Dangerous rock early warning method, system, equipment and medium

Abstract

The invention provides a dangerous rock early warning method, system and device and a medium. Extracting local features of the geological point cloud data, aggregating the local features to generate global features, and obtaining dangerous rock features according to the global features; constructing a dangerous rock three-dimensional model according to the dangerous rock characteristics; performing stability and change trend prediction according to the dangerous rock three-dimensional model to obtain dangerous rock early warning information; according to the method, the change trend can be accurately predicted by using the dangerous rock three-dimensional model, the accuracy of dangerous rock early warning is improved, the uncertainty analysis of dangerous rock disaster time is met according to the dynamic expression of the personalized characteristics of the dangerous rock hidden danger, the reliability and accuracy of dangerous rock disaster early warning are improved, and a data basis is provided for disaster prevention and reduction work of geological disasters.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of geological monitoring, and in particular to dangerous rock early warning methods, systems, equipment and media. Background Art

[0002] Dangerous rocks are prone to collapse accidents, and they are highly concealed and sudden. In order to avoid the collapse of dangerous rocks, it is necessary to take early warning and prevent dangerous rocks, further improve the analysis of dangerous rock change trends and the precision of monitoring indicators, and identify the deformation of dangerous rock disaster bodies through subtle changes and acceleration of dangerous rock bodies. To identify and monitor dangerous rocks, a three-dimensional monitoring and early warning system is mainly established for dangerous rock deformation, crack dislocation, etc.

[0003] However, the traditional artificial geological disaster investigation method is inefficient in identifying and analyzing dangerous rocks, and it is difficult to identify the morphology and deformation signs of dangerous rock disasters, especially in high and steep slopes and places where investigators cannot reach, and it is impossible to identify, analyze and monitor dangerous rocks. For areas with many dangerous rock points and remote locations, it is difficult to build fixed monitoring equipment stations. For example, it is difficult to deploy automatic monitoring equipment such as acoustic emission, microseismic, cracks, and stress on a dangerous rock of several cubic meters. The use of satellite remote sensing technology can only carry out large-scale deformation identification, and it is impossible to accurately identify small dangerous rock bodies and conduct trend analysis. Summary of the invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The purpose of the present application is to solve one of the technical problems existing in the related art to at least a certain extent. The embodiments of the present application provide a dangerous rock warning method, system, equipment and medium, which can improve the accuracy of dangerous rock warning.

[0006] An embodiment of the first aspect of the present application is a dangerous rock early warning method, comprising:

[0007] Obtain geological point cloud data of the target area;

[0008] Extracting local features of the geological point cloud data, aggregating the local features to generate global features, and obtaining dangerous rock features according to the global features;

[0009] Constructing a three-dimensional model of dangerous rocks according to the characteristics of the dangerous rocks;

[0010] The stability and change trend are predicted based on the three-dimensional dangerous rock model to obtain dangerous rock warning information.

[0011] According to certain embodiments of the first aspect of the present application, the step of obtaining geological point cloud data of a target area includes:

[0012] Generate dense point cloud data based on multi-view images of the target area;

[0013] Align, register, and fuse the dense point cloud data to obtain preprocessed point cloud data;

[0014] Use the rock mass structure characteristics of historical unstable rock data as the initial clustering centers to cluster the preprocessed point cloud data to obtain the geological point cloud data of the target area.

[0015] According to some embodiments of the first aspect of the present application, extracting the local features of the geological point cloud data includes:

[0016] Perform point cloud segmentation on the geological point cloud data to classify each point of the geological point cloud data;

[0017] Perform neighborhood sampling on each classified point to obtain local information and aggregate the local information;

[0018] Capture local geometric detail information according to the local information;

[0019] Stitch the low-level local features and high-level local features in the local geometric detail information to obtain the local features of the geological point cloud data.

[0020] According to some embodiments of the first aspect of the present application, aggregating the local features to generate global features includes:

[0021] Obtain the unstable rock geometric features from the local features;

[0022] Calculate the dynamic time warping distances of time series corresponding to unstable rock geometric features with different fine-grained levels;

[0023] Minimize the dynamic time warping distances to align the time series corresponding to the unstable rock geometric features to obtain time series features;

[0024] Obtain spatial features according to the unstable rock geometric features with regional changes;

[0025] Generate global features from the time series features and the spatial features.

[0026] According to some embodiments of the first aspect of the present application, constructing an unstable rock three-dimensional model according to the unstable rock features includes:

[0027] Obtain a mesh model according to the unstable rock features through Poisson reconstruction, surface reconstruction by spherical wave transformation, voxelization, and fusion of voxels;

[0028] Generate the geometric shape and topological structure of the unstable rock according to the unstable rock features;

[0029] Combine the geometric shape and topological structure of the dangerous rock with the mesh model to construct a 3D model of the dangerous rock.

[0030] According to some embodiments of the first aspect of the present application, the stability and change trend of the dangerous rock are predicted based on the 3D model of the dangerous rock to obtain dangerous rock warning information, including:

[0031] Monitor the dangerous rocks in the target area to obtain monitoring data;

[0032] Input the monitoring data into the 3D model of the dangerous rock to extract the spatio-temporal characteristics of the dangerous rock at the current timestamp;

[0033] Update the geological monitoring indicators for the next timestamp according to the dynamic changes of the dangerous rock characteristics, and obtain the spatio-temporal characteristics of the dangerous rock for the next timestamp based on the spatio-temporal characteristics of the dangerous rock at the current timestamp and the geological monitoring indicators for the next timestamp;

[0034] Predict the stability and change trend based on the spatio-temporal characteristics of the dangerous rock at the current timestamp and the spatio-temporal characteristics of the dangerous rock for the next timestamp to obtain dangerous rock warning information.

[0035] According to some embodiments of the first aspect of the present application, after predicting the stability and change trend based on the 3D model of the dangerous rock to obtain dangerous rock warning information, the method includes:

[0036] Conduct a sensitivity analysis based on the dangerous rock warning information to determine the risk level and the corresponding response facilities;

[0037] Combine the dangerous rock warning information with geographic information to generate a risk zoning map;

[0038] Import the monitoring data, dangerous rock warning information, and risk zoning map into a geographic information system to obtain the displacement vector field of the dangerous rock, crack propagation information, dangerous rock collapse movement path, and threat area.

[0039] Embodiments of the second aspect of the present application, a dangerous rock warning system, include:

[0040] A data collection unit for obtaining geological point cloud data of the target area;

[0041] A feature extraction unit for extracting local features of the geological point cloud data, aggregating the local features to generate global features, and obtaining dangerous rock features based on the global features;

[0042] A model construction unit for constructing a 3D model of the dangerous rock based on the dangerous rock features;

[0043] A prediction unit for predicting the stability and change trend based on the 3D model of the dangerous rock to obtain dangerous rock warning information.

[0044] An embodiment of the third aspect of the present application is an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the dangerous rock warning method described in the embodiment of the first aspect of the present application is implemented.

[0045] An embodiment of the fourth aspect of the present application is a computer storage medium storing computer-executable instructions for executing the dangerous rock warning method described in the embodiment of the first aspect of the present application.

[0046] The above solution has at least the following beneficial effects: by extracting local features of geological point cloud data, aggregating local features to generate global features, and obtaining dangerous rock features according to the global features; constructing a three-dimensional model of dangerous rocks according to the dangerous rock features; predicting the stability and change trend according to the three-dimensional model of dangerous rocks to obtain dangerous rock warning information; being able to accurately predict the change trend using the three-dimensional model of dangerous rocks, improving the accuracy of dangerous rock warning, and satisfying the uncertainty analysis of the time of dangerous rock disasters according to the dynamic expression of the personalized features of dangerous rock hidden dangers, improving the reliability and accuracy of dangerous rock disaster warning, and providing a data basis for disaster prevention and mitigation work of geological disasters. Description of the Drawings

[0047] The drawings are used to provide a further understanding of the technical solution of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation to the technical solution of the present application.

[0048] Figure 1 It is a step diagram of the dangerous rock warning method;

[0049] Figure 2 It is a step diagram of obtaining geological point cloud data of the target area;

[0050] Figure 3 It is a step diagram of extracting local features of geological point cloud data;

[0051] Figure 4 It is a step diagram of aggregating local features to generate global features;

[0052] Figure 5 It is a step diagram of constructing a three-dimensional model of dangerous rocks according to the dangerous rock features;

[0053] Figure 6 It is a step diagram of predicting the stability and change trend according to the three-dimensional model of dangerous rocks to obtain dangerous rock warning information;

[0054] Figure 7 It is a step diagram of the response step. Detailed Embodiments

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following further elaborates on this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0056] It should be noted that although functional module division is carried out in the device schematic diagram and the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division in the device or a different sequence in the flowchart. Terms such as "first" and "second" in the description, claims, or the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0057] The following further elaborates on the embodiments of this application in conjunction with the accompanying drawings.

[0058] The embodiments of this application provide a dangerous rock warning method.

[0059] Referring to Figure 1 , the dangerous rock warning method includes the following steps:

[0060] Step S100: Obtain the geological point cloud data of the target area;

[0061] Step S200: Extract the local features of the geological point cloud data, aggregate the local features to generate global features, and obtain the dangerous rock features according to the global features;

[0062] Step S300: Construct a three-dimensional model of the dangerous rock according to the dangerous rock features;

[0063] Step S400: Predict the stability and change trend according to the three-dimensional model of the dangerous rock to obtain the dangerous rock warning information.

[0064] Referring to Figure 2 , for step S100, obtaining the geological point cloud data of the target area includes the following steps:

[0065] Step S110: Generate dense point cloud data according to the multi-view images of the target area;

[0066] Step S120: Align, register, and fuse the dense point cloud data to obtain preprocessed point cloud data;

[0067] Step S130: Use the rock mass structure characteristics of the historical dangerous rock data as the initial clustering centers to cluster the preprocessed point cloud data to obtain the geological point cloud data of the target area.

[0068] Exemplarily, multi-view images of the target area are obtained, and dense point cloud data is generated based on the multi-view images of the target area. Denoising filtering is performed on the dense point cloud through radius filtering to eliminate interferences such as vegetation and artificial facilities. The iterative closest point algorithm suitable for surface registration is used to align, register, and fuse multi-site point clouds, and through its objective function minimize the mean square error between corresponding points, use statistical methods to remove mismatched point pairs, assign weights to different point pairs to reduce the influence of noise, first perform rough registration on the low-resolution point cloud, and then gradually refine it to obtain the geological environment data of the target area from multi-view images of large-scale complex terrain as preprocessed point cloud data.

[0069] Pre-classify the preprocessed multi-source point cloud data; use the existing historical dangerous rock data as a sample data set, and cluster the sample data set according to the rock mass structure characteristics of the disaster body samples. Cluster processing of the rock mass structure characteristics is performed through the geometric skeleton, color information, and normal vector of the dangerous rock point cloud data to obtain the rock mass structure characteristics of the target area.

[0070] Use the rock mass structure characteristics as the initial clustering centers in the clustering process; assign the dangerous rock sample point cloud data in the sample data set to the nearest initial clustering center, obtain the clusters corresponding to the initial clustering centers, update the clustering centers, and obtain the final clustering result through iterative clustering to obtain the geological point cloud data of the target area and generate a dangerous rock point cloud data set.

[0071] Obtain the rock mass structure characteristics of the target area, use the point cloud data with multiple attributes to describe complex geometric shapes and physical properties in three-dimensional space, providing a rich information basis for subsequent processing and analysis. Obtain point cloud data with millimeter-level accuracy through lidar scanning, preprocess the data of the surface and surrounding terrain of the dangerous rock mass, use the iterative closest point algorithm to gradually reduce the distance between the source point cloud and the target point cloud, improve the robustness of registration by extracting local features of the point cloud, and use neural networks to learn the internal features of the point cloud to improve the registration accuracy. Obtain the registration of the rock mass structure characteristics in the target area, pre-classify the preprocessed cloud data according to the position and characteristics of the dangerous rocks, and screen the potential hazard locations of the dangerous rocks in the target area.

[0072] Point clouds have characteristics such as disorder, sparsity, and unstructuredness. The core goal of point cloud segmentation is to divide the points in the three-dimensional point cloud into different semantic categories or instances. The role of the multi-layer perceptron (MLP) in point cloud processing is feature extraction and local feature learning. Through fully connected layers and non-linear activation functions, the MLP maps the original point coordinates or low-dimensional features to a high-dimensional hidden space, captures local geometric patterns, independently processes all points within the neighborhood through the MLP layer with shared weights, and combines pooling operations (such as max pooling) to extract robust features of the local area. Using point cloud segmentation technology and the multi-layer perceptron to extract the local features of the point cloud, and then applying the max pooling operation to aggregate the features of all points to generate a global feature vector, forming the dangerous rock features.

[0073] Refer to Figure 3 , for step S200, extracting the local features of the geological point cloud data includes the following steps:

[0074] Step S211, performing point cloud segmentation on the geological point cloud data to classify each point of the geological point cloud data;

[0075] Step S212, performing neighborhood sampling on each classified point to obtain local information and aggregating the local information;

[0076] Step S213, capturing local geometric detail information according to the local information;

[0077] Step S214, splicing the low-level local features and high-level local features in the local geometric detail information to obtain the local features of the geological point cloud data.

[0078] Exemplarily, obtain the hidden danger locations of dangerous rocks in the target area, extract the point cloud data corresponding to the hidden danger locations of the dangerous rocks, perform point cloud segmentation on the geological point cloud data, and classify each point in the geological point cloud data into different object types. Sample the neighborhood of each point to form a local point set to obtain local information. Use the MLP with shared weights to process each point and its neighborhood, and then aggregate the local information. Use multiple stacked MLP modules and pooling modules to capture local geometric details, splice the low-level local features and high-level features to obtain local features, improve the ability to retain details, and refine the segmentation result through graph optimization.

[0079] Refer to Figure 4 , aggregating local features to generate global features includes the following steps:

[0080] Step S221, obtaining the dangerous rock geometric features from the local features;

[0081] Step S222, calculating the dynamic time warping distance of the time series corresponding to the dangerous rock geometric features of different fine-grained levels;

[0082] Step S223: Minimize the dynamic time warping distance to align the time series corresponding to the geometric features of the dangerous rock, and obtain the time series features;

[0083] Step S224: Obtain the spatial features based on the geometric features of the dangerous rock with regional changes;

[0084] Step S225: Generate the global features from the time series features and the spatial features.

[0085] Through curvature and normal vector analysis, identify the steep faces, concave and convex regions (potential instability surfaces) of the dangerous rock. Based on region growing and clustering (such as DBSCAN), segment the fracture point cloud to obtain the geometric features of the dangerous rock. Extract parameters such as fracture length, width, dip angle, and connectivity to obtain the fracture parameters of the dangerous rock as the geometric features of the dangerous rock.

[0086] Calculate the dynamic time warping distance of the time series corresponding to the geometric features of the dangerous rock with different fine-grained levels through the dynamic time warping algorithm. Use the minimized dynamic time warping distance to align different time series deformation sequences, and obtain the spatial features according to the geometric features with regional changes. Generate the global feature vector from the time series features and the spatial features.

[0087] Obtain the hidden danger features of the dangerous rock disaster according to the time series features and the spatial features.

[0088] Refer to Figure 5 , for step S300, construct the 3D model of the dangerous rock according to the features of the dangerous rock, including the following steps:

[0089] Step S310: Obtain the mesh model according to the features of the dangerous rock through Poisson reconstruction, surface reconstruction by spherical wave transformation, voxelization, and voxel fusion;

[0090] Step S320: Generate the geometric shape and topological structure of the dangerous rock according to the features of the dangerous rock;

[0091] Step S330: Combine the geometric shape and topological structure of the dangerous rock with the mesh model to construct the 3D model of the dangerous rock.

[0092] Exemplarily, register and splice the point cloud data from multiple perspectives together to form an initial model. Through Poisson reconstruction and surface reconstruction by spherical wave transformation, as well as voxelization that divides the point cloud data into a series of small cubes, obtain the mesh model through voxel fusion and refinement; use ICP to align the multi-site point clouds, and use various algorithms (such as PointNet, NPGA, and 3DGaussian Splattering, etc.) for triangulation, surface fitting, or deep learning generation. Combine the geometric shape and topological structure of the dangerous rock with the mesh model to construct the 3D model of the dangerous rock.

[0093] Refer to Figure 6, for step S400, predicting the stability and change trend based on the 3D model of dangerous rocks to obtain dangerous rock warning information, including the following steps:

[0094] Step S410, monitoring the dangerous rocks in the target area to obtain monitoring data;

[0095] Step S420, inputting the monitoring data into the 3D model of dangerous rocks to extract the spatio-temporal characteristics of the dangerous rocks at the current timestamp;

[0096] Step S430, updating the geological monitoring indicators for the next timestamp according to the dynamic changes of the characteristics of dangerous rocks, and obtaining the spatio-temporal characteristics of the dangerous rocks at the next timestamp based on the spatio-temporal characteristics of the dangerous rocks at the current timestamp and the geological monitoring indicators at the next timestamp;

[0097] Step S440, predicting the stability and change trend based on the spatio-temporal characteristics of the dangerous rocks at the current timestamp and the spatio-temporal characteristics of the dangerous rocks at the next timestamp to obtain dangerous rock warning information.

[0098] Exemplarily, dynamic detection of the dangerous rocks in the target area is carried out to obtain monitoring data. The means of the dynamic monitoring department can adopt airborne LiDAR of drones, 3D laser scanning, etc., and adopt regular data collection and fixed acquisition technical parameters. The dynamic monitoring data is preprocessed by denoising, filtering, and interpolation, and then index calculations are carried out, such as displacement rate, acceleration, crack propagation rate, etc., to obtain monitoring data.

[0099] Input the monitoring data into the 3D model of dangerous rocks to extract the spatio-temporal characteristics of the dangerous rocks at the current timestamp. Extract the spatial attributes corresponding to the dangerous rocks from the monitoring data, and import the obtained time series of index characteristics with spatial attributes into the gated recurrent unit to obtain the spatio-temporal characteristics of the dangerous rocks at the current timestamp.

[0100] Update the geological monitoring indicators for the next monitoring timestamp according to the dynamic changes of the hidden danger characteristics of dangerous rocks, and use the 3D model of dangerous rock disasters to obtain the spatio-temporal characteristics of dangerous rocks at the next monitoring timestamp; according to the spatio-temporal characteristics of the positions of dangerous rocks at adjacent timestamps, import the 3D model into a mathematical analysis model, such as time series analysis and regression analysis, to predict the change trend of dangerous rocks, and through mechanical models such as the limit equilibrium method and deformation threshold, combined with geological environmental factors, simulate the stress distribution and instability conditions, and conduct sensitivity analysis and stability evaluation of dangerous rocks.

[0101] It should be noted that using lidar to generate high-precision 3D point clouds is suitable for large-scale or complex surface objects; using a laser rangefinder for single-point or multi-point ranging is suitable for small targets or low-cost scenarios. Mark the data collected each time through timestamps and spatial coordinate systems (such as WGS84 or local coordinate systems) to ensure data alignment and data synchronization. In terms of environmental control, set fixed reference points near the object to assist data alignment and error correction.

[0102] It should be noted that the coordinate differences of each point of the registered point cloud are calculated to generate a displacement vector field. At the same time, the center of gravity, volume or surface curvature change of the point cloud is calculated using the three-dimensional model to realize the stability evaluation of the quantitative difference analysis of dangerous rocks. By increasing the acquisition frequency or using a phase-type lidar (such as FMCW LiDAR) to improve the ranging resolution and enhance the detection of small displacements, a displacement threshold (such as 5 mm) is set, and an object movement is considered if the threshold is exceeded.

[0103] For the change rate of dangerous rocks, according to the displacement rate threshold method of the specification, a critical displacement rate (such as 10 mm / day) is set, and the acceleration analysis is used to judge the accelerated deformation stage by using the second derivative of displacement. For the prediction of the displacement trend of dangerous rocks, the statistical model grey system theory (GM(1,1)) is used to predict the displacement trend of dangerous rocks. The machine learning models LSTM neural network and random forest regression are used to train historical data to predict the future deformation of dangerous rocks. At the same time, a rainfall infiltration model (such as GreenAmpt) and seismic response analysis are introduced to simulate the influence of external incentives on stability.

[0104] After predicting the stability and change trend based on the three-dimensional model of dangerous rocks and obtaining the early warning information of dangerous rocks, the method includes response steps. Refer to Figure 7 , and the response steps include the following steps:

[0105] Step S510, perform sensitivity analysis according to the early warning information of dangerous rocks to determine the danger level and the corresponding response facilities;

[0106] Step S520, combine the early warning information of dangerous rocks with geographical information to generate a risk zoning map;

[0107] Step S530, import the monitoring data, the early warning information of dangerous rocks, and the risk zoning map into the geographical information system to obtain the displacement vector field, crack propagation information, collapse movement path and threat area of dangerous rocks.

[0108] Exemplarily, according to the stability evaluation and change trend of dangerous rocks, sensitivity analysis or probability assessment is carried out to determine the danger level, and emergency plans and evacuation routes are planned. Based on geological disaster prevention and control, in the early warning system, yellow, orange, and red warning levels and corresponding response measures are set. Using a geographic information system platform, three-dimensional models, and dynamic charts, the monitoring data is combined with geographic information to generate a heat map or a risk zoning map. Based on indicators such as deformation amount, acceleration, and crack density, the fuzzy comprehensive evaluation method is used to divide the danger levels of target dangerous rocks, such as high, medium, and low danger levels. The monitoring data, model prediction results, and risk zoning map are imported into the geographic information system platform to construct a three-dimensional model of the dangerous rock mass. By overlaying terrain data on the geographic information system platform, the displacement vector field and crack propagation animation are displayed in real time, the collapse movement path of the dangerous rock is simulated, the threatened area is calculated, the risk level distribution is shown in the heat map, and the population density and infrastructure layers are overlaid to construct a three-dimensional visualization platform. Based on the threat range interval of dangerous rock hidden dangers, different levels of early warnings are generated according to the disaster range interval. Based on the early warning information, relevant knowledge graphs are connected for regional risk avoidance decision-making. The visualization interface supports real-time query of monitoring data, early warning information, and the emergency plan library.

[0109] The dangerous rock early warning method includes data collection, dangerous rock hidden danger identification, dynamic monitoring, early warning model, and early warning processing.

[0110] By obtaining multi-source point cloud data of the target area, the point cloud data includes key attributes such as spatial coordinates, color information, and normal vectors. Methods such as the iterative closest point algorithm and the FINet algorithm are used to solve problems such as data noise and local optimal solutions faced in point cloud registration. Through the preprocessed multi-source point cloud data, data fusion analysis and feature extraction are carried out to identify and screen the locations of dangerous rock hidden dangers in the target area. Based on the point cloud data of the dangerous rock hidden danger locations, a three-dimensional model of the dangerous rock is established, and the existing deformation and crack characteristics of the dangerous rock are obtained. Based on the block theory, the potential sliding surface and separated bodies are analyzed. According to the characteristics of the dangerous rock hidden dangers, through regular multi-dimensional monitoring, multi-dimensional and multi-period point cloud differential detection data for crack propagation or displacement change monitoring are obtained. Based on the multi-dimensional monitoring data, hierarchical feature fusion and feature extraction are carried out to construct a dangerous rock early warning model, dynamically judge the change trend of the dangerous rock mass, and carry out danger analysis and risk avoidance decision-making according to the change trend. The danger analysis and risk avoidance decision-making of the dangerous rock are visually expressed to obtain the interactive information of the danger analysis and risk avoidance decision-making, and the dangerous rock hidden danger early warning model is dynamically corrected according to the interactive information.

[0111] By dynamically expressing the personalized characteristics of dangerous rock hidden dangers, it meets the uncertainty analysis of the time of dangerous rock disasters, improves the reliability and accuracy of dangerous rock disaster early warnings, and provides a data basis for the disaster prevention and mitigation work of geological disasters.

[0112] An embodiment of the present application provides a dangerous rock early warning system.

[0113] The dangerous rock warning system includes: a data collection unit, a feature extraction unit, a model construction unit, and a prediction unit.

[0114] Among them, the data collection unit is used to obtain the geological point cloud data of the target area; the feature extraction unit is used to extract the local features of the geological point cloud data, aggregate the local features to generate global features, and obtain dangerous rock features according to the global features; the model construction unit is used to construct a three-dimensional model of dangerous rocks according to the dangerous rock features; the prediction unit is used to predict the stability and change trend according to the three-dimensional model of dangerous rocks to obtain dangerous rock warning information.

[0115] It can be understood that the dangerous rock warning system in this embodiment adopts the above-mentioned dangerous rock warning method. Each unit of the dangerous rock warning system corresponds to each step of the dangerous rock warning method. The dangerous rock warning system and the dangerous rock warning method have the same technical solution, solve the same technical problems, and have the same technical effects.

[0116] An embodiment of the present application provides an electronic device. The electronic device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned dangerous rock warning method.

[0117] The electronic device can be any intelligent terminal including a computer, etc.

[0118] Generally speaking, for the hardware structure of the electronic device, the processor can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing relevant programs to implement the technical solution provided by the embodiment of the present application.

[0119] The memory can be implemented in forms such as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory can store an operating system and other application programs. When implementing the technical solution provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory and are called by the processor to execute the method of the embodiments of the present application.

[0120] The input / output interface is used to implement information input and output.

[0121] The communication interface is used to implement the communication interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WI FI, Bluetooth, etc.).

[0122] The bus transmits information between various components of the device (such as the processor, memory, input / output interface, and communication interface). The processor, memory, input / output interface, and communication interface are communicatively connected to each other within the device through the bus.

[0123] Embodiments of the present application provide a computer storage medium. The computer storage medium stores computer-executable instructions for executing the rockfall warning method as described above.

[0124] Those of ordinary skill in the art will appreciate that all or some of the steps and systems disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium typically contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium. In the above description of this specification, the description referring to the terms "one embodiment / embodiment", "another embodiment / embodiment", or "certain embodiments / embodiments", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0125] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in systems and devices, can be implemented as software, firmware, hardware, or a suitable combination thereof.

[0126] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store programs.

[0129] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms. Although the embodiments of the present application have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and purpose of the present application. The scope of the present application is defined by the claims and their equivalents. The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the embodiments. Those skilled in the art can make various equivalent deformations or substitutions without violating the spirit of the present application, and these equivalent deformations or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for warning of dangerous rocks, characterized in that, Including: Obtain the geological point cloud data of the target area; Extract the local features of the geological point cloud data, aggregate the local features to generate global features, and obtain the dangerous rock features according to the global features; Construct a 3D model of dangerous rocks according to the dangerous rock features; Perform stability and change trend prediction according to the 3D model of dangerous rocks to obtain dangerous rock warning information.

2. The dangerous rock warning method according to claim 1, characterized in that The obtaining of the geological point cloud data of the target area includes: Generate dense point cloud data according to the multi-view images of the target area; Perform alignment registration and fusion on the dense point cloud data to obtain preprocessed point cloud data; Use the rock mass structure characteristics of historical dangerous rock data as the initial clustering centers to cluster the preprocessed point cloud data to obtain the geological point cloud data of the target area.

3. The rockfall warning method according to claim 1, wherein The extraction of the local features of the geological point cloud data includes: Perform point cloud segmentation on the geological point cloud data and classify each point of the geological point cloud data; Perform neighborhood sampling on each classified point to obtain local information and aggregate the local information; Capture local geometric detail information according to the local information; Stitch the low-level local features and high-level local features in the local geometric detail information to obtain the local features of the geological point cloud data.

4. The rockfall warning method according to claim 1, wherein The aggregation of the local features to generate global features includes: Obtain the dangerous rock geometric features from the local features; Calculate the dynamic time warping distance of the time series corresponding to the dangerous rock geometric features of different fine-grained levels; Minimize the dynamic time warping distance to align the time series corresponding to the dangerous rock geometric features to obtain time series features; Obtain spatial features according to the dangerous rock geometric features of regional changes; Generate global features from the time series features and the spatial features.

5. The rockfall warning method according to claim 1, characterized in that, The construction of the 3D model of dangerous rocks according to the dangerous rock features includes: Obtain a mesh model according to the dangerous rock features through Poisson reconstruction, surface reconstruction by spherical wave transformation, voxelization, and fusion of voxels; Generate the geometric shape and topological structure of the dangerous rocks according to the dangerous rock features; Combine the geometric shape and topological structure of the dangerous rocks with the mesh model to construct a 3D model of dangerous rocks.

6. The rockfall warning method according to claim 1, wherein The stability and change trend prediction according to the 3D model of dangerous rocks to obtain dangerous rock warning information includes: Monitor the dangerous rocks in the target area to obtain monitoring data; Input the monitoring data into the 3D model of dangerous rocks to extract the spatio-temporal features of the dangerous rocks at the current timestamp; Update the geological monitoring indicators at the next timestamp according to the dynamic changes of the dangerous rock features, and obtain the spatio-temporal features of the dangerous rocks at the next timestamp according to the spatio-temporal features of the dangerous rocks at the current timestamp and the geological monitoring indicators at the next timestamp; Perform stability and change trend prediction according to the spatio-temporal features of the dangerous rocks at the current timestamp and the spatio-temporal features of the dangerous rocks at the next timestamp to obtain dangerous rock warning information.

7. The dangerous rock warning method according to claim 6, wherein After the stability and change trend prediction according to the 3D model of dangerous rocks to obtain dangerous rock warning information, the method includes: Perform sensitivity analysis according to the dangerous rock warning information to determine the danger level and the corresponding response facilities; Combine the dangerous rock warning information with geographical information to generate a risk zoning map; Import the monitoring data, dangerous rock warning information, and risk zoning map into the geographic information system to obtain the displacement vector field of the dangerous rock, crack expansion information, dangerous rock collapse movement path, and threat area.

8. A dangerous rock warning system, characterized in that, Including: A data collection unit for acquiring the geological point cloud data of the target area; A feature extraction unit for extracting local features of the geological point cloud data, aggregating the local features to generate global features, and obtaining dangerous rock features based on the global features; A model construction unit for constructing a three-dimensional model of the dangerous rock according to the dangerous rock features; A prediction unit for predicting the stability and change trend based on the three-dimensional model of the dangerous rock to obtain dangerous rock warning information.

9. An electronic device, characterized in that, Including: A memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the dangerous rock warning method according to any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium, characterized in that, Stored with computer-executable instructions for executing the dangerous rock warning method according to any one of claims 1 to 7.

Images