A rain-after railway geological disaster risk identification method based on automatic comparison

Abstract

The application discloses a kind of rain after railway geological disaster risk identification methods based on automatic comparison, it is related to geological disaster identification technical field.The steps are as follows: according to forecast rainfall data and real-time rainfall data, rain before image data acquisition and rain after image data acquisition;When rain before image and rain after image data are returned, three-dimensional modeling is carried out to the image data, and rain before railway geological three-dimensional model and rain after railway geological three-dimensional model are obtained;Geological disaster risk identification model based on image comparison algorithm is used to extract deformation area, and the risk probability and type of disaster occurrence are calculated according to the change of deformation area.The above-mentioned rain after railway geological disaster risk identification method based on automatic comparison is used, and the image data is obtained by triggering unmanned aerial vehicle to patrol according to forecast rainfall and real-time rainfall, and the rain after three-dimensional model is compared with the rain before three-dimensional model by comparison algorithm, and the geological disaster risk hidden danger is automatically identified, which improves the identification efficiency of geological disaster hidden danger.

Description

Technical Field

[0001] This invention relates to the field of geological disaster identification technology, and in particular to a method for identifying post-rain railway geological disaster risks based on automatic comparison. Background Technology

[0002] Railway flood control management is a crucial measure to ensure the safe operation of railways during flood season and heavy rain. Existing technologies involve data collection through sensor networks deployed at key locations. For example, patent CN118446869A discloses a railway flood control management system, including a data acquisition module. This module uses sensors to collect data from key flood control points in real time and employs drones to monitor and collect images along the railway line during extreme weather. However, this only achieves the monitoring function; manual image review and judgment are still required. Given the long distances along railway lines, this approach is time-consuming and labor-intensive, making it difficult to obtain timely disaster information. Furthermore, it only processes current images, but the difference between pre- and post-rain images often indicates the occurrence and presence of geological disasters. Therefore, there is an urgent need for an automatic comparison method for identifying post-rain railway geological disaster risks along railway lines. Summary of the Invention

[0003] The purpose of this invention is to provide a method for identifying post-rain railway geological disaster risks based on automatic comparison, thereby solving the above-mentioned technical problems.

[0004] To achieve the above objectives, this invention provides a method for identifying post-rain railway geological hazard risks based on automatic comparison, the specific steps of which are as follows:

[0005] Step S1: Acquire forecast rainfall data and real-time rainfall data in real time;

[0006] Step S2: Collect pre-rain image data and post-rain image data based on forecast rainfall data and real-time rainfall data;

[0007] Step S3: When transmitting the pre-rain and post-rain image data, perform 3D modeling on the image data to obtain the pre-rain railway geological 3D model and the post-rain railway geological 3D model;

[0008] Step S4: Input the pre-rain railway geological 3D model and the post-rain railway geological 3D model into the geological disaster risk identification model based on image comparison algorithm to extract the deformation area, and calculate the risk probability and type of disaster based on the change in the deformation area.

[0009] Preferably, in step S2, when the forecast rainfall is greater than the set rainfall, the drones in the drone library are triggered to collect pre-rain image data of the set railway line.

[0010] Real-time rainfall data is acquired. When the real-time rainfall is not greater than the set rainfall and the forecast rainfall within the set time interval is less than the set rainfall, the drones in the drone library are triggered to collect post-rain image data of the set railway line.

[0011] Preferably, the UAV is equipped with lidar and photogrammetry equipment to scan the railway line and obtain three-dimensional point cloud data of the geological conditions around the railway line.

[0012] Preferably, in step S3, data preprocessing is performed, including coordinate alignment and resolution unification of the 3D point cloud data; geological features are extracted from the preprocessed 3D point cloud data using a terrain feature extraction model, and the extracted features are represented as raster data, with the feature values ​​superimposed onto each cell grid; 3D modeling is performed using the extracted terrain data.

[0013] Preferably, in step S4,

[0014] Step S41: Extract the pre-rain and post-rain 3D geological model images of the railway at the same location;

[0015] Step S42: Compare the three-dimensional geological model of the railway before and after the rain point by point and pixel by pixel using the direct point cloud difference method and the feature change monitoring method, and calculate the change in feature values.

[0016] Step S43: Determine the deformation area based on the change in characteristic value, and obtain the risk probability and type of disaster based on the characteristic value and change characteristics of the identified change area.

[0017] In step S43, the change in eigenvalues ​​is calculated, which includes both temporal and spatial changes.

[0018] The formula for calculating the change over time is as follows:

[0019] ΔV t =V(t)-V(t-1)

[0020] Where, ΔV t V(t) represents the change in characteristic value over time, where V(t) is the characteristic value before the rain and V(t-1) is the characteristic value after the rain.

[0021] The formula for calculating spatial change is as follows:

[0022] ΔV s =V(x)-V(x-1)

[0023] Where V(x) is the feature value at a certain spatial location, V(x-1) is the feature value at adjacent locations, and ΔV s This represents the spatial variation of eigenvalues;

[0024] The conditions for determining the deformation region are as follows:

[0025] When |ΔV t |>T t or |ΔV S |>T s If T is a deformable region, then it is determined to be a deformable region. t T is the threshold for the change over time. s This is the threshold for spatial variation.

[0026] Preferably, in step S43,

[0027] The formula for calculating the probability of risk is as follows:

[0028]

[0029] Where P is the probability of a disaster occurring, and α and β are the weighting coefficients for the time variation and spatial variation, respectively.

[0030] Preferred disaster types include flooding, landslides, mudslides, mudslides, roadbed subsidence, and bridge and culvert damage.

[0031] Therefore, the above-mentioned method for identifying post-rain railway geological disaster risks based on automatic comparison has the following beneficial effects: Based on the forecast and real-time rainfall, the conditions for UAV patrol are triggered. Under the influence of meteorological environment, the UAV flies along the planned route to take aerial photographs of the surrounding environment in three dimensions. After the aerial photographs, the remote sensing image data is automatically transmitted to the data processing server. The post-rain three-dimensional model is compared and analyzed with the pre-rain three-dimensional model using a three-dimensional model comparison algorithm, automatically identifying potential geological disaster risks. This improves the efficiency of identifying potential geological disaster risks and enhances the technical defense capabilities of railway disaster prevention and flood control.

[0032] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0033] Figure 1 This is a flowchart of a method for identifying post-rain railway geological disaster risks based on automatic comparison, according to the present invention. Detailed Implementation

[0034] Example 1

[0035] like Figure 1 As shown, a method for identifying post-rain railway geological hazard risks based on automatic comparison is described, with the following specific steps:

[0036] Step S1: Acquire forecast rainfall data and real-time rainfall data in real time. Rainfall data is acquired by establishing a connection with the meteorological platform.

[0037] Step S2: Collect pre-rain and post-rain image data based on forecast and real-time rainfall data. When the forecast rainfall exceeds a set rainfall threshold, trigger drones from the drone library to collect pre-rain image data along the designated railway line. Real-time rainfall is acquired; when the real-time rainfall is not greater than the set rainfall threshold and the forecast rainfall is less than the set rainfall threshold within a set time interval, trigger drones from the drone library to collect post-rain image data along the designated railway line. The drones, equipped with lidar and photogrammetry equipment, scan the railway line to acquire 3D point cloud data of the surrounding geological conditions.

[0038] Step S3: When transmitting pre-rain and post-rain image data, 3D modeling is performed on the image data to construct 3D geological models of the railway before and after the rain. Data preprocessing includes coordinate alignment and resolution unification of the 3D point cloud data; geological features are extracted from the preprocessed 3D point cloud data using a terrain feature extraction model, with the extracted features represented as raster data, and the feature values ​​are overlaid into each cell grid; 3D modeling is then performed using the extracted terrain data.

[0039] Step S4: Input the pre-rain railway geological 3D model and the post-rain railway geological 3D model into the geological disaster risk identification model based on image comparison algorithm to extract the deformation area, and calculate the risk probability and type of disaster based on the change in the deformation area.

[0040] Step S41: Extract the pre-rain and post-rain 3D geological model images of the railway at the same location;

[0041] Step S42: Compare the three-dimensional geological model of the railway before and after the rain point by point and pixel by pixel using the direct point cloud difference method and the feature change monitoring method, and calculate the change in feature values.

[0042] Step S43: Determine the deformation area based on the change in characteristic values, and obtain the risk probability and type of disaster based on the characteristic values ​​and change characteristics of the identified deformation area. Disaster types include flooding, landslides, debris flows, mudslides, roadbed settlement, and bridge and culvert damage.

[0043] In step S43, the change in eigenvalues ​​is calculated, which includes both temporal and spatial changes.

[0044] The formula for calculating the change over time is as follows:

[0045] ΔV t =V(t)-V(t-1)

[0046] Where, ΔV t V(t) represents the change in characteristic value over time, where V(t) is the characteristic value before the rain and V(t-1) is the characteristic value after the rain.

[0047] The formula for calculating spatial change is as follows:

[0048] ΔV s =V(x)-V(x-1)

[0049] Where V(x) is the feature value at a certain spatial location, V(x-1) is the feature value at adjacent locations, and ΔV s This represents the spatial variation of eigenvalues;

[0050] The conditions for determining the deformation region are as follows:

[0051] When |ΔV t |>T t or |ΔV S |>T s If T is a deformable region, then it is determined to be a deformable region. t T is the threshold for the change over time. s This is the threshold for spatial variation.

[0052] Preferably, in step S43,

[0053] The formula for calculating the probability of risk is as follows:

[0054]

[0055] Where P is the probability of a disaster occurring, and α and β are the weighting coefficients for the time variation and spatial variation, respectively.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for identifying post-rain railway geological hazard risks based on automatic comparison, characterized in that, The specific steps are as follows: Step S1: Acquire forecast rainfall data and real-time rainfall data in real time; Step S2: Collect pre-rain image data and post-rain image data based on forecast rainfall data and real-time rainfall data; when the forecast rainfall is greater than the set rainfall, trigger the drones in the drone library to collect pre-rain image data of the set railway line. Real-time rainfall data is acquired. When the real-time rainfall is not greater than the set rainfall and the forecast rainfall within the set time interval is less than the set rainfall, the drones in the drone library are triggered to collect post-rain image data of the set railway line. Step S3: When transmitting the pre-rain and post-rain image data, perform 3D modeling on the image data to obtain the pre-rain railway geological 3D model and the post-rain railway geological 3D model; Step S4: Input the pre-rain railway geological 3D model and the post-rain railway geological 3D model into the geological disaster risk identification model based on image comparison algorithm to extract the deformation area, and calculate the risk probability and type of disaster based on the change in the deformation area; In step S4, Step S41: Extract the pre-rain and post-rain 3D geological model images of the railway at the same location; Step S42: Compare the three-dimensional geological model of the railway before and after the rain point by point and pixel by pixel using the direct point cloud difference method and the feature change monitoring method, and calculate the change in feature values. Step S43: Determine the deformation area based on the change in characteristic values, and obtain the risk probability and disaster type based on the characteristic values ​​and change characteristics of the identified change area; The change in eigenvalues ​​is calculated, including both temporal and spatial changes. The formula for calculating the change over time is as follows: in, V(t) represents the time change of the characteristic value, where V(t) is the characteristic value before the rain and V(t−1) is the characteristic value after the rain. The formula for calculating spatial change is as follows: Where V(x) is the feature value at a certain spatial location, and V(x−1) is the feature value at adjacent locations. This represents the spatial variation of eigenvalues; The conditions for determining the deformation region are as follows: when or If , then it is determined to be a deformation region, where , The threshold for the change over time. The threshold for spatial variation; The formula for calculating the probability of risk is as follows: Where P is the probability of the disaster occurring. and These are the weighting coefficients for time-varying and spatial-varying quantities, respectively.

2. The method for identifying post-rain railway geological hazard risks based on automatic comparison according to claim 1, characterized in that: The drone, equipped with lidar and photogrammetry equipment, scans the railway line to obtain three-dimensional point cloud data of the surrounding geological conditions.

3. The method for identifying post-rain railway geological hazard risks based on automatic comparison according to claim 2, characterized in that: In step S3, data preprocessing is performed, including coordinate alignment and resolution unification of the 3D point cloud data; geological features are extracted from the preprocessed 3D point cloud data using a terrain feature extraction model, and the extracted features are represented as raster data, with the feature values ​​superimposed onto each cell grid. 3D modeling is performed using extracted terrain data.

4. The method for identifying post-rain railway geological hazard risks based on automatic comparison according to claim 3, characterized in that: The types of disasters include flooding, landslides, mudslides, mudslides, roadbed subsidence, and damage to bridges and culverts.

Images