A sky-ground integrated highway multi-source three-dimensional rock and soil disaster identification system

Abstract

The present invention discloses a highway multi-source stereoscopic rock and soil disaster identification system integrating sky and ground, including a satellite monitoring subsystem for screening the road environment to be monitored for disaster hazards by using satellite monitoring, combined with InSAR technology and optical images; an aviation monitoring subsystem for obtaining optical images and point cloud data of the road environment to be monitored by aerial photography, and identifying the road environment for disaster hazards; and a ground monitoring subsystem for verifying and optimizing the results of disaster hazard screening and disaster hazard identification by manual verification. The present invention extracts multi-source data of the road environment, and screens and identifies the road disaster hazards respectively, and finally optimizes the screening and identification results, effectively improving the early identification capability of rock and soil geological disasters, effectively reducing the threat of geological disasters to highways, and comprehensively improving the comprehensive prevention and control capabilities of geological disasters in the transportation field.

Description

Technical Field

[0001] The invention belongs to the technical field of road disaster identification, and in particular relates to a highway multi-source three-dimensional rock and soil disaster identification system integrating sky and ground. Background Art

[0002] In the highway environment, major geological disaster hazards are often concealed, sudden, uncertain and other complex characteristics, which greatly increases the difficulty of active prevention and monitoring and early warning. The traditional geological disaster prevention and control method is mainly through regular on-site investigation by personnel in early identification. However, manual investigation alone is not only labor-intensive and inefficient, but even impossible to achieve in some areas. Manual monitoring methods such as GPS, level, total station, close-range photogrammetry and displacement meter are used at high-risk points. Although these monitoring technologies have made considerable achievements in geological disaster monitoring and prediction research, and have accumulated rich practical experience, making breakthrough progress in disaster early warning, there are still some obvious shortcomings under special conditions:

[0003] (1) Manual investigation is labor-intensive, inefficient, and relies solely on the naked eye to identify early geological hazards;

[0004] (2) The areas where landslides, mudslides and other disasters occur are usually high mountainous and densely forested areas with harsh geological environments, which are difficult to reach manually;

[0005] (3) Traditional measurement methods (level, total station, close-range photogrammetry) require relevant staff to arrive at the site to observe and record a large amount of field measurement data. As a result, there will be problems such as large computing workload, low work efficiency, and high costs. Summary of the invention

[0006] The purpose of the present invention is to provide a highway multi-source three-dimensional rock and soil disaster identification system integrating sky and ground to solve the problems existing in the above-mentioned prior art.

[0007] To achieve the above-mentioned purpose, the present invention provides a highway multi-source three-dimensional rock and soil disaster identification system integrating sky and ground, comprising a satellite monitoring subsystem, an aviation monitoring subsystem, and a ground monitoring subsystem connected in sequence;

[0008] The satellite monitoring subsystem is used to screen for disaster hazards in the road environment to be monitored by using satellite monitoring methods combined with InSAR technology and optical imaging;

[0009] The aerial monitoring subsystem is used to obtain optical images and point cloud data of the road environment to be monitored by aerial photography, and identify disaster hazards in the road environment;

[0010] The ground monitoring subsystem is used to verify and optimize the results of disaster hazard screening and disaster hazard identification by manual verification.

[0011] Optionally, the satellite monitoring subsystem includes an InSAR analysis module and a high-resolution image analysis module;

[0012] The InSAR analysis module includes a plurality of interferometric radars, which are used to extract the deformation field in the road environment, obtain the large-scale deformation and the time series deformation according to the deformation field, and obtain the deformation characteristics according to the large-scale deformation and the time series deformation;

[0013] The high-resolution image analysis module includes a plurality of imaging spectrometers, through which the landslide morphology and ground feature classification information of the road environment are extracted, a geological disaster database is constructed based on the landslide morphology and ground feature classification information, and the disaster distribution law and geological disaster susceptibility evaluation results are obtained.

[0014] Optionally, the satellite monitoring subsystem also includes a disaster screening module, which obtains the surface deformation rate, land feature classification, ground inversion temperature, vegetation coverage factor according to the deformation characteristics and the geological disaster susceptibility assessment results, and constructs a geological hazard knowledge map, determines the key factors for the occurrence of geological disasters according to the geological hazard knowledge map, and uses machine learning methods to extract geological disasters based on the landslide morphology and land feature classification information obtained in real time.

[0015] Optionally, the disaster screening module uses a convolutional neural network to construct a disaster extraction model, and obtains the landslide morphology, land feature classification information and the key factors stored in the geological disaster database to construct a training set, trains the disaster extraction model, and uses the trained disaster extraction model to extract geological disasters from the landslide morphology and land feature classification information obtained in real time.

[0016] Optionally, the aviation monitoring subsystem includes a drone aerial photography module and a drone iDAR module;

[0017] The drone aerial photography module includes a plurality of drones, each of which is equipped with a high-resolution optical camera, and a two-dimensional optical image of the road environment is obtained through the high-resolution optical camera;

[0018] The drone iDAR module includes a plurality of laser scanners, which are all arranged on the aerial photography drone, and the three-dimensional point cloud data of the road environment is acquired through the laser scanners.

[0019] Optionally, the aerial monitoring subsystem also includes a risk analysis module, which constructs a digital surface model based on the two-dimensional optical image and the three-dimensional point cloud data, removes vegetation from the digital surface model using a filtering algorithm, and uses two-dimensional and three-dimensional interpretation methods to identify potential hidden dangers of geological disasters such as collapsed loose accumulations, ancient landslide accumulations, debris flow accumulation fans, and larger cracks in the mountain that are prone to geological disasters.

[0020] Optionally, the filtering algorithm includes but is not limited to slope filtering, wavelet layered filtering, and pseudo-scan line filtering algorithm; the two-dimensional and three-dimensional interpretation methods include but are not limited to point cloud feature extraction, point cloud registration, and point cloud segmentation.

[0021] Optionally, the ground monitoring subsystem includes a manual verification module and a verification analysis module; when the manual verification module is used to generate disaster hazard screening results and disaster hazard identification results, it adopts a manual dispatch method to conduct on-site field investigations on the road environment to obtain investigation results including disaster occurrence, stratum lithology and landslide characteristics; the verification analysis module compares and analyzes the investigation results with the generated disaster hazard screening results and disaster hazard identification results. When the comparison results are inconsistent, the disaster extraction model and the digital surface model are optimized according to the investigation results.

[0022] The technical effects of the present invention are:

[0023] The present invention adopts the integrated air-space-ground monitoring technology to construct a multi-source stereoscopic observation system for transportation geological disasters, and adopts InSAR technology, laser point cloud technology, and optical imaging technology to extract multi-source data of the road environment, and adopts machine learning algorithm, point cloud filtering algorithm and point cloud interpretation method to screen and identify road disaster hazards. Finally, manual verification is used to optimize the screening and identification results, which effectively improves the early identification capability of rock and soil geological disasters, effectively reduces the threat of geological disasters to highways, and comprehensively enhances the comprehensive prevention and control capabilities of geological disasters in the transportation field. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 It is a framework diagram of a highway multi-source three-dimensional rock and soil disaster identification system in an embodiment of the present invention;

[0026] Figure 2 This is a relationship diagram of multi-source three-dimensional data of space, ground and sky in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Embodiment 1

[0030] like Figure 1-2 As shown, this embodiment provides a highway multi-source three-dimensional rock and soil disaster identification system integrating sky and ground, including:

[0031] Geological disaster survey based on satellite platform

[0032] "Tian" refers to the satellite remote sensing platform, which mainly uses the method of InSAR combined with optical remote sensing. The platform has the advantages of high working efficiency and large monitoring area, including InSAR analysis module, high-resolution image analysis module and disaster screening module;

[0033] The high-resolution image analysis module includes several imaging spectrometers. Through the imaging spectrometers, optical remote sensing is used to extract information such as landslide morphology and ground feature classification. In the InSAR analysis module, several interferometric radars are used to extract deformation fields. Through the disaster screening module, a geological hazard knowledge map is constructed based on the acquired surface deformation rate, ground feature classification, ground inversion temperature, vegetation coverage and other factors. The characteristics and correlation of the three elements of the typical landslide hazard, namely, the disaster-prone environment (geological structure, hydrological conditions, surface undulation, surface coverage, etc.), inducing factors (precipitation, soil freezing and thawing, etc.), and change signs (displacement, settlement, etc.), are constructed to analyze the characteristics and formation conditions of major geological disasters, and screen and determine the key factors for the occurrence of geological disasters. Through the analysis and calculation of disaster-causing factors, an automatic identification system for geological disasters is established, and machine learning methods are used to achieve automatic or semi-automatic extraction of geological disasters.

[0034] Specifically, the disaster screening module uses a convolutional neural network to construct a disaster extraction model, and obtains the landslide morphology, land feature classification information and the key factors stored in the geological disaster database to construct a training set, trains the disaster extraction model, and uses the trained disaster extraction model to extract geological disasters from the landslide morphology and land feature classification information obtained in real time, thereby completing a detailed investigation of geological disasters.

[0035] Detailed investigation of geological hazards based on airborne platforms

[0036] “Air” refers to the airborne platform, which mainly includes the drone aerial photography module, drone iDAR module and risk analysis module; among which:

[0037] The drone aerial photography module includes several drones, which are mainly equipped with GPS, IMU (inertial measurement), high-resolution optical camera (image acquisition) and other equipment to obtain optical image data of the road environment;

[0038] The UAV iDAR module includes several laser scanners installed on the UAV to acquire point cloud data of the road environment to be monitored;

[0039] Through laser scanners and high-resolution optical cameras, the three-dimensional coordinates and image data of the ground can be acquired synchronously, quickly and with high precision, and the three-dimensional real-time, changing and true morphological characteristics of the ground objects can be reproduced quickly and intelligently. The vertical displacement of the ground surface, volume change, and profiles before and after the change can be calculated.

[0040] Through the risk analysis module, point cloud data filtering algorithm technology is used for complex terrain with steep slopes and dense vegetation. The digital surface model (DSM) obtained by removing vegetation from LiDAR data is combined with two-dimensional and three-dimensional interpretation to identify potential hidden dangers of geological disasters such as collapsed loose accumulations, ancient landslide accumulations, debris flow accumulation fans and large shattered mountain cracks under vegetation coverage, so as to achieve a detailed investigation of high-risk areas for geological disasters; among them, filtering algorithms include but are not limited to slope filtering method, wavelet layered filtering method, and pseudo scanning line filtering algorithm; two-dimensional and three-dimensional interpretation methods include but are not limited to point cloud feature extraction, point cloud registration, and point cloud segmentation.

[0041] Ground inspection by geological personnel

[0042] "Ground" refers to ground geological verification, including manual verification module and verification analysis module. Through the manual verification module, professional geological personnel are dispatched to high-risk areas to conduct on-site field investigations, establish professional inspection forms, and inspect on-site conditions such as stratum lithology, occurrence, joints, drainage system, landslide characteristics, etc. The verification and analysis module verifies and supplements the results of the general survey and detailed investigation, and compares and analyzes the investigation results with the generated disaster hazard screening results and disaster hazard identification results. When the comparison results are inconsistent, the disaster extraction model and digital surface model are optimized according to the investigation results, and the general survey and detailed investigation algorithms are optimized.

[0043] Those skilled in the art will appreciate that embodiments of the present invention may be provided as systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0044] The present invention is described with reference to the flowcharts and / or block diagrams of computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0045] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0047] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A highway multi-source three-dimensional rock and soil disaster identification system integrating sky and ground, characterized in that: It includes a satellite monitoring subsystem, an aviation monitoring subsystem, and a ground monitoring subsystem connected in sequence; The satellite monitoring subsystem is used to screen for disaster hazards in the road environment to be monitored by using satellite monitoring methods combined with InSAR technology and optical imaging; The aerial monitoring subsystem is used to obtain optical images and point cloud data of the road environment to be monitored by aerial photography, and identify disaster hazards in the road environment; The ground monitoring subsystem is used to verify and optimize the results of disaster hazard screening and disaster hazard identification by manual verification; The satellite monitoring subsystem includes an InSAR analysis module and a high-resolution image analysis module; The InSAR analysis module includes a plurality of interferometric radars, which are used to extract the deformation field in the road environment, obtain the large-scale deformation and the time series deformation according to the deformation field, and obtain the deformation characteristics according to the large-scale deformation and the time series deformation; In the InSAR analysis module, deformation field extraction is performed through several interferometric radars, and through the disaster screening module, a geological hazard knowledge map is constructed based on the acquired surface deformation rate, ground feature classification, ground inversion temperature, and vegetation coverage factors. The disaster-prone environment in typical landslide hazards: geological structure, hydrological conditions, surface undulation, and surface coverage; inducing factors: precipitation, soil freeze-thaw, and change signs: the characteristics of the three elements of displacement and settlement and their correlation are constructed, the characteristics and formation conditions of major geological disasters are analyzed, and the key factors for the occurrence of geological disasters are screened and determined; through the analysis and calculation of disaster-causing factors, an automatic identification system for geological disasters is established, and machine learning methods are used to achieve automatic or semi-automatic extraction of geological disasters; The high-resolution image analysis module includes a plurality of imaging spectrometers, through which the landslide morphology and ground feature classification information of the road environment are extracted, a geological disaster database is constructed based on the landslide morphology and ground feature classification information, and the disaster distribution law and the geological disaster susceptibility evaluation results are obtained; The satellite monitoring subsystem also includes a disaster screening module, which obtains the surface deformation rate, ground feature classification, ground inversion temperature, and vegetation coverage factor according to the deformation characteristics and the geological disaster susceptibility evaluation results, and constructs a geological hazard knowledge map, determines the key factors of geological disasters according to the geological hazard knowledge map, and uses a machine learning method to extract geological disasters according to the landslide morphology and ground feature classification information obtained in real time; The disaster screening module uses a convolutional neural network to construct a disaster extraction model, obtains the landslide morphology, ground feature classification information and the key factors stored in the geological disaster database to construct a training set, trains the disaster extraction model, and uses the trained disaster extraction model to extract geological disasters from the landslide morphology and ground feature classification information obtained in real time; The aerial monitoring subsystem also includes a risk analysis module, which constructs a digital surface model based on two-dimensional optical images and three-dimensional point cloud data, removes vegetation from the digital surface model using a filtering algorithm, and uses two-dimensional and three-dimensional interpretation methods to identify potential hazards of collapsed loose accumulations, ancient landslide accumulations, debris flow accumulation fans, and larger cracks in the mountain body covered by vegetation; The filtering algorithms include slope filtering, wavelet layered filtering, and pseudo scanning line filtering algorithms; the two-dimensional and three-dimensional interpretation methods include point cloud feature extraction, point cloud registration, and point cloud segmentation.

2. The sky-ground integrated highway multi-source three-dimensional rock and soil disaster identification system according to claim 1 is characterized in that: The aviation monitoring subsystem includes a drone aerial photography module and a drone iDAR module; The drone aerial photography module includes a plurality of drones, each of which is equipped with a high-resolution optical camera, and a two-dimensional optical image of the road environment is obtained through the high-resolution optical camera; The drone iDAR module includes a plurality of laser scanners, which are all arranged on the aerial photography drone, and the three-dimensional point cloud data of the road environment is acquired through the laser scanners.

3. The sky-ground integrated highway multi-source three-dimensional rock and soil disaster identification system according to claim 1 is characterized in that: The ground monitoring subsystem includes a manual verification module and a verification analysis module; the manual verification module is used to generate disaster hazard screening results and disaster hazard identification results by using a manual dispatch method to conduct on-site field investigations on the road environment to obtain investigation results including disaster occurrence, stratum lithology and landslide characteristics; The verification and analysis module compares and analyzes the survey results with the generated disaster hazard screening results and disaster hazard identification results. When the comparison results are inconsistent, the disaster extraction model and the digital surface model are optimized according to the survey results.

Images