to find the endpoints of the ground fissures as seed points. The specific iteration method is to start from the initial pixels of each ground fissure that meets the linear and length conditions, track the ground fissure pixels along the main direction of the connected domain, and finally the bright pixel endpoints tracked are defined as seed points.

[0067] Subsequently, starting from the seed points, search is carried out and the Bresenham algorithm is used for growth to achieve the gap connection of the ground fissure pixels. The search conditions are determined by the radius of the search area, the angle and the length of the connected domain where the ground fissure is located. These three factors jointly determine the extraction conditions of the ground fissures, which are determined by the length of the ground fissures after gap connection. It should be noted that the Bresenham algorithm is a classic algorithm in digital image processing used to generate straight lines or arcs, and is widely used in graphics rendering and path tracking. The Bresenham algorithm growth is used to accurately track and connect the pixels of the ground fissures, solving the problem of ground fissure gap connection. Its core advantage lies in the efficient pixel generation method, which can accurately "grow" or "fill" the ground fissure path along the target direction under certain search conditions, and finally complete the accurate extraction of the ground fissures.

[0068] For the search conditions, set

[0069] ;

[0070] ;

[0071] ;

[0072] ;

[0073] Among them, , , respectively represent the initial constraint values of the radius, length and angle of the search area, is the length condition for ground fissure extraction, , , are all iteration thresholds, is the iteration termination condition, represents the number of iterations.

[0074] It should be noted that in practical applications, the above threshold should be set according to the actual situation, continuously expanding the growth search range and refining the ground fissure extraction range until the extraction size does not meet the definition of ground fissures, at which point the growth and extraction iteration stop, solving the problem of incomplete filtering of the above-mentioned small noises. This not only effectively eliminates small noises in complex mining areas but also ensures the complete extraction of large-scale ground fissures, realizing the automation of multi-spatial scale threshold segmentation iteration.

[0075] For example, in one specific implementation of this embodiment, the iteration threshold can be set to 5, 、 、 are respectively set to 60, 220, and 30.

[0076] As described above, the remote sensing identification method for ground fissures in complex mining areas provided by this embodiment, on the one hand, brightens the mining area shadows, performs hue compensation based on the HSV hue difference between the shadow area and the real image, and excludes the interference of solar shadows on ground fissure extraction; on the other hand, proposes two ground fissure evaluation indicators and combines connected region analysis to filter out noises, restores the true crack morphology based on crack morphology processing based on continuity and linear assumptions, performs threshold hierarchical growth considering the length of the connected domain, the end trend, and the distance and angle between connected domains based on multi-spatial scale threshold segmentation iteration, and sets automatic extraction, realizing noise elimination and complete identification of ground fissures, providing a new technical support for ground fissure identification in complex mining areas.

[0077] The feasibility of this method is further verified through the following specific cases. Taking a mining area in a certain place as a demonstration area, unmanned aerial vehicle (UAV) remote sensing image data covering the mining area in February 2023 is selected. To demonstrate the advantages of this method, the traditional mining area ground fissure extraction method based on digital image processing technology is compared with this method in terms of accuracy, integrity, and kappa coefficient (where the kappa coefficient is an index for consistency test, used to measure whether the ground fissure identification result is consistent with the actual situation), and the results are as Figure 2 shown. It can be seen from Figure 2 that this method can greatly improve the ground fissure identification accuracy compared with the traditional method. Its integrity is improved from 31.46% of the traditional method to 60.96%, the accuracy is improved from 28.06% to 83.79%, and the kappa coefficient is improved from 28.15% to 70.07%. Therefore, this method can accurately identify ground fissures in mining areas affected by large deformations and complex surface environments.

[0078] The above embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A remote sensing identification method for ground fissures in complex mining areas, characterized in that It includes the following steps: S1. Perform non-shadow area filtering based on a sliding window, brighten the mining area shadows based on HSV color compensation, and exclude the interference of solar shadows on ground fissure identification; S2. Filter out the ground fissure noise based on the ground fissure evaluation index of the linear index and the shape index, and identify the initial ground fissures; S3. Combine morphological processing and regional connectivity analysis to establish a comprehensive evaluation and determination mechanism, and accurately restore the true shape of the ground fissures hierarchically and multi-scale; Set the continuity assumption: is the gray level of the background pixel, is the average gray value of the initial ground fissure pixel. If it satisfies , this pixel is determined as a ground fissure object; If the above conditions are not met, perform the following linear hypothesis: Set a ground fissure compensation template that satisfies the ground fissure relationship. If it is determined that a pixel matches one of the defined templates, further check the conditions , where 、 are thresholds, and the threshold > threshold . If satisfied, classify the background pixel as an initial ground fissure pixel; S4. Based on multi-spatial scale threshold segmentation iteration, consider the length, end direction, inter-domain distance, and angle of the connected domain, perform hierarchical threshold growth, and combine the automatic extraction mechanism to eliminate small noises to complete the accurate identification of ground fissures.

2. The remote sensing identification method for ground fissures in complex mining areas according to claim 1, wherein, S1 includes the following sub-steps: S11. Set the size of the sliding window. When gradually sliding the window, count the number of pixels in each window, and suppress the small-scale noises according to the morphological characteristics of the non-shadow area to retain the large shadow areas; S12. Brighten the mining area shadows based on HSV color compensation for the shadow areas that meet the conditions. Use the V channel in the HSV space to brighten the shadows, and then locally filter the H and S channels to make the color effect of the shadow areas closer to the real color.

3. The remote sensing identification method for ground fissures in complex mining areas according to claim 2, characterized in that S11 is represented by the following formula: ； Among them, is the reserved pixel value, is the pixel value of the input image, is the number of black pixels within, is the empirical threshold. When the above conditions are met, the pixels are covered with white. The black pixel value is 0, and the white pixel value is 255. The specific definition is as follows: ； Among them, represents a sliding window centered at with a size of . represents each pixel point of the sliding window . is an indicator function.

4. A method for remotely sensing and identifying ground fissures in a complex mining area according to claim 2, characterized in that, The linear exponent in S2 is represented by as follows: ； Among them, and respectively represent the length and width of the minimum circumscribed rectangle of the connected domain where the ground fissure is located. The connected domain is the image area composed of the pixels recognized as ground fissure pixels in the image; The shape index is represented by as follows: ； Among them, represents the area of the circumcircle of the minimum circumscribed rectangle of the connected domain where the ground fissure is located.

5. A remote sensing identification method for ground fissures in complex mining areas according to claim 4, characterized in that In S4, starting from the initial pixels of each ground fissure that meets the linear and length conditions, track the ground fissure pixels along the main direction of the connected domain, and the bright pixel endpoint finally tracked is defined as the seed point; Subsequently, starting from the seed points, search is carried out and the Bresenham algorithm is used for growth to achieve the gap connection of the pixels of the ground fissure. The search conditions include the radius of the search area , the angle and the length of the connected domain where the ground fissure is located . The ground fissure extraction conditions include the length of the ground fissure after gap connection .

6. The remote sensing identification method for ground fissures in complex mining areas according to claim 5, wherein, For the search conditions, ； ； ； ； Among them, , , respectively represent the initial constraint values of the radius, length, and angle of the search area, is the condition for the extraction length of the ground fissure, , , are all iteration thresholds, is the iteration termination condition, represents the number of iterations.

Images