Expressway disaster identification method, device and system, and storage medium

Abstract

The invention discloses a highway disaster identification method, device and system, and a storage medium. The method comprises the following steps: S1, obtaining ground subsidence information of a monitoring area according to a time sequence InSAR; s2, obtaining a highway PS point according to the land subsidence information of the monitoring area; and S3, performing expressway disaster identification according to the expressway PS point. By adopting the technical scheme of the invention, rapid, accurate and precise recognition of expressway disasters can be realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of disaster identification, and in particular relates to a highway disaster identification method and device, a system, and a storage medium. Background Art

[0002] Expressways have the advantages of high efficiency and fast access, saving transportation costs and promoting the development of commodity economy along the expressways. However, as expressways are put into operation, the road surface will inevitably experience different degrees of settlement. For example, there is a significant vertical displacement difference between the highway structure and the road surface, which causes bridge head jumping and other problems. This is due to the continuous uneven settlement of the roadbed and pavement, which not only affects the safety and comfort of high-speed driving and the normal operation of the highway, but also seriously threatens people's lives and property safety. The maintenance of expressways faces major challenges, such as monitoring the settlement of roadbed and pavement. Therefore, it is of great significance to prevent disasters caused by ground settlement, monitor the deformation of expressways, study their deformation characteristics and causes, and predict their settlement trends.

[0003] Precision leveling observation and GPS observation are conventional methods for highway settlement monitoring, but they have the disadvantages of covering blank areas, long operation cycle, and requiring a lot of manpower, material and financial resources. It is difficult to ensure high-frequency continuous monitoring, and it is impossible to provide timely and effective information for highway maintenance and disaster prevention along the road. Moreover, measurements can only be performed on sparse discrete points, making it difficult to monitor all highways and obtain a wide range of settlement information. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a highway disaster identification method and device, system, and storage medium, which can realize rapid, accurate and precise identification of highway disasters.

[0005] To achieve the above object, the present invention adopts the following technical solution: A highway disaster identification method, comprising: Step S1, obtaining ground subsidence information in the monitoring area according to time series InSAR; Step S2, extracting highway PS points based on the ground subsidence information in the monitoring area through scene knowledge and highway GIS database; Step S3, identifying highway disasters according to highway PS points; Wherein, step S2 comprises: Step S21, generating new highway PS point element data according to the inclusion relationship between the PS point elements of the monitoring area ground subsidence information and the surface elements of the highway GIS database; Step S22, performing denoising on the disturbance factors existing on both sides and in the middle of the new highway PS point element data; Step S23, obtaining a PS point cloud of a flat section of the highway and a PS point cloud of an undulating section of the highway according to the new PS point feature data of the highway after denoising; Step S24, performing denoising on the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway; Step S3 includes: Calculate the surface settlement and road surface smoothness at the PS point of the highway; Highway disaster identification is carried out based on surface settlement and road surface smoothness.

[0006] The present invention also provides a highway disaster identification device, comprising: An acquisition module is used to obtain ground subsidence information in the monitoring area based on time-series InSAR; The extraction module is used to extract PS points on highways based on the ground subsidence information in the monitoring area through scene knowledge and highway GIS database; Recognition module, used for highway hazard recognition based on highway PS points; The extraction module includes: The first processing unit is used to generate new highway PS point element data according to the inclusion relationship between the PS point element of the ground subsidence information in the monitoring area and the surface element of the highway GIS database; The second processing unit is used to perform denoising on disturbance factors existing on both sides and in the middle of the new highway PS point element data; The third processing unit is used to obtain the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway according to the new PS point element data of the highway after the denoising process; The fourth processing unit is used for denoising the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway; The identification module includes: A calculation unit, used to calculate the surface settlement and road surface flatness at the PS point of the highway; The identification unit is used to identify highway disasters based on the surface settlement and road surface flatness.

[0007] The present invention also provides a highway disaster identification system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a highway disaster identification method when executed by the processor.

[0008] The present invention also provides a storage medium, on which a computer program is stored, and the computer program executes the highway disaster identification method when running.

[0009] The present invention utilizes the PS point fine classification method to realize the accurate extraction of highway deformation information, and comprehensively utilizes the roadbed settlement and road surface flatness indicators to carry out the identification and analysis of highway disasters, which can realize the rapid, accurate and precise identification of highway disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0011] Figure 1 A flowchart of highway disaster identification according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the inclusion relationship analysis between the highway GIS database area elements and PS point elements; Figure 3 Schematic diagram of the inclusion relationship analysis between highway GIS database area elements and PS point elements considering geocoding errors Figure 4 This is a schematic diagram of local elevation statistical filtering analysis; Figure 5 Schematic diagram of PS point cloud denoising processing on a flat section of a highway. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0014] Embodiment 1: like Figure 1 As shown, an embodiment of the present invention provides a highway disaster identification method, comprising: Step S1, obtaining ground subsidence information in the monitoring area according to time series InSAR; Step S2, obtaining the PS point of the highway according to the ground subsidence information of the monitoring area; Step S3: identify highway disasters based on highway PS points.

[0015] As an implementation of the embodiment of the present invention, in step S2, highway PS points are extracted through scene knowledge and highway GIS database.

[0016] Further, step S2 comprises: Step S21: Spatial analysis of highway GIS database elements and PS point elements like Figure 2 As shown in the figure, the plumb line algorithm is used to determine whether there is an inclusion relationship between the PS point element (circle) and the highway GIS database area element (solid line polygon). For the PS point element and highway GIS database area element that have an inclusion relationship, new highway PS point element data is generated, and the attribute information of the PS point element and the highway GIS database area element are assigned to the newly generated element data.

[0017] like Figure 3 As shown, due to the geocoding error of the PS point. To ensure the reliability of the results, based on the highway GIS database surface feature data (solid rectangle), the positioning error threshold Tx of the PS point in the east-west direction and the positioning error threshold Ty in the north-south direction form the suspected highway distribution range represented by the red rectangle. The red rectangle represents the range formed by the east-west expansion Tx and the north-south expansion Ty of the highway GIS database surface feature data (solid rectangle). The plumb line algorithm is used to determine whether there is an inclusion relationship between the PS point feature (circle) and the suspected distribution range (dashed polygon). For the PS point feature and suspected distribution range feature data with an inclusion relationship, new feature data is generated, and the attribute information of the PS point feature and the highway GIS database surface feature are assigned to the newly generated feature data as the output of this step.

[0018] Step S22: Considering the disturbance factors such as trees and greenery on both sides and in the middle of the expressway, a local elevation statistical filtering method is used for denoising. like Figure 4 As shown in the figure, the suspected highway PS point cloud output in the previous step is used as input. The calculation method is to iteratively analyze each PS point (circular point and triangular point) after geocoding, and select a square with no restrictions in the horizontal direction (shown as a black rectangle) as the center; statistically analyze the elevation value difference of the PS point cloud in this narrow rectangle. If the elevation value difference is greater than a certain threshold, the point is regarded as a noise point (the misclassified point shown by the triangle in the figure) and is removed. The output is the denoised suspected highway PS point cloud.

[0019] Step S23: Classify the highway into undulating sections and flat sections according to the terrain undulations corresponding to the PS point cloud of the suspected highway in the measurement area. ① Interpolate the PS points within the highway range to the depth map of the highway GIS database surface feature range The input is the suspected highway PS point cloud and the highway GIS database surface element. The calculation method is to use the elevation information of the highway PS point cloud and use the linear interpolation method to obtain the elevation of each pixel value within the highway GIS database surface element range, where the pixel size is consistent with the resolution of the synthetic aperture radar (SAR). The output is the depth map within the highway GIS database surface element range.

[0020] ② Calculate the gradient map along the center line of the highway The input is the depth map within the area of ​​the highway GIS database and the centerline of the highway. The calculation method is to calculate the difference between the pixel depth value and the previous pixel depth value for each pixel along the centerline of the highway, and use it as the value of the new output gradient map. The output of this step is the gradient map along the centerline of the highway.

[0021] ③Filter the gradient image The input is the gradient map along the center line of the highway. The calculation method is to calculate the middle value of the pixel depth value and the depth values ​​of the three pixels before and after (a total of 7 values) for each pixel value along the center line of the highway, and use it as the value of the new output filtered gradient map. The output of this step is the filtered gradient map along the center line of the highway.

[0022] ④ Binarize and classify the window's gradient mean map The input is the filtered gradient map along the centerline of the highway. The calculation method is to judge the relationship between the value of each pixel and the specified threshold along the centerline of the highway, and classify the section with a pixel value greater than the specified threshold as an undulating section, and the corresponding section PS point is the PS point cloud of the undulating section of the highway; the section with a pixel value less than the specified threshold is classified as a flat section, and the corresponding section PS point is the PS point cloud of the flat section of the highway.

[0023] Step S24: PS point cloud denoising of the flat section of the highway The input is the suspected highway PS point cloud of the flat section of the highway. The calculation method is as follows: for each PS point; take the PS point cloud along the centerline of the highway and within the range of b / 2 as the calculation object, calculate the maximum elevation, minimum elevation, mean and mean square error statistics of the PS point cloud, and obtain the optimal statistical value through comprehensive weight analysis, where b is the length of the denoising processing window; then judge the difference between the elevation value of the PS point and the optimal statistical value, if it is less than the specified threshold, it is classified as a highway point, if it is greater than the specified threshold, it is classified as a noise point and removed.

[0024] Step S25: PS point cloud denoising of the undulating section of the highway The input is the suspected highway PS point cloud of the undulating section of the highway. The calculation method is as follows: for each PS point; take the PS point cloud within the range of b / 2 along the centerline of the highway as the calculation object, select the initial ground point based on the distance to the centerline of the comprehensive road and the elevation value of the PS point, and then construct the triangulation network, where b is the length of the denoising processing window; then calculate the distance and angle from the PS point to the corresponding triangulation network, if it is less than the specified threshold, it is classified as a highway point, if it is greater than the specified threshold, it is classified as a noise point and removed.

[0025] As an implementation of the embodiment of the present invention, step S3 includes: Calculate the surface settlement and road surface smoothness at the PS point of the highway; Highway disaster identification is carried out based on surface settlement and road surface smoothness.

[0026] Furthermore, highway disaster identification is performed based on surface settlement as follows: The regional land subsidence status development degree classification standard shown in Table 1 is selected to carry out early disaster identification based on highway surface subsidence. For each PS point, the relationship between its deformation rate value and the thresholds T1 and T2 in Table 1 is judged. If it is less than or equal to T1, the development degree is classified as weak; if it is greater than threshold T1 and less than threshold T2, the development degree is classified as medium; if it is greater than or equal to threshold T2, the development degree is classified as strong. The output is the highway land subsidence development degree classification result.

[0027] Table 1

[0028] Furthermore, highway disaster identification based on road surface roughness is as follows: Uneven settlement of highway subgrade can damage the subgrade itself, which in turn leads to uneven deformation of the road surface. When the uneven settlement of the road surface exceeds a certain standard, it will damage the road surface structure, reduce the service life of the road, and affect driving safety. The road surface smoothness is used as an important indicator to evaluate the road surface quality and driving comfort. Under the assumption that the road surface smoothness is 0 before the settlement observation begins, the formula for calculating the highway road surface smoothness index based on settlement observation is shown in the following formula, and its value should be less than 0.47%.

[0029]

[0030] in, is the road surface smoothness index. is the differential sedimentation, For distance.

[0031] Highway hazard identification based on road surface roughness includes: Step 10: interpolate the PS points within the expressway range to the settlement rate map within the expressway GIS database area feature range.

[0032] The input is the PS points of highways and the surface elements of highway GIS database. The calculation method is to use the sedimentation rate information of the PS point cloud of highways and use the linear interpolation method to obtain the sedimentation rate of each pixel value within the surface element range of the highway GIS database, where the pixel size is consistent with the resolution of the synthetic aperture radar (SAR). The output is the sedimentation rate map within the surface element range of the highway GIS database.

[0033] Step 20: Calculate the flatness along the centerline of the highway The input is the sedimentation rate map within the area of ​​the highway GIS database and the center line of the highway. The calculation method is to calculate the difference ds between the sedimentation rate value of the pixel and the sedimentation rate value of the previous pixel with a distance S along the center line of the highway, and compare the sedimentation rate difference ds with the distance S to obtain the flatness corresponding to the pixel. .

[0034] Step 30: Disaster identification along the center line of the highway The input is the smoothness of the highway centerline. The calculation method is to convert the smoothness It is compared with the specified threshold value T3. If it is less than the threshold value T3, there is no hidden danger within the monitoring period; if it is greater than the threshold value T3, there is a hidden danger within the monitoring period.

[0035] Embodiment 2: The embodiment of the present invention further provides a highway disaster identification device, comprising: An acquisition module is used to obtain ground subsidence information in the monitoring area based on time-series InSAR; The extraction module is used to extract PS points on highways based on the ground subsidence information in the monitoring area through scene knowledge and highway GIS database; Recognition module, used for highway hazard recognition based on highway PS points; The extraction module includes: The first processing unit is used to generate new highway PS point element data according to the inclusion relationship between the PS point element of the ground subsidence information in the monitoring area and the surface element of the highway GIS database; The second processing unit is used to perform denoising on disturbance factors existing on both sides and in the middle of the new highway PS point element data; The third processing unit is used to obtain the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway according to the new PS point element data of the highway after the denoising process; The fourth processing unit is used for denoising the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway; The identification module includes: A calculation unit, used to calculate the surface settlement and road surface flatness at the PS point of the highway; The identification unit is used to identify highway disasters based on the surface settlement and road surface flatness.

[0036] Embodiment 3: An embodiment of the present invention further provides a highway disaster identification system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a highway disaster identification method when executed by the processor.

[0037] Embodiment 4: An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and the computer program executes the highway disaster identification method when running.

[0038] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A highway disaster identification method, characterized in that: include: Step S1, obtaining ground subsidence information in the monitoring area according to time series InSAR; Step S2, extracting highway PS points based on the ground subsidence information in the monitoring area through scene knowledge and highway GIS database; Step S3, identifying highway disasters according to highway PS points; Wherein, step S2 comprises: Step S21, generating new highway PS point element data according to the inclusion relationship between the PS point elements of the monitoring area ground subsidence information and the surface elements of the highway GIS database; Step S22, performing denoising on the disturbance factors existing on both sides and in the middle of the new highway PS point element data; Step S23, obtaining a PS point cloud of a flat section of the highway and a PS point cloud of an undulating section of the highway according to the new PS point feature data of the highway after denoising; Step S24, performing denoising on the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway; Step S3 includes: Calculate the surface settlement and road surface smoothness at the PS point of the highway; Highway disaster identification is carried out based on surface settlement and road surface smoothness.

2. A highway disaster identification device, characterized in that: include: An acquisition module is used to obtain ground subsidence information in the monitoring area based on time-series InSAR; The extraction module is used to extract PS points on highways based on the ground subsidence information in the monitoring area through scene knowledge and highway GIS database; Recognition module, used for highway hazard recognition based on highway PS points; The extraction module includes: The first processing unit is used to generate new highway PS point element data according to the inclusion relationship between the PS point element of the ground subsidence information in the monitoring area and the surface element of the highway GIS database; The second processing unit is used to perform denoising on disturbance factors existing on both sides and in the middle of the new highway PS point element data; The third processing unit is used to obtain the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway according to the new PS point element data of the highway after the denoising process; The fourth processing unit is used for denoising the PS point cloud of the flat section of the highway and the PS point cloud of the undulating section of the highway; The identification module includes: A calculation unit, used to calculate the surface settlement and road surface flatness at the PS point of the highway; The identification unit is used to identify highway disasters based on the surface settlement and road surface flatness.

3. A highway disaster identification system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the highway disaster identification method according to claim 1 is executed.

4. A storage medium, characterized in that: The storage medium stores a computer program, and the computer program executes the highway disaster identification method according to claim 1 when running.

Images