A geological disaster monitoring and early warning system and method

Abstract

The present application provides a geological disaster monitoring and early warning system and method. By monitoring the surface area with cracks, disaster monitoring images are obtained; based on the shaded pixel points of the disaster monitoring images, a plurality of characteristic marker points are determined, morphological expansion is performed on each characteristic marker point to obtain a plurality of expanded pixels, and a plurality of suspicious characteristic points are determined based on all the expanded pixels; a plurality of sub-image blocks are divided according to all the suspicious characteristic points, the image block centroid of the sub-image block is determined, and a shape descriptor is obtained based on the minimum circumscribed rectangle of the sub-image block and the image block centroid; the disaster monitoring image is analyzed according to the shape descriptor of the sub-image block and the evolution prediction model of the crack, and the analysis result is output to the geological disaster early warning center. By adopting the solution of the present application, geological disaster analysis can be realized under a complex light and shadow environment, thereby improving the accuracy of geological disaster monitoring and early warning.

Description

Technical Field

[0001] This application relates to the technical field of monitoring image analysis. More specifically, this application relates to a geological disaster monitoring and early warning system and method. Background Art

[0002] Monitoring image analysis is a process of detecting, recognizing, tracking, and analyzing targets in images or videos based on computer vision and image processing technologies. It is widely used in fields such as environmental monitoring, disaster early warning, intelligent transportation, and security monitoring. In addition, the combination of real-time processing and big data analysis has promoted the application of monitoring image analysis in large-scale monitoring systems. For example, in disaster monitoring, by combining satellite images and ground sensor data, the risks of natural disasters such as fires and floods can be identified in real time, and corresponding countermeasures can be quickly formulated. With the continuous optimization of algorithms, the accuracy, speed, and application scope of monitoring image analysis will continue to expand, becoming the core supporting technology for various intelligent systems.

[0003] Geological disaster monitoring based on monitoring image analysis uses remote sensing technology and deep learning algorithms, combines multi-source data, and monitors and evaluates the risks of geological disasters in real time. High-resolution image data is obtained through drone aerial photography and ground camera equipment, and a neural network model is used for target detection to automatically identify abnormal features of geological disasters. At the same time, based on multi-source data fusion technology, the accuracy and response speed of the monitoring system are improved, providing key data support for disaster emergency response; however, in the prior art, the target monitoring area usually has complex terrain and large lighting changes, and there will be many shadow areas. These shadows not only cover disaster features (such as cracks, landslides, etc.), but may also produce similar visual manifestations to geological changes such as cracks and rock mass deformation, affecting the accurate identification of targets, making it difficult to distinguish disaster features, and thus reducing the accuracy of monitoring and early warning. Therefore, how to perform geological disaster analysis in a complex lighting and shadow environment to improve the accuracy of geological disaster monitoring and early warning has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides a geological disaster monitoring and early warning system and method, which can perform geological disaster analysis in a complex lighting and shadow environment, thereby improving the accuracy of geological disaster monitoring and early warning.

[0005] In a first aspect, this application provides a method for analyzing disaster monitoring images, which includes the following steps:

[0006] Monitor the surface area with cracks to obtain disaster monitoring images;

[0007] Determine multiple feature marker points of the disaster monitoring image based on the pixel gradients of each shaded pixel point in the disaster monitoring image, perform morphological expansion on the pixel points adjacent to each feature marker point in the disaster monitoring image in combination with a preset morphological operator to obtain multiple expanded pixels, and then determine multiple suspicious feature points within the disaster monitoring image based on all the expanded pixels;

[0008] Divide the disaster monitoring image into multiple sub-image blocks according to all the suspicious feature points, select one sub-image block as the selected sub-image block, determine the centroid of the image block of the selected sub-image block, perform shape analysis on the selected sub-image block based on the minimum circumscribed rectangle of the selected sub-image block and the centroid of the image block to obtain the shape descriptor of the selected sub-image block, and continue to determine the shape descriptors of the remaining sub-image blocks;

[0009] Analyze the disaster monitoring image according to the shape descriptors of each sub-image block and the crack evolution prediction model, and output the analysis result to the geological disaster warning center.

[0010] In some embodiments, determining multiple feature marker points of the disaster monitoring image based on the pixel gradients of each shaded pixel point in the disaster monitoring image specifically includes:

[0011] Perform shadow segmentation on the disaster monitoring image to obtain multiple shadow areas of the disaster monitoring image;

[0012] Determine the pixel gradient corresponding to each shaded pixel point in each shadow area;

[0013] Extract multiple feature marker points in the disaster monitoring image from all the shaded pixel points based on the pixel gradients corresponding to each shaded pixel point in each shadow area in combination with a pixel gradient threshold.

[0014] In some embodiments, performing morphological expansion on the pixel points adjacent to each feature marker point in the disaster monitoring image in combination with a preset morphological operator to obtain multiple expanded pixels specifically includes:

[0015] Set the morphological operator of the disaster monitoring image;

[0016] Perform feature expansion on the pixel points adjacent to each feature marker point in the disaster monitoring image based on the morphological operator to obtain multiple expanded pixels.

[0017] In some embodiments, determining multiple suspicious feature points within the disaster monitoring image based on all the expanded pixels specifically includes:

[0018] Obtain the disaster monitoring image and the morphological operator;

[0019] Traverse the disaster monitoring image through the morphological operator to obtain multiple verification regions;

[0020] Determine multiple suspicious feature points in the disaster monitoring image based on all the verification regions and all the extended pixels.

[0021] In some embodiments, dividing the disaster monitoring image into multiple sub-image blocks according to all the suspicious feature points specifically includes:

[0022] Cluster all the suspicious feature points to obtain multiple feature grouping sets;

[0023] Construct sub-image blocks corresponding to each feature grouping set, and then obtain multiple sub-image blocks of the disaster monitoring image.

[0024] In some embodiments, analyzing the disaster monitoring image according to the shape descriptors of each sub-image block and the crack evolution prediction model, and outputting the analysis result to the geological disaster warning center specifically includes:

[0025] Determine multiple surface risk features based on the shape descriptors of each sub-image block and a preset feature threshold;

[0026] Extract the crack features of the disaster monitoring image from all the surface risk features;

[0027] Generate a disaster trend analysis chart of the disaster monitoring image through the crack evolution prediction model combined with the crack features;

[0028] Use the disaster trend analysis chart as the analysis result of the disaster monitoring image, and send the analysis result to the geological disaster warning center.

[0029] In some embodiments, use a drone to monitor the surface area with cracks and capture a disaster monitoring image.

[0030] In a second aspect, the present application provides a geological disaster monitoring and warning system, which includes a disaster monitoring image analysis unit. The disaster monitoring image analysis unit includes:

[0031] An acquisition module for monitoring the surface area with cracks to obtain a disaster monitoring image;

[0032] A processing module for determining multiple feature marker points of the disaster monitoring image based on the pixel gradients of each shaded pixel point in the disaster monitoring image, performing morphological expansion on the pixel points adjacent to each feature marker point in the disaster monitoring image in combination with a preset morphological operator to obtain multiple extended pixels, and then determining multiple suspicious feature points in the disaster monitoring image based on all the extended pixels;

[0033] The processing module is further configured to divide the disaster monitoring image into a plurality of sub-image blocks according to all the suspicious feature points, select one sub-image block as the selected sub-image block, determine the centroid of the selected sub-image block, perform shape analysis on the selected sub-image block based on the minimum bounding rectangle of the selected sub-image block and the centroid of the image block, obtain the shape descriptor of the selected sub-image block, and continue to determine the shape descriptors of the remaining sub-image blocks;

[0034] The execution module is configured to analyze the disaster monitoring image according to the shape descriptors of each sub-image block and the crack evolution prediction model, and output the analysis result to the geological disaster warning center.

[0035] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned disaster monitoring image analysis method.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned disaster monitoring image analysis method is implemented.

[0037] The technical solution provided by the disclosed embodiments of the present application has the following beneficial effects:

[0038] In the geological disaster monitoring and warning system and method provided by the present application, first, the surface area with cracks is monitored to obtain a disaster monitoring image; secondly, a plurality of feature marker points of the disaster monitoring image are determined based on the pixel gradients of the shadow pixel points in the disaster monitoring image, and morphological expansion is performed on the pixel points adjacent to each feature marker point in the disaster monitoring image in combination with a preset morphological operator to obtain a plurality of expanded pixels, and then a plurality of suspicious feature points in the disaster monitoring image are determined based on all the expanded pixels; further, the disaster monitoring image is divided into a plurality of sub-image blocks according to all the suspicious feature points, one sub-image block is selected as the selected sub-image block, the centroid of the selected sub-image block is determined, shape analysis is performed on the selected sub-image block based on the minimum bounding rectangle of the selected sub-image block and the centroid of the image block, the shape descriptor of the selected sub-image block is obtained, and the shape descriptors of the remaining sub-image blocks are continued to be determined; finally, the disaster monitoring image is analyzed according to the shape descriptors of each sub-image block and the crack evolution prediction model, and the analysis result is output to the geological disaster warning center.

[0039] It can be seen that the present application can realize geological disaster analysis in a complex light and shadow environment, thereby improving the accuracy of geological disaster monitoring and early warning. First, obtaining disaster monitoring images can provide an effective data source for subsequent analysis and early warning. Secondly, determining multiple feature marker points in the disaster monitoring images to describe the general outline of the surface shadow area, thereby providing support for subsequent image analysis. Further, morphological verification is performed on all the feature marker points to obtain multiple suspicious feature points of the disaster monitoring images, so as to preliminarily describe the regional characteristics of the surface cracks, thereby increasing the efficiency of identification and processing in subsequent analysis. Then, multiple sub-image blocks of the disaster monitoring images are divided to extract potential geological disaster occurrence locations in the surface monitoring images, thereby improving the accuracy of geological disaster monitoring. In addition, determining the shape descriptors of the sub-image blocks can provide a data basis for subsequent judgment on whether the sub-image blocks are surface crack areas, and can describe the geometric characteristics and expansion trends of the surface cracks, thereby improving the effectiveness of geological disaster monitoring. Finally, the analysis results of the disaster monitoring images are output according to the shape descriptors, thereby assisting managers to evaluate the possibility of geological disasters occurring and taking corresponding emergency prevention measures. In summary, the technical solution provided by the present application can realize geological disaster analysis in a complex light and shadow environment, thereby improving the accuracy of geological disaster monitoring and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is an exemplary flowchart of a disaster monitoring image analysis method according to some embodiments of the present application;

[0041] Figure 2 is an exemplary flowchart of determining multiple feature marker points of the disaster monitoring images according to some embodiments of the present application;

[0042] Figure 3 is an exemplary flowchart of determining the shape descriptors of selected sub-image blocks according to some embodiments of the present application;

[0043] Figure 4 is a schematic structural diagram of a disaster monitoring image analysis unit according to some embodiments of the present application;

[0044] Figure 5 is a schematic structural diagram of a computer device for implementing the disaster monitoring image analysis method according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] To better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0046] Reference Figure 1, The figure is an exemplary flowchart of a disaster monitoring image analysis method according to some embodiments of the present application. The disaster monitoring image analysis method 100 mainly includes the following steps:

[0047] In step 101, monitor the surface area with cracks to obtain a disaster monitoring image.

[0048] Specifically, when implemented, monitor the surface area with cracks to obtain a disaster monitoring image, that is: monitor and take pictures of the surface area with cracks by an unmanned aerial vehicle, and use the obtained image as the disaster monitoring image. In addition, in other embodiments, other methods can also be used to obtain the disaster monitoring image, such as satellite images, etc., which are not limited here.

[0049] It should be noted that in the present application, the disaster monitoring image refers to an image used to monitor natural disaster-related information. This image has a wide coverage area and high resolution. By obtaining the disaster monitoring image, an effective data source can be provided for subsequent analysis and early warning.

[0050] In step 102, based on the pixel gradients of the respective shaded pixel points in the disaster monitoring image, determine a plurality of feature marker points of the disaster monitoring image, perform morphological expansion on the pixel points adjacent to each feature marker point in the disaster monitoring image in combination with a preset morphological operator to obtain a plurality of expanded pixels, and then based on all the expanded pixels, determine a plurality of suspicious feature points within the disaster monitoring image.

[0051] In some embodiments, refer to Figure 2 As shown, the figure is an exemplary flowchart of determining a plurality of feature marker points of the disaster monitoring image according to some embodiments of the present application. In this embodiment, determining a plurality of feature marker points of the disaster monitoring image based on the pixel gradients of the respective shaded pixel points in the disaster monitoring image can be implemented by the following steps:

[0052] First, in step 1021, perform shadow segmentation on the disaster monitoring image to obtain a plurality of shadow regions of the disaster monitoring image;

[0053] Then, in step 1022, determine the pixel gradient corresponding to each shaded pixel point in each shadow region;

[0054] Finally, in step 1023, based on the pixel gradients corresponding to the respective shaded pixel points in each shadow region and in combination with a pixel gradient threshold, extract a plurality of feature marker points in the disaster monitoring image from all the shaded pixel points.

[0055] In specific implementation, the shadow segmentation of the disaster monitoring image is performed by the threshold segmentation method to obtain multiple shadow areas of the disaster monitoring image. The threshold segmentation method is an existing technology in image processing, and the specific segmentation process will not be elaborated here. It should be noted that the shadow area represents the position of the black shadow generated in the area below the ground surface when illuminated by light. By segmenting the shadow area, the geological features of the cracks can be further analyzed and extracted, thereby improving the effectiveness of early warning.

[0056] Among them, in some embodiments, the pixel gradients corresponding to each shadow pixel point in each shadow area can be determined by the following method, that is:

[0057] For each shadow area, all the shadow pixel points in the shadow area are extracted;

[0058] The pixel gradients corresponding to each shadow pixel point are determined according to the gray value of each shadow pixel point.

[0059] In specific implementation, all the shadow pixel points in the shadow area are extracted, that is: all the pixel points located in the shadow area are used as shadow pixel points, so as to obtain all the shadow pixel points in the shadow area.

[0060] In specific implementation, the pixel gradients corresponding to each shadow pixel point are determined according to the gray value of each shadow pixel point, that is: a shadow pixel point is selected, and the horizontal pixel gradient and vertical pixel gradient of the shadow pixel point are calculated by combining the Canny edge operator with the gray values of the shadow pixel point and its adjacent shadow pixel points. The sum of the square value of the horizontal pixel gradient and the square value of the vertical pixel gradient is calculated, and the arithmetic square root of the sum result is used as the pixel gradient corresponding to the shadow pixel point, so as to obtain the pixel gradients corresponding to each shadow pixel point. In addition, in other embodiments, other methods can also be used to calculate the pixel gradient, for example, the Soble edge operator, etc., which are not limited here.

[0061] It should be noted that the Canny edge operator represents an existing technology for edge detection in image processing, and the specific calculation process will not be elaborated here.

[0062] In specific implementation, based on the pixel gradients corresponding to each shadow pixel point in each shadow area and combined with the pixel gradient threshold, multiple feature marker points in the disaster monitoring image are extracted from all the shadow pixel points, that is: a pixel gradient threshold is set, the pixel gradients of each shadow pixel point are respectively compared with the pixel gradient threshold, all the pixel gradients greater than the pixel gradient threshold are extracted, and the shadow pixel points corresponding to the extracted pixel gradients are used as feature marker points, so as to obtain multiple feature marker points in the disaster monitoring image.

[0063] It should be noted that in this embodiment, the value of the pixel gradient threshold can be set according to specific application requirements, and its specific size is not limited here. In addition, in this application, the feature marker points represent the edge pixel points located at the shadow positions, which have relatively prominent color brightness and darkness features. By extracting the feature marker points, the general outline of the surface shadow area can be described, thereby providing support for subsequent image analysis and further improving the prediction accuracy of potential geological disasters.

[0064] In some embodiments, the adjacent pixels of each feature marker point in the disaster monitoring image can be morphologically expanded by combining a preset morphological operator. The following method can be adopted, that is:

[0065] Set the morphological operator of the disaster monitoring image;

[0066] Based on the morphological operator, perform feature expansion on the adjacent pixels of each feature marker point in the disaster monitoring image to obtain a plurality of expanded pixels.

[0067] Specifically, when implementing, set the morphological operator of the disaster monitoring image, that is: set a rectangular frame with a fixed size, and use this rectangular frame as the morphological operator of the disaster monitoring image. The size of the morphological operator can be set according to the accuracy requirements in actual applications and is not limited here. In this embodiment, the set size is 5*5.

[0068] It should be noted that in this embodiment, the morphological operator is an operator for further detecting and confirming the surface morphology of the disaster monitoring image. By setting the morphological operator, the robustness and consistency of image analysis and processing can be enhanced, thereby improving the monitoring accuracy of the disaster monitoring image.

[0069] Specifically, when implementing, perform feature expansion on the adjacent pixels of each feature marker point in the disaster monitoring image based on the morphological operator to obtain a plurality of expanded pixels, that is: use the morphological operator to traverse each feature marker point in sequence from the upper left corner of the disaster monitoring image. Each traversal will cover a pixel area, which includes the feature marker point and the adjacent pixels within a range of 5*5 centered on this feature marker point. If there are at least five other feature marker points in the pixel area, then all the pixel points in the pixel area are used as expanded pixels, and thus a plurality of expanded pixels of the disaster monitoring image are obtained.

[0070] It should be noted that in this embodiment, the expanded pixels represent the newly added pixel points during the process of repairing the integrity of the disaster monitoring image. Through the expanded pixels, the shape and connectivity of the disaster monitoring image can be optimized, thereby enhancing the effectiveness of geological disaster monitoring.

[0071] In some embodiments, the following method may be adopted to determine multiple suspicious feature points in the disaster monitoring image based on all the extended pixels, that is:

[0072] Obtain the disaster monitoring image and the morphological operator;

[0073] Traverse the disaster monitoring image with the morphological operator to obtain multiple verification regions;

[0074] Determine multiple suspicious feature points in the disaster monitoring image based on all the verification regions and all the extended pixels.

[0075] Specifically, when implementing, traverse the disaster monitoring image with the morphological operator to obtain multiple verification regions, that is: starting from the upper left corner of the disaster monitoring image, use the morphological operator to perform a sliding traversal of the disaster monitoring image with a step size of 1, and take the covered area of each traversal as a verification region, thereby obtaining multiple verification regions.

[0076] It should be noted that in this embodiment, the verification region represents the sub-image region obtained by traversal, and all pixel points in this region need to be further verified and analyzed.

[0077] Specifically, when implementing, determine multiple suspicious feature points in the disaster monitoring image based on all the verification regions and all the extended pixels, that is: select a verification region, if all pixel points in this verification region are extended pixels, then take the central pixel point of this verification region as a suspicious feature point, otherwise do not process it, thereby obtaining multiple suspicious feature points of the disaster monitoring image.

[0078] It should be noted that in this application, the suspicious feature point represents a pixel point suspected to be at the surface crack. The suspicious feature point is identified during the process of geological disaster monitoring of the disaster monitoring image. During the subsequent monitoring process, the suspicious feature point needs to be analyzed and verified key points. By extracting the suspicious feature point, a preliminary regional feature description of the surface crack position can be made, thereby increasing the efficiency of identification and processing in the subsequent analysis process, and further improving the accuracy and timeliness of disaster monitoring and early warning.

[0079] In step 103, divide the disaster monitoring image into multiple sub-image blocks according to all the suspicious feature points, select one sub-image block as the selected sub-image block, determine the centroid of the image block of the selected sub-image block, perform shape analysis on the selected sub-image block based on the minimum bounding rectangle of the selected sub-image block and the centroid of the image block to obtain the shape descriptor of the selected sub-image block, and continue to determine the shape descriptors of the remaining sub-image blocks.

[0080] In some embodiments, the multiple sub-image blocks of the disaster monitoring image can be divided according to all the suspicious feature points in the following manner, that is:

[0081] Cluster all the suspicious feature points to obtain multiple feature grouping sets;

[0082] Construct sub-image blocks corresponding to each feature grouping set, and then obtain multiple sub-image blocks of the disaster monitoring image.

[0083] In specific implementation, cluster all the suspicious feature points to obtain multiple feature grouping sets, that is: cluster all the suspicious feature points through a clustering algorithm to obtain multiple feature grouping sets. Specifically, the DBSCAN clustering algorithm can be selected for clustering. The specific clustering process is not described here. In addition, in other embodiments, other algorithms can also be used for clustering, such as K-means clustering, hierarchical clustering, etc., which are not limited here.

[0084] It should be noted that in this embodiment, the feature grouping set represents a set composed of suspicious feature points. Determining the feature grouping set is beneficial to improving the integrity of subsequent analysis.

[0085] In specific implementation, construct sub-image blocks corresponding to each feature grouping set, that is: for each feature grouping set, connect all the suspicious feature points in the feature grouping set through a region-growing connectivity algorithm to form a closed region, and use this closed region as a sub-image block of the disaster monitoring image. The specific connection process is not described here. In addition, in other embodiments, other algorithms can also be used to connect the pixel points in the feature grouping set, such as pixel cluster merging based on machine learning, etc., which are not limited here.

[0086] It should be noted that in this application, the sub-image block represents the shaded part in the disaster monitoring image. The shaded part can represent potential surface cracks, and further confirmation and analysis are required. By determining the sub-image block, the potential geological disaster occurrence location in the surface monitoring image can be extracted, thereby improving the accuracy of geological disaster monitoring.

[0087] In some embodiments, the image block centroid of the selected sub-image block can be determined in the following manner, that is:

[0088] Extract the pixel coordinates of all pixel points in the selected sub-image block;

[0089] Determine the image block centroid of the selected sub-image block based on all the pixel coordinates.

[0090] In specific implementation, the pixel coordinates of all pixel points in the selected sub-image block can be extracted through the image processing software OpenCV, and the number of coordinate quantities of the pixel coordinates is recorded. In addition, in other embodiments, other methods can also be used to extract the pixel coordinates of the pixel points, which are not limited here.

[0091] In specific implementation, based on all the pixel coordinates, the centroid of the selected sub-image block is determined, that is: the abscissa and ordinate corresponding to each pixel coordinate are extracted, and then all the abscissas and all the ordinates are obtained. The quotient of the sum of all abscissas and the number of coordinates is used as the centroid abscissa, and the quotient of the sum of all ordinates and the number of coordinates is used as the centroid ordinate. The centroid of the selected sub-image block is determined through the centroid abscissa and the centroid ordinate.

[0092] It should be noted that the centroid of the image block in this application represents the geometric center of the sub-image block. By determining the centroid of the image block, it is convenient for subsequent geometric analysis of the sub-image block, thereby improving the accuracy of geological disaster monitoring.

[0093] In some embodiments, with reference to Figure 3 As shown, this figure is an exemplary flowchart for determining the shape descriptor of the selected sub-image block according to some embodiments of the present application. In this embodiment, shape analysis of the selected sub-image block is performed based on the minimum bounding rectangle of the selected sub-image block and the centroid of the image block. The following steps can be used to obtain the shape descriptor of the selected sub-image block:

[0094] First, in step 1031, the minimum bounding rectangle of the selected sub-image block is determined;

[0095] Secondly, in step 1032, the first shape parameter of the selected sub-image block is determined based on the minimum bounding rectangle;

[0096] Furthermore, in step 1033, the maximum inscribed circle of the selected sub-image block is fitted based on the centroid of the image block;

[0097] Then, in step 1034, the second shape parameter of the selected sub-image block is determined according to the maximum inscribed circle;

[0098] Finally, in step 1035, the shape descriptor of the selected sub-image block is determined based on the first shape parameter and the second shape parameter.

[0099] In specific implementation, determine the minimum bounding rectangle of the selected sub-image block, that is: obtain the pixel coordinates of all pixel points in the selected sub-image block, extract the maximum abscissa, minimum abscissa, maximum ordinate, and minimum ordinate from all the pixel coordinates, and determine the minimum bounding rectangle of the selected sub-image block through the minAreaRect function in Open CV in combination with the maximum abscissa, minimum abscissa, maximum ordinate, and minimum ordinate.

[0100] It should be noted that in this application, the minimum bounding rectangle refers to the smallest rectangle that can enclose the sub-image block, and the boundaries of this rectangle are parallel to the coordinate axes. By determining the minimum bounding rectangle, it is beneficial to quickly evaluate the spatial range and geometric characteristics of the sub-image block, thereby simplifying the subsequent analysis process.

[0101] In specific implementation, determine the first shape parameter of the selected sub-image block based on the minimum bounding rectangle, that is: use the diagonal length of the minimum bounding rectangle as the first shape parameter of the selected sub-image block. The first shape parameter represents the geometric characteristics of the sub-image block in terms of shape and provides data support for subsequent analysis.

[0102] Among them, in some embodiments, the maximum inscribed circle of the selected sub-image block can be obtained by fitting based on the centroid of the image block in the following manner, that is:

[0103] Extract all the boundary pixels of the selected sub-image block;

[0104] Determine the boundary distance between each boundary pixel and the centroid of the image block;

[0105] Determine the maximum inscribed circle of the selected sub-image block based on all the boundary distances.

[0106] In specific implementation, extract all the boundary pixels of the selected sub-image block through a contour extraction algorithm. The boundary pixels represent the pixel points located at the boundary of the selected sub-image block. In addition, in other embodiments, other methods can also be used to extract boundary pixels, such as connected component labeling, etc., which are not limited here.

[0107] In specific implementation, determine the boundary distance between each boundary pixel and the centroid of the image block, that is: select a boundary pixel, substitute the pixel coordinates of this boundary pixel and the pixel coordinates of the centroid of the image block into the distance calculation formula to obtain the boundary distance between this boundary pixel and the centroid of the image block, and then obtain the boundary distances between each boundary pixel and the centroid of the image block.

[0108] It should be noted that in this embodiment, the boundary distance represents the distance from the centroid of the sub-image block to the boundary of the sub-image block.

[0109] In specific implementation, based on all the boundary distances, the maximum inscribed circle of the selected sub-image block is determined, that is: the minimum boundary distance is extracted from all the boundary distances, and this boundary distance is used as the maximum inscribed radius. With the centroid of the image block as the center and the maximum inscribed radius as the radius, the maximum inscribed circle of the selected sub-image block is obtained.

[0110] It should be noted that in this embodiment, the maximum inscribed circle represents the maximized circle that can be placed within the sub-image block without exceeding the boundary of the sub-image block. By determining the maximum inscribed circle, more geometric features of the sub-image block can be extracted, thereby providing stronger data support for subsequent analysis.

[0111] In specific implementation, according to the maximum inscribed circle, the second shape parameter of the selected sub-image block is determined, that is: the pixel coordinates of all pixel points within the maximum inscribed circle are combined into a two-dimensional coordinate matrix, the covariance matrix of this two-dimensional coordinate matrix is calculated, and the first eigenvalue and the second eigenvalue of this covariance matrix are calculated (the first eigenvalue is greater than the second eigenvalue). The quotient of the first eigenvalue and the second eigenvalue is used as the second shape parameter of the selected sub-image block.

[0112] It should be noted that the above calculation processes are all implemented using the numpy library in Python. In addition, in other embodiments, other methods can also be used for calculation, which is not limited here.

[0113] It also should be noted that in this embodiment, the first eigenvalue and the second eigenvalue represent the degree of change of the pixel coordinates in different directions. Therefore, in this embodiment, the second shape parameter represents the geometric characteristic parameter of the sub-image block in terms of direction.

[0114] In specific implementation, based on the first shape parameter and the second shape parameter, the shape descriptor of the selected sub-image block is determined, that is: the mean value of the first shape parameter and the second shape parameter is used as the shape descriptor of the selected sub-image block.

[0115] It should be noted that in this application, the shape descriptor represents an index for measuring the geometric features of the sub-image block; in geological disaster monitoring, after preliminary extraction, there are often some isolated and small-sized interference regions. By determining the shape descriptor, it can provide a data basis for subsequent judgment on whether the sub-image block is a surface crack region, and can describe the geometric features and expansion trend of the surface crack, thereby improving the effectiveness of geological disaster monitoring.

[0116] It should be noted that the implementation steps of "performing shape analysis on the selected sub-image block based on the minimum circumscribed rectangle of the selected sub-image block and the centroid of the image block to obtain the shape descriptor of the selected sub-image block" are continued to determine the shape descriptors of the remaining sub-image blocks, which will not be elaborated here.

[0117] In step 104, the disaster monitoring image is analyzed according to the shape descriptors of each sub-image block and the crack evolution prediction model, and the analysis result is output to the geological disaster warning center.

[0118] In some embodiments, analyzing the disaster monitoring image according to the shape descriptors of each sub-image block and the crack evolution prediction model and outputting the analysis result to the geological disaster warning center can be implemented in the following manner, that is:

[0119] Determine a plurality of surface risk features based on the shape descriptors of each sub-image block and a preset feature threshold;

[0120] Extract the crack features of the disaster monitoring image from all the surface risk features;

[0121] Generate a disaster trend analysis chart of the disaster monitoring image through the crack evolution prediction model in combination with the crack features;

[0122] Use the disaster trend analysis chart as the analysis result of the disaster monitoring image and send the analysis result to the geological disaster warning center.

[0123] In specific implementation, determining a plurality of surface risk features based on the shape descriptors of each sub-image block and a preset feature threshold, that is: preset a feature threshold, compare the shape descriptors of all sub-image blocks with the feature threshold, extract all shape descriptors greater than the feature threshold, and use the sub-image blocks corresponding to the extracted shape descriptors as surface risk features, and do not process otherwise, so as to obtain a plurality of surface risk features.

[0124] It should be noted that in this embodiment, the feature threshold represents a threshold for determining whether a sub-image block has risks. The specific value can be set according to the actual monitoring requirements in combination with historical expert experience data, which is not limited here. By setting the feature threshold, the interference brought by isolated and small-sized interference regions to geological disaster monitoring can be eliminated.

[0125] It should also be noted that in this embodiment, the surface risk feature represents the crack position on the surface. The existence of this position will bring potential geological disaster risks and needs to be focused on.

[0126] In specific implementation, extract the crack features of the disaster monitoring image from all the surface risk features, that is: obtain the shape descriptors of all surface risk features, extract the largest shape descriptor, and use the surface risk feature corresponding to the extracted shape descriptor as the crack feature of the disaster monitoring image.

[0127] It should be noted that in this application, the crack feature represents the most representative crack position on the ground surface, which is often located in special parts of the disaster monitoring image. For example, the upper edge or lower edge of a slope. By determining the crack feature, the most risky crack in the disaster monitoring image can be characterized, so as to conduct key monitoring on it, and then improve the effectiveness of geological disaster monitoring and early warning.

[0128] In specific implementation, a disaster trend analysis diagram of the disaster monitoring image is generated by combining the crack evolution prediction model with the crack feature, that is: First, the crack feature is continuously photographed by a drone to obtain crack inspection data, and the shooting frequency can be set according to actual emergency needs. For example, shooting is carried out every ten minutes; Then, the crack inspection data is input into the pre-trained crack evolution prediction model to obtain the change information of the crack feature; Finally, the change information of the crack feature over time is integrated on a time series diagram to obtain the disaster trend analysis diagram of the disaster monitoring image.

[0129] It should be noted that the crack evolution prediction model in this embodiment is a neural network model trained with a large amount of disaster monitoring data. In addition, the change information of the crack feature over time can be integrated through GIS (Geographic Information System, GIS). In addition, in other embodiments, other methods can also be used for information integration, which is not limited here.

[0130] It should also be noted that the crack inspection data in this embodiment represents an image set obtained by the drone shooting the crack area at a fixed frequency. The disaster trend analysis diagram contains change information such as the development trend and expansion rate of the crack feature. By generating the disaster trend analysis diagram, it can assist managers to evaluate the possibility of geological disasters and take corresponding emergency prevention measures.

[0131] In addition, on the other hand of this application, in some embodiments, this application provides a geological disaster monitoring and early warning system, which includes a disaster monitoring image analysis unit. Refer to Figure 4 , this figure is a schematic structural diagram of the disaster monitoring image analysis unit shown in some embodiments of this application. The disaster monitoring image analysis unit 200 includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described as follows:

[0132] The acquisition module 201 is mainly used in this application to monitor the ground surface area with cracks and obtain disaster monitoring images.

[0133] The processing module 202. In this application, the processing module 202 is mainly used to determine a plurality of feature marker points of the disaster monitoring image based on the pixel gradients of each shadow pixel point in the disaster monitoring image, perform morphological expansion on the pixel points adjacent to each feature marker point in the disaster monitoring image by combining a preset morphological operator to obtain a plurality of expanded pixels, and then determine a plurality of suspicious feature points in the disaster monitoring image based on all the expanded pixels;

[0134] The processing module 202 is further used to divide the disaster monitoring image into a plurality of sub-image blocks according to all the suspicious feature points, select one sub-image block as the selected sub-image block, determine the image block centroid of the selected sub-image block, perform shape analysis on the selected sub-image block based on the minimum circumscribed rectangle of the selected sub-image block and the image block centroid to obtain the shape descriptor of the selected sub-image block, and continue to determine the shape descriptors of the remaining sub-image blocks;

[0135] The execution module 203. In this application, the execution module 203 is mainly used to analyze the disaster monitoring image according to the shape descriptors of each sub-image block and the crack evolution prediction model, and output the analysis result to the geological disaster warning center.

[0136] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned disaster monitoring image analysis method.

[0137] In some embodiments, refer to Figure 5 , this figure is a schematic structural diagram of a computer device for implementing the disaster monitoring image analysis method according to some embodiments of this application. The disaster monitoring image analysis method in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0138] The processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the disaster monitoring image analysis method in this application.

[0139] The communication bus 302 can be used to transmit information between the above components.

[0140] The memory 303 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 303 can exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 can also be integrated with the processor 301.

[0141] Among them, the memory 303 is used to store the program code for executing the solution of this application and is controlled by the processor 301 for execution. The processor 301 is used to execute the program code stored in the memory 303. The program code can include one or more software modules. The determination of the disaster monitoring image analysis method in the above embodiments can be implemented by one or more software modules in the program code in the processor 301 and the memory 303.

[0142] The communication interface 304 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 networks (WLAN), etc.

[0143] In a specific implementation, as an embodiment, the computer device can include multiple processors, and each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, the processor can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0144] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a laptop 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 the present application do not limit the type of the computer device.

[0145] In addition, the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-described disaster monitoring image analysis method is implemented.

[0146] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0147] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A disaster monitoring image analysis method, characterized in that: The steps include: Monitor surface areas with cracks and obtain disaster monitoring images; Determine multiple characteristic marking points of the disaster monitoring image based on the pixel gradient of each shadow pixel in the disaster monitoring image, perform morphological expansion on the pixel points adjacent to each characteristic marking point in the disaster monitoring image in combination with a preset morphological operator to obtain multiple expanded pixels, and then determine multiple suspicious characteristic points in the disaster monitoring image based on all the expanded pixels; Divide the disaster monitoring image into multiple sub-image blocks according to all suspicious feature points, select a sub-image block as a selected sub-image block, determine the image block centroid of the selected sub-image block, perform shape analysis on the selected sub-image block based on the minimum circumscribed rectangle of the selected sub-image block and the image block centroid, obtain a shape descriptor of the selected sub-image block, and continue to determine the shape descriptors of the remaining sub-image blocks; Analyze the disaster monitoring image according to the shape descriptors of each sub-image block and the crack evolution prediction model, and output the analysis results to the geological disaster early warning center, wherein the crack evolution prediction model inputs the time series change data of the crack characteristics and outputs the disaster trend analysis diagram including the crack expansion rate and direction; The following steps are used to perform shape analysis on the selected sub-image block based on the minimum bounding rectangle of the selected sub-image block and the centroid of the image block to obtain the shape descriptor of the selected sub-image block: Determine the minimum bounding rectangle of the selected sub-image block; Determining a first shape parameter of the selected sub-image block based on the minimum circumscribed rectangle, wherein the first shape parameter is the diagonal length of the minimum circumscribed rectangle, and represents a geometric characteristic of the sub-image block in terms of size; Obtaining a maximum inscribed circle of a selected sub-image block based on the centroid fitting of the image block; Determining a second shape parameter of the selected sub-image block according to the maximum inscribed circle, the second shape parameter represents a geometric characteristic of the sub-image block in a direction, wherein the pixel coordinates of all pixel points within the maximum inscribed circle are combined into a two-dimensional coordinate matrix, a covariance matrix of the two-dimensional coordinate matrix is ​​calculated, and a first eigenvalue and a second eigenvalue of the covariance matrix are calculated, and a quotient of the first eigenvalue and the second eigenvalue is used as the second shape parameter of the selected sub-image block; determining a shape descriptor of the selected sub-image block according to the first shape parameter and the second shape parameter; The sub-image block represents the shadow area in the disaster monitoring image.

2. The method according to claim 1, characterized in that Determining a plurality of characteristic marking points of the disaster monitoring image based on the pixel gradient of each shadow pixel point in the disaster monitoring image specifically includes: Performing shadow segmentation on the disaster monitoring image to obtain a plurality of shadow areas of the disaster monitoring image; Determine the pixel gradient corresponding to each shadow pixel in each shadow area; Based on the pixel gradient corresponding to each shadow pixel point in each shadow area combined with the pixel gradient threshold, multiple feature marker points in the disaster monitoring image are extracted from all the shadow pixels.

3. The method according to claim 1, characterized in that The pixel points adjacent to each feature mark point in the disaster monitoring image are morphologically expanded by combining a preset morphological operator to obtain a plurality of expanded pixels, specifically including: Setting a morphological operator of the disaster monitoring image; Based on the morphological operator, feature expansion is performed on pixel points adjacent to each feature marker point in the disaster monitoring image to obtain a plurality of expanded pixels.

4. The method according to claim 1, characterized in that Determining multiple suspicious feature points in the disaster monitoring image based on all the extended pixels specifically includes: Acquiring the disaster monitoring image and the morphological operator; Traversing the disaster monitoring image by using the morphological operator to obtain a plurality of verification areas; A plurality of suspicious feature points in the disaster monitoring image are determined based on all verification areas and all expanded pixels.

5. The method according to claim 1, characterized in that Dividing the disaster monitoring image into a plurality of sub-image blocks according to all suspicious feature points specifically includes: Cluster all suspicious feature points to obtain multiple feature grouping sets; A sub-image block corresponding to each feature grouping set is constructed, thereby obtaining a plurality of sub-image blocks of the disaster monitoring image.

6. The method according to claim 1, characterized in that The disaster monitoring image is analyzed according to the shape descriptors of each sub-image block and the crack evolution prediction model, and the analysis results are output to the geological disaster early warning center, which specifically includes: Determine a plurality of surface risk features based on shape descriptors of each sub-image block and a preset feature threshold; Extracting crack features of the disaster monitoring image from all surface risk features; Generate a disaster trend analysis diagram of the disaster monitoring image by combining the crack evolution prediction model with the crack characteristics; The disaster trend analysis diagram is used as the analysis result of the disaster monitoring image, and the analysis result is sent to a geological disaster early warning center.

7. The method according to claim 1, characterized in that Use drones to monitor surface areas where cracks exist and take photos to obtain disaster monitoring images.

8. A geological disaster monitoring and early warning system, which adopts the method described in any one of claims 1 to 7 to perform disaster monitoring image analysis, and the geological disaster monitoring and early warning system includes a disaster monitoring image analysis unit, characterized in that: The disaster monitoring image analysis unit comprises: An acquisition module is used to monitor the surface area where cracks exist and obtain disaster monitoring images; A processing module, used to determine a plurality of characteristic marking points of the disaster monitoring image based on the pixel gradient of each shadow pixel point in the disaster monitoring image, perform morphological expansion on the pixel points adjacent to each characteristic marking point in the disaster monitoring image in combination with a preset morphological operator to obtain a plurality of expanded pixels, and then determine a plurality of suspicious characteristic points in the disaster monitoring image based on all the expanded pixels; The processing module is further used to divide the disaster monitoring image into multiple sub-image blocks according to all suspicious feature points, select a sub-image block as a selected sub-image block, determine the image block centroid of the selected sub-image block, perform shape analysis on the selected sub-image block based on the minimum circumscribed rectangle of the selected sub-image block and the image block centroid, obtain a shape descriptor of the selected sub-image block, and continue to determine the shape descriptors of the remaining sub-image blocks; The execution module is used to analyze the disaster monitoring image according to the shape descriptors of each sub-image block and the crack evolution prediction model, and output the analysis results to the geological disaster early warning center.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the disaster monitoring image analysis method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the disaster monitoring image analysis method according to any one of claims 1 to 7 is implemented.

Images