Method for monitoring settlement of engineering under railway line

Abstract

The invention discloses a railway line engineering settlement monitoring method which comprises the following steps: arranging a plurality of sensors for a monitoring area of a railway line engineering, and monitoring sensor-based settlement values of a plurality of settlement points in a monitoring period through the plurality of sensors; a camera is carried on an unmanned aerial vehicle, the unmanned aerial vehicle is controlled to fly along a railway line, and image data of a monitoring area of a project under the railway line in a monitoring period are collected through the camera; establishing three-dimensional point cloud data in the monitoring period according to the image data of the monitoring area in the monitoring period; determining photography-based settlement values of the plurality of settlement points in the monitoring period through the three-dimensional point cloud data in the monitoring period; and respectively distributing reliability weights for the settlement value based on the sensor and the settlement value based on the photography of each settlement point, and carrying out weighted average operation to obtain a fused settlement value. According to the invention, the accuracy and reliability of engineering settlement monitoring under the railway line can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of construction engineering, and in particular to a method for monitoring settlement of subgrade works of railways. Background Art

[0002] The settlement condition of subgrade works of railways is directly related to the safety and stability of railway operation. Traditional settlement monitoring methods, such as leveling method, total station trigonometric leveling method, etc., have problems such as low efficiency and being greatly affected by the environment; single sensor measurement method or photogrammetry method also has its own limitations. For example, although the sensor measurement method has high precision, the layout range of sensors is limited and it is difficult to comprehensively reflect the settlement conditions of large areas; although photogrammetry can achieve large-area monitoring, its precision is relatively low. Therefore, there is an urgent need for a settlement monitoring method that can comprehensively utilize the advantages of various measurement means to improve the accuracy and reliability of settlement monitoring of subgrade works of railways. Summary of the Invention

[0003] One object of the present invention is to solve at least the above problems and / or defects, and provide at least the advantages described hereinafter.

[0004] One object of the present invention is to provide a method for monitoring settlement of subgrade works of railways, which can improve the accuracy and reliability of settlement monitoring of subgrade works of railways.

[0005] To achieve these objects and other advantages according to the present invention, there is provided a method for monitoring settlement of subgrade works of railways, including:

[0006] Step 1: Sensor layout operation:

[0007] Arrange a plurality of sensors for the monitoring area of the subgrade works of railways, and monitor the settlement values of a plurality of settlement points based on the sensors in a monitoring period through the plurality of sensors; mount a camera on a drone, control the drone to fly along the railway line, and collect image data of the monitoring area of the subgrade works of railways in the monitoring period through the camera;

[0008] Step 2: Data processing operation:

[0009] Establish three-dimensional point cloud data in the monitoring period according to the image data of the monitoring area in the monitoring period; determine the settlement values based on photography of the plurality of settlement points in the monitoring period through the three-dimensional point cloud data in the monitoring period;

[0010] Step 3: Weight assignment and data fusion operation:

[0011] Assign reliability weights to the settlement values based on sensors and the settlement values based on photography for each settlement point respectively, perform weighted average operation, and obtain the fused settlement value. The calculation formula is:

[0012] $S_{fusion}=W_{sensor}×S_{sensor}+W_{photography}×S_{photography}$, where $S_{fusion}$ is the fused settlement value, $W_{sensor}$ and $W_{photography}$ are the weights of the settlement value based on the sensor and the settlement value based on photography respectively, and $S_{sensor}$ and $S_{photography}$ are the settlement value based on the sensor and the settlement value based on photography respectively.

[0013] Preferably, the settlement monitoring method for the subgrade works under the railway line further includes a fused value verification operation: select the settlement values based on the sensor and the settlement values based on photography at several settlement points and compare them with the fused settlement values of the corresponding settlement points respectively, calculate the error. If the error is within the preset allowable range, it is considered that the accuracy of the fused settlement value meets the standard; otherwise, adjust the weights of the settlement values based on the sensor and the settlement values based on photography.

[0014] Preferably, in the settlement monitoring method for the subgrade works under the railway line, the preset allowable range is ±2 mm.

[0015] Preferably, in the settlement monitoring method for the subgrade works under the railway line, in the first step, for different parts of the monitoring area, select corresponding types of sensors for layout, including: at the key positions of the subgrade, arrange a static level for monitoring the vertical settlement value; at the bridge piers and abutments, arrange strain gauge sensors for monitoring the settlement value caused by structural deformation.

[0016] Preferably, in the settlement monitoring method for the subgrade works under the railway line, in the third step, when a static level is used for a settlement point, set the weight of the settlement value based on the sensor of this settlement point to 0.7 and the weight of the settlement value based on photography to 0.3; when a strain gauge sensor is used for a settlement point, set the weight of the settlement value based on the sensor of this settlement point to 0.6 and the weight of the settlement value based on photography to 0.4.

[0017] Preferably, in the settlement monitoring method for the subgrade works under the railway line, in the third step, if the weather condition is poor, set the weight of the settlement value based on the sensor of this settlement point to 0.6 and the weight of the settlement value based on photography to 0.4; if the weather condition is good, set the weight of the settlement value based on the sensor to 0.5 and the weight of the settlement value based on photography to 0.5.

[0018] Preferably, in the settlement monitoring method for the subgrade works under the railway line, in the third step, if the standard deviation of the settlement value based on the sensor of a settlement point in a statistical time period is less than the standard deviation of the settlement value based on photography, and the difference exceeds the set threshold, then adjust the weight of the settlement value based on the sensor to 0.6 and the weight of the settlement value based on photography to 0.4.

[0019] Preferably, in the settlement monitoring method for the subgrade works under the railway, step two further includes: for the settlement values based on sensors at each settlement point, determining the coordinates in the national geodetic coordinate system according to the installation positions of the corresponding settlement points; for the three-dimensional point cloud data of the monitoring area: arranging control points in the monitoring area, determining the coordinates of the control points in the national geodetic coordinate system, and converting the three-dimensional point cloud data of the monitoring area into the national geodetic coordinate system through the coordinates of the control points in the national geodetic coordinate system; using the iterative closest point algorithm to register the settlement values based on sensors and the settlement values based on photography at each settlement point in the national geodetic coordinate system, so that the settlement values based on sensors and the settlement values based on photography are aligned in terms of spatial positions.

[0020] Preferably, in the settlement monitoring method for the subgrade works under the railway, in step one, the sensor acquisition frequency is set according to the expected rate of change of the settlement of the subgrade works under the railway. For the newly built subgrade section with relatively fast settlement changes, the value is collected every 15 minutes, and for the existing bridge with relatively stable settlement, the value is collected every hour; a camera with a pixel of not less than 20 million and the lens distortion controlled within a very small range is used for image data acquisition. The UAV flight route is planned along the railway line direction to ensure that the overlap degree between adjacent flight strips is not less than 60% and the side overlap degree is not less than 30%. A comprehensive image data acquisition is carried out once a month during a sunny day with uniform light.

[0021] The present invention has at least the following beneficial effects:

[0022] The present invention provides a method for monitoring the settlement of railway subgrade works, including: Step 1, sensor arrangement operation: Arrange a plurality of sensors for the monitoring area of railway subgrade works, and monitor the settlement values of a plurality of settlement points based on the sensors in one monitoring period through the plurality of sensors; Mount a camera on a drone, control the drone to fly along the railway line, and collect image data of the monitoring area of the railway subgrade works in the monitoring period through the camera; Step 2, data processing operation: Establish three-dimensional point cloud data in the monitoring period according to the image data of the monitoring area in the monitoring period; Determine the settlement values based on photography of the plurality of settlement points in the monitoring period through the three-dimensional point cloud data in the monitoring period; Step 3, weight assignment and data fusion operation: Assign reliability weights to the settlement values based on sensors and the settlement values based on photography for each settlement point respectively, perform weighted average operation, and obtain the fused settlement value. The calculation formula is: S_fusion = W_sensor × S_sensor + W_photography × S_photography, where S_fusion is the fused settlement value, W_sensor and W_photography are the weights of the settlement value based on the sensor and the settlement value based on photography respectively, and S_sensor and S_photography are the settlement value based on the sensor and the settlement value based on photography respectively. The method provided by the present invention combines the advantages of high-precision measurement data of sensors and large-area coverage data of photogrammetry, can more comprehensively and accurately reflect the settlement situation of railway subgrade works, reduce errors caused by the limitations of a single measurement method, and improve the monitoring accuracy. And through the drone for photogrammetry data collection, it can quickly obtain image information of a large-area monitoring area, combined with the real-time monitoring of sensors, greatly improving the efficiency of settlement monitoring, reducing the labor and time costs, and enhancing the monitoring efficiency.

[0023] Other advantages, objectives and features of the present invention will be partially reflected by the following description, and partially will be understood by those skilled in the art through the research and practice of the present invention. Brief Description of the Drawings

[0024] Figure 1 It is a flowchart of the method for monitoring the settlement of railway subgrade works provided by the present invention. Detailed Description of the Invention

[0025] The following further describes the present invention in detail with reference to the drawings, so that those skilled in the art can implement it according to the description in the specification.

[0026] As Figure 1 shown, the present invention provides a method for monitoring the settlement of railway subgrade works, including:

[0027] Step 1, sensor arrangement operation:

[0028] A plurality of sensors are arranged in the monitoring area of the subgrade works of the railway. The settlement values of a plurality of settlement points based on the sensors are monitored by the plurality of sensors in a monitoring period. A camera is mounted on a drone, and the drone is controlled to fly along the railway line. Image data of the monitoring area of the subgrade works of the railway in the monitoring period is collected by the camera.

[0029] For the monitoring area of the subgrade works of the railway, a plurality of sensors are reasonably arranged according to factors such as the engineering structure characteristics, geological conditions, and historical settlement data. Among them, static level gauges are arranged at key parts of the subgrade, such as the subgrade slope and the center of the embankment, for monitoring vertical settlement. Strain gauge sensors are arranged at parts such as bridge piers and abutments to monitor the settlement caused by structural deformation. Through these sensors, the settlement values of a plurality of settlement points based on the sensors in a monitoring period are monitored in real time. At the same time, a high-resolution camera is mounted on the drone. According to the railway line orientation and the monitoring area range, the flight route of the drone is planned to ensure that the overlap degree between adjacent flight strips is not less than 60%, and the side overlap degree is not less than 30%. In a period of clear weather and uniform light, the drone is controlled to fly along the planned railway line, and image data of the monitoring area of the subgrade works of the railway in the monitoring period is collected by the camera.

[0030] Step 2: Data processing operation:

[0031] Three-dimensional point cloud data in the monitoring period is established according to the image data of the monitoring area in the monitoring period. The settlement values of the plurality of settlement points based on photography in the monitoring period are determined through the three-dimensional point cloud data in the monitoring period.

[0032] The collected image data is preprocessed. Using the calibration parameters and distortion model of the camera itself, the image is corrected for distortion to eliminate the influence of lens distortion on the image. The SIFT (Scale-Invariant Feature Transform) algorithm is used to extract a large number of stable feature points in the image, and based on these feature points, the matching of homologous points between different images is realized through a stereo matching algorithm. On this basis, combined with the position and attitude information of the camera (provided by the GPS and IMU carried by the drone), methods such as triangulation are used to establish three-dimensional point cloud data of the monitoring area in this monitoring period. By analyzing the three-dimensional point cloud data, comparing the coordinate changes of the corresponding position points in the three-dimensional point clouds at different sampling times, the settlement values of the plurality of settlement points based on photography in this monitoring period are determined.

[0033] Step 3: Weight assignment and data fusion operation:

[0034] Reliability weights are respectively assigned to the settlement values of each settlement point based on the sensor and the settlement values based on photography, and a weighted average operation is performed to obtain a fused settlement value. The calculation formula is:

[0035] $S_{fusion}=W_{sensor}×S_{sensor}+W_{photography}×S_{photography}$, where $S_{fusion}$ is the fused settlement value, $W_{sensor}$ and $W_{photography}$ are the weights of the settlement value based on the sensor and the settlement value based on the photography respectively, and $S_{sensor}$ and $S_{photography}$ are the settlement value based on the sensor and the settlement value based on the photography respectively.

[0036] Taking into account the measurement accuracy and data stability of the sensor, as well as the image quality and coverage of photogrammetry, etc., reliability weights are assigned to the settlement value based on the sensor and the settlement value based on the photography for each settlement point. For example, for the data of a static level with high precision and stable data, a higher weight is given; for the photogrammetry data with high image quality and wide coverage, a relatively reasonable weight is given. The settlement value based on the sensor and the settlement value based on the photography are fused by means of weighted average operation.

[0037] In a preferred embodiment, the settlement monitoring method for the subgrade works under the railway line further includes a fusion value verification operation: select the settlement value based on the sensor and the settlement value based on the photography of several settlement points and compare them with the fused settlement value of the corresponding settlement points respectively, calculate the error. If the error is within the preset allowable range, it is considered that the accuracy of the fused settlement value meets the standard; otherwise, adjust the weights of the settlement value based on the sensor and the settlement value based on the photography.

[0038] Select several settlement points, compare the settlement value based on the sensor and the settlement value based on the photography of these settlement points with the fused settlement value of the corresponding settlement points respectively, and calculate the error. Preset the allowable error range in advance. If the calculated error is within the preset allowable range, it is considered that the accuracy of the fused settlement value meets the standard; if the error exceeds the preset allowable range, adjust the weights of the settlement value based on the sensor and the settlement value based on the photography. The adjustment method can re-determine the weights according to factors such as changes in measurement accuracy and acquisition conditions, and then perform data fusion and verification again until the accuracy of the fused settlement value meets the standard.

[0039] In a preferred embodiment, in the settlement monitoring method for the subgrade works under the railway line, the preset allowable range is ±2 mm.

[0040] In a preferred embodiment, in the settlement monitoring method for the subgrade works under the railway line, in step one, for different parts of the monitoring area, corresponding types of sensors are selected for layout, including: at the key positions of the subgrade, static level instruments are arranged to monitor the vertical settlement value; at the bridge piers and abutments, strain gauge sensors are arranged to monitor the settlement value caused by structural deformation.

[0041] At key positions of the subgrade, such as areas prone to vertical settlement like subgrade slopes and embankment centers, static level gauges are arranged. Through the principle of communicating vessels, the static level gauges can monitor the vertical settlement values in real time and with high precision, providing reliable data for analyzing the vertical deformation of the subgrade.

[0042] At bridge piers and abutments, due to the special nature of the bridge structure, its settlement is mostly caused by structural deformation. Therefore, strain gauge sensors are arranged. The strain gauge sensors can sensitively capture the tiny deformations generated by the bridge piers and abutments under the action of forces, and then monitor the settlement values caused by structural deformation, providing key data support for the health assessment of the bridge structure.

[0043] In a preferred embodiment, in the method for monitoring the settlement of the subgrade works under the railway, in step three, when a settlement point uses a static level gauge, the weight of the sensor-based settlement value of this settlement point is set to 0.7, and the weight of the photography-based settlement value is set to 0.3; when a settlement point uses a strain gauge sensor, the weight of the sensor-based settlement value of this settlement point is set to 0.6, and the weight of the photography-based settlement value is set to 0.4.

[0044] Taking into comprehensive consideration factors such as the measurement accuracy and data stability of the sensors, as well as the image quality and coverage of photogrammetry, reliability weights are assigned to the sensor-based settlement values and photography-based settlement values for each settlement point. For example, for the data of the static level gauge with high precision and stable data, a higher weight is given; for the photogrammetry data with high image quality and wide coverage, a relatively reasonable weight is given.

[0045] In a preferred embodiment, in the method for monitoring the settlement of the subgrade works under the railway, in step three, if the weather conditions are poor, the weight of the sensor-based settlement value of this settlement point is set to 0.6, and the weight of the photography-based settlement value is set to 0.4; if the weather conditions are good, the weight of the sensor-based settlement value is set to 0.5, and the weight of the photography-based settlement value is set to 0.5.

[0046] Taking into comprehensive consideration factors such as the measurement accuracy and data stability of the sensors, the image quality and coverage of photogrammetry, and the weather conditions, reliability weights are assigned to the sensor-based settlement values and photography-based settlement values for each settlement point: if the weather conditions are poor, such as in the case of strong winds, heavy rains, thick fogs, etc. that affect the image quality of photogrammetry, the weight of the sensor-based settlement value of this settlement point is set to 0.6, and the weight of the photography-based settlement value is set to 0.4; if the weather conditions are good, with uniform light and no interference from bad weather, the weight of the sensor-based settlement value is set to 0.5, and the weight of the photography-based settlement value is set to 0.5.

[0047] In a preferred embodiment, in the method for monitoring the settlement of the subgrade works under the railway, in step three, if the standard deviation of the sensor-based settlement value of a settlement point in a statistical time period is less than the standard deviation of the photography-based settlement value, and the difference exceeds the set threshold, then the weight of the sensor-based settlement value is adjusted to 0.6, and the weight of the photography-based settlement value is adjusted to 0.4.

[0048] Adjust the weight according to the data stability. Calculate the standard deviation of the sensor-based settlement value and the photography-based settlement value of a settlement point in a statistical time period. This standard deviation is used to reflect the data stability. If the standard deviation of the sensor-based settlement value in this statistical time period is less than the standard deviation of the photography-based settlement value, and the difference between them exceeds the set threshold (such as 0.1), for example, the standard deviation of the sensor-based settlement value of a settlement point in a statistical time period is 0.05, while the standard deviation of the photography-based settlement value is 0.2, then the weight of the sensor-based settlement value is adjusted to 0.6, and the weight of the photography-based settlement value is adjusted to 0.4.

[0049] In a preferred embodiment, in the method for monitoring the settlement of the subgrade works under the railway, in step two, it further includes: for the sensor-based settlement value of each settlement point, determine the coordinates in the national geodetic coordinate system according to the installation position of the corresponding settlement point; for the three-dimensional point cloud data of the monitoring area: arrange control points in the monitoring area, determine the coordinates of the control points in the national geodetic coordinate system, and convert the three-dimensional point cloud data of the monitoring area to the national geodetic coordinate system through the coordinates of the control points in the national geodetic coordinate system; use the iterative closest point algorithm to register the sensor-based settlement value and the photography-based settlement value of each settlement point in the national geodetic coordinate system to align the sensor-based settlement value and the photography-based settlement value in terms of spatial position.

[0050] In a preferred embodiment, in the method for monitoring the settlement of the subgrade works under the railway, in step one, set the sensor acquisition frequency according to the expected rate of change of the settlement of the subgrade works under the railway. For the newly built subgrade section with a relatively fast settlement change, collect the value every 15 minutes, and for the existing bridge with relatively stable settlement, collect the value every hour; use a camera with a pixel of not less than 20 million and the lens distortion controlled within a very small range to collect image data. Plan the UAV flight route along the railway line direction to ensure that the overlap between adjacent flight strips is not less than 60%, and the side overlap is not less than 30%. Select a sunny and evenly lit period to conduct a comprehensive image data collection once a month.

[0051] Set the sensor acquisition frequency according to the expected rate of change of the settlement of the subgrade works under the railway. For the newly built subgrade section with relatively fast settlement changes, collect the values every 15 minutes to capture the rapidly changing settlement data in a timely manner; for the existing bridges with relatively stable settlement, collect the values every hour to improve the monitoring efficiency while ensuring the data validity. The data collected by the sensors is transmitted to the data acquisition terminal via wired or wireless means, and preliminary denoising processing is performed at the terminal to eliminate the significantly incorrect or abnormal data points.

[0052] Use a camera with a pixel count of no less than 20 million and the lens distortion controlled within a very small range for image data acquisition, and mount it on a drone. Plan the drone flight route along the railway line direction to ensure that the overlap between adjacent flight strips is no less than 60% and the lateral overlap is no less than 30% to ensure the full coverage of the monitoring area and the integrity of the data. Conduct a comprehensive image data acquisition once a month during sunny days with uniform light, increase the acquisition frequency during the periods when settlement anomalies may occur, and perform preliminary screening on the images after acquisition to remove the blurred and abnormally exposed images. Through the above operations, the settlement values based on the sensors of multiple settlement points within a monitoring cycle can be monitored in real time, and the image data of the monitoring area of the subgrade works under the railway in this monitoring cycle can be obtained.

[0053] Although the embodiments of the present invention have been disclosed as above, they are not limited to only the applications listed in the specification and the embodiments. It can be fully applied to various fields suitable for the present invention. For those familiar with the field, additional modifications can be easily achieved. Therefore, without departing from the general concept defined by the claims and the equivalent scope, the present invention is not limited to the specific details and the examples shown and described herein.

Claims

1. A method for monitoring the settlement of subgrade works of railways, characterized in that, Including: Step 1, Sensor Arrangement Operation: Arrange multiple sensors for the monitoring area of the railway subgrade project, and monitor the settlement values of multiple settlement points based on the sensors in a monitoring period through the multiple sensors; Mount a camera on a drone, control the drone to fly along the railway line, and collect image data of the monitoring area of the railway subgrade project in the monitoring period through the camera; Step 2, Data Processing Operation: Establish three-dimensional point cloud data in the monitoring period based on the image data of the monitoring area in the monitoring period; Determine the settlement values based on photography of the multiple settlement points in the monitoring period through the three-dimensional point cloud data in the monitoring period; Step 3, Weight Assignment and Data Fusion Operation: Assign reliability weights to the settlement values based on sensors and the settlement values based on photography for each settlement point respectively, perform weighted average calculation, and obtain the fused settlement value. The calculation formula is: S_fusion = W_sensor × S_sensor + W_photography × S_photography, where S_fusion is the fused settlement value, W_sensor and W_photography are the weights of the settlement value based on the sensor and the settlement value based on photography respectively, and S_sensor and S_photography are the settlement values based on the sensor and the settlement value based on photography respectively.

2. The settlement monitoring method for the subgrade works of a railway according to claim 1, characterized in that, It also includes a fused value verification operation: Select the settlement values based on sensors and the settlement values based on photography of several settlement points and compare them with the fused settlement values of the corresponding settlement points respectively, calculate the error. If the error is within the preset allowable range, it is considered that the accuracy of the fused settlement value meets the standard; otherwise, adjust the weights of the settlement values based on sensors and the settlement values based on photography.

3. The settlement monitoring method for the subgrade works of a railway according to claim 1, characterized in that, The preset allowable range is ±2mm.

4. The settlement monitoring method for subgrade works of railway as claimed in claim 1, wherein In the said Step 1, for different parts of the monitoring area, select corresponding types of sensors for arrangement, including: At the key positions of the subgrade, arrange static level gauges to monitor the vertical settlement value; At the bridge piers and abutments, arrange strain gauge sensors to monitor the settlement value caused by structural deformation.

5. The settlement monitoring method for the subgrade works of a railway according to claim 2, characterized in that, In the said Step 3, when a static level gauge is used for a settlement point, set the weight of the settlement value based on the sensor of this settlement point to 0.7, and set the weight of the settlement value based on photography to 0.3; When a strain gauge sensor is used for a settlement point, set the weight of the settlement value based on the sensor of this settlement point to 0.6, and set the weight of the settlement value based on photography to 0.

4.

6. The method for monitoring settlement of railway subgrade works as described in claim 1, wherein In the said Step 3, if the weather condition is poor, set the weight of the settlement value based on the sensor of this settlement point to 0.6, and set the weight of the settlement value based on photography to 0.4; If the weather condition is good, set the weight of the settlement value based on the sensor to 0.5, and set the weight of the settlement value based on photography to 0.

5.

7. The method for monitoring settlement of subgrade works of railway as claimed in claim 1, wherein In the said Step 3, if the standard deviation of the settlement value of a settlement point based on the sensor in a statistical time period is less than the standard deviation of the settlement value based on photography, and the difference exceeds the set threshold, then adjust the weight of the settlement value based on the sensor to 0.6, and adjust the weight of the settlement value based on photography to 0.

4.

8. The settlement monitoring method for subgrade works of railway as claimed in claim 1, wherein, The second step further includes: for the sensor-based settlement values of each settlement point, determining the coordinates in the national geodetic coordinate system according to the installation positions of the corresponding settlement points; for the three-dimensional point cloud data of the monitoring area: arranging control points in the monitoring area, determining the coordinates of the control points in the national geodetic coordinate system, and converting the three-dimensional point cloud data of the monitoring area into the national geodetic coordinate system through the coordinates of the control points in the national geodetic coordinate system; using the iterative closest point algorithm to register the sensor-based settlement values and the photograph-based settlement values of each settlement point in the national geodetic coordinate system, so that the sensor-based settlement values and the photograph-based settlement values are aligned in terms of spatial positions.

9. The settlement monitoring method for the subgrade works of a railway according to claim 1, wherein In the first step, the sensor acquisition frequency is set according to the expected rate of change of the settlement of the subgrade works under the railway. For the newly built subgrade section with relatively fast settlement changes, the values are acquired every 15 minutes, and for the existing bridges with relatively stable settlement, the values are acquired every hour; a camera with a pixel of not less than 20 million and the lens distortion controlled within a very small range is used for image data acquisition. The UAV flight route is planned along the railway line direction to ensure that the overlap degree between adjacent flight strips is not less than 60%, and the side overlap degree is not less than 30%. A comprehensive image data acquisition is carried out once a month during a period with clear weather and uniform light.

Images