Ground subsidence detection method, device and equipment and storage medium
Through multi-information sensing and multi-level multi-blocking factor structure methods, the problems of low degree of automation and poor real-time performance of ground settlement detection in the prior art are solved, and high-frequency, accurate, accurate ground settlement detection is achieved.
Patent Information
- Application Number
- CN202411116528.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-26
AI Technical Summary
The existing ground settlement detection methods have problems such as high human investment cost, low degree of automation, narrow coverage and poor real-time performance, which are difficult to meet the needs of high-frequency and quasi-real-time ground settlement detection in urban areas.
High-precision geographic factor data is obtained through multi-information induction, and the target factor data is extracted and matched using a multi-level multi-blocking factor structure, the displacement is calculated to determine the degree of settlement, and high-frequency, quasi-real-time ground settlement detection is achieved.
It improves the automation and coverage of ground settlement detection, ensures high accuracy and real-time detection, and significantly improves detection efficiency and accuracy.
Smart Images

Figure CN119022878A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of ground detection technology, and in particular to a ground subsidence detection method, device, equipment and storage medium. Background Art
[0002] With the continuous advancement of urbanization, underground construction in urban areas and excessive use of groundwater may lead to ground subsidence in urban areas. Subsidence problems in daily operations can easily cause casualties and property losses. It can be seen that there is an urgent practical need to reasonably and effectively detect ground subsidence.
[0003] At present, traditional detection methods include geometric leveling method and total station method, which use level or total station to measure the height difference between reference point and observation point. The above methods are suitable for small-scale settlement observation, but there are problems such as high manpower input cost, sparse point distribution, long operation cycle and low degree of automation.
[0004] It can be seen that there is an urgent need for a ground subsidence detection solution with a higher degree of automation, better real-time performance and wider coverage. Summary of the invention
[0005] The embodiments of the present disclosure at least provide a ground subsidence detection method, device, equipment and storage medium to extract high-precision geographic element data through multi-information sensing, thereby realizing high-frequency and quasi-real-time ground subsidence detection within the operating range.
[0006] In a first aspect, an embodiment of the present disclosure provides a method for detecting ground subsidence, comprising:
[0007] Acquire multiple types of first ground information currently collected, each type of first ground information is obtained based on information sensing performed by a corresponding collection device on a target detection area;
[0008] Based on the multiple types of first ground information, extracting first target element data within the target detection area in the current phase;
[0009] Searching for second target element data matching the first target element data from a pre-constructed multi-level and multi-block element structure; the second target element data is in a different time phase from the first target element data;
[0010] Based on the difference operation between the first target element data and the second target element data, the displacement generated by the same target element is determined, and the displacement is used to indicate the degree of settlement of the target detection area.
[0011] In a possible implementation, the multi-level and multi-block element structure is pre-built according to the following steps:
[0012] Acquire a plurality of second ground information collected in advance in the target detection area;
[0013] Extracting at least one second target element data in the target detection area based on a plurality of second ground information collected in advance;
[0014] Based on the element type to which each of the second target element data belongs and the pre-segmentation of the target detection area, the corresponding position of each of the second target element data in the multi-level and multi-block element structure is determined.
[0015] In a possible implementation manner, the multi-level multi-block element structure includes a multi-level substructure and a multi-block substructure; and determining the corresponding position of each second target element data in the multi-level multi-block element structure includes:
[0016] For each second target element data, based on the correspondence between the element type to which the second target element data belongs and the multiple element types corresponding to the multi-level substructure, determining the corresponding position of the second target element data in the multi-level substructure;
[0017] When it is determined that the target detection area includes multiple pre-divided detection ground area blocks, the corresponding position of the second target element data in the multi-block substructure is determined based on the correspondence between the element position indicated by the second target element data and the multiple detection ground area blocks corresponding to the multi-block substructure.
[0018] In a possible implementation manner, extracting the first target element data in the target detection area at the current time phase includes:
[0019] In response to the element type of the first target element belonging to the road surface element type, determining the elevation data of any coordinate point in the road surface in the target detection area based on the laser point cloud information in the plurality of first ground information, and using the elevation data as the first target element data;
[0020] In response to the element type of the first target element belonging to the road surface damage element type, element recognition is performed based on the image information in the plurality of first ground information, and the element recognition result is projected onto the laser point cloud ground area indicated in the plurality of first ground information, and the damage data on the target detection area is extracted as the first target element data;
[0021] In response to the fact that the element type of the first target element belongs to the linear guardrail element type, point cloud segmentation is performed based on the laser point cloud information in the plurality of first ground information, and the highest point connection line data close to the inner side of the road in the target detection area indicated in the point cloud segmentation result is used as the first target element data;
[0022] In response to the fact that the element type of the first target element belongs to the rod-shaped object element type, rod-shaped object data in the target detection area is determined based on the laser point cloud information in the plurality of first ground information, and is used as the first target element data.
[0023] In a possible implementation, the method further includes:
[0024] The first target feature data extracted in the current time phase is stored in a pre-constructed multi-level multi-block feature structure to obtain an updated multi-level multi-block feature structure.
[0025] In a possible implementation manner, searching for second target element data matching the first target element data from a pre-constructed multi-level and multi-block element structure includes:
[0026] In response to the element type of the first target element belonging to the point element type, based on the attribute information of the first target element and the orientation information between the first target element and the reference element, point search is performed on the multi-level and multi-block element structure within the spatial position to obtain element data with the same attributes within a preset search range;
[0027] The retrieved element data is determined as second target element data matching the first target element data.
[0028] In a possible implementation manner, searching for second target element data matching the first target element data from a pre-constructed multi-level and multi-block element structure includes:
[0029] In response to the feature type of the first target feature belonging to the linear feature type, calculating the distance between the first target feature and a second target feature to be matched in the multi-level multi-block feature structure;
[0030] The second target feature data with the largest distance confidence is determined as the second target feature data matching the first target feature data.
[0031] In a possible implementation manner, searching for second target element data matching the first target element data from a pre-constructed multi-level and multi-block element structure includes:
[0032] In response to the fact that the element type of the first target element belongs to the planar element type, searching for a second target element segment matching each contour segment included in the first target element from the multi-level multi-block element structure;
[0033] The determined second target element segments are combined to determine second target element data matching the first target element data.
[0034] In a possible implementation manner, after determining the displacement amount generated by the same target element, the method further includes:
[0035] Based on the displacement generated by each target element, determine to filter out the initial settlement deformation area from the target detection area;
[0036] In the initial settlement deformation area, the deformation amount is verified by superimposing other element data to determine the final settlement deformation area and the overall deformation amount of the final settlement deformation area.
[0037] In a possible implementation manner, after determining the displacement amount generated by the same target element, the method further includes:
[0038] Determine a deformation trend analysis result for the target detection area based on the displacements generated for the same target element at different time phases;
[0039] Based on the deformation trend analysis results, an implementable ground subsidence monitoring feedback strategy is determined.
[0040] In a second aspect, the present disclosure also provides a ground subsidence detection device, including:
[0041] An acquisition module, used to acquire a plurality of first ground information currently collected, each of which is obtained based on information sensing performed by a corresponding acquisition device on a target detection area;
[0042] An extraction module, configured to extract first target element data in the target detection area at a current time phase based on the multiple types of first ground information;
[0043] A search module, used to search for second target element data matching the first target element data from a pre-built multi-level and multi-block element structure; the second target element data is different in time phase from the first target element data;
[0044] The detection module is used to determine the displacement generated by the same target element based on the difference operation between the first target element data and the second target element data, and the displacement is used to indicate the degree of settlement of the target detection area.
[0045] In the third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, a ground subsidence detection method as described in any one of the first aspect and its various embodiments is performed.
[0046] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the ground subsidence detection method as described in any one of the first aspect and its various embodiments is executed.
[0047] By adopting the above-mentioned ground subsidence detection method, device, equipment and storage medium, when a plurality of first ground information currently collected is obtained, the first target element data in the target detection area in the current phase can be extracted based on the plurality of first ground information; and then the second target element data matching the first target element data is searched from the pre-constructed multi-level and multi-block element structure, and the displacement generated by the same target element is determined based on the difference operation between the first target element data and the second target element data. The first target element data disclosed in the present invention is extracted from a plurality of first ground information, thereby ensuring the high precision of the element data itself, and then the second target element data matching the first target element data can be quickly searched through the pre-constructed multi-level and multi-block element structure, which will significantly improve the efficiency of subsequent ground subsidence detection. In addition, based on the data difference between two element data with different phases, the determined degree of subsidence can be made more accurate.
[0048] Other advantages of the present disclosure will be explained in more detail in conjunction with the following description and drawings.
[0049] It should be understood that the above description is only an overview of the technical solution of the present disclosure, so that the technical means of the present disclosure can be generally understood and then implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are specifically described below with examples. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments are briefly introduced below. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the drawings only illustrate certain embodiments of the present disclosure and therefore should not be regarded as limiting the scope of protection. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work. Moreover, the same reference numerals are used to represent the same components throughout the drawings. In the drawings:
[0051] Figure 1 A flow chart of a ground subsidence detection method provided by an embodiment of the present disclosure is shown;
[0052] FIG. 2( a ) shows a schematic diagram of the effect before point element matching in the ground subsidence detection method provided by an embodiment of the present disclosure;
[0053] FIG2( b ) shows a schematic diagram of the effect after point elements are matched in the ground subsidence detection method provided in an embodiment of the present disclosure;
[0054] FIG3( a ) shows a schematic diagram of the effect before linear element matching in the ground subsidence detection method provided by an embodiment of the present disclosure;
[0055] FIG3( b ) shows a schematic diagram of the effect after linear elements are matched in the ground subsidence detection method provided in an embodiment of the present disclosure;
[0056] Figure 4 A schematic diagram of a ground subsidence detection device provided by an embodiment of the present disclosure is shown;
[0057] Figure 5 A schematic diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0058] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0059] In the description of the embodiments of the present disclosure, it should be understood that terms such as "including" or "having" are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or a combination thereof in the specification, and do not exclude the possibility of the presence of one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof.
[0060] Unless otherwise specified, “ / ” means or. For example, A / B can mean A or B. The “and / or” in this article is merely a way to describe the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.
[0061] The terms "first", "second", etc. are used only to distinguish the same or similar technical features for the convenience of description, and should not be understood as indicating or implying the relative importance or quantity of these technical features. Thus, the features defined by "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise specified, the term "plurality" means two or more than two.
[0062] According to research, the current traditional detection methods include geometric leveling and total station methods, which use level or total station to measure the height difference between the reference point and the observation point. The above methods are suitable for small-scale settlement observation, but there are problems such as high labor input cost, sparse point distribution, long operation cycle, and low degree of automation.
[0063] In order to solve the above technical problems, the related technology also provides a settlement monitoring network solution based on the Global Navigation Satellite System (GNSS). This is mainly because GNSS observation has the characteristics of rapid network deployment, short observation cycle, high accuracy and high degree of automation, and is widely used in control measurement, deformation monitoring and other fields.
[0064] Among them, the establishment of a GNSS settlement monitoring network usually requires the selection of higher-level GNSS control points or regional Cors stations as reference points, the establishment of monitoring points at relatively stable locations with good visibility, and the deployment of relevant GNSS receiving devices at the monitoring points. The monitoring resolution of this method depends on the density of monitoring points. Considering the construction cost, the density of monitoring points is usually around 10km, so it cannot meet the monitoring of fine-grained settlement in cities.
[0065] In addition, a synthetic aperture radar interferometry (Interferometric Synthetic Aperture Radar, InSAR) solution is also provided in the related technology. As a widely used microwave remote sensing technology, InSAR obtains information about the observed object by emitting radar waves to illuminate the target body and receiving the reflected signal. It is an active observation technology. Among them, Differential Synthetic Aperture Radar Interferometry (Differential Synthetic Aperture Radar Interferometry, D-InSAR) uses the phase information of multiple phase SAR complex images to extract surface deformation variables, and its accuracy has reached the cm level. The significant feature of Permanent Scatter InSAR (PS-InSAR) is that the ground with relatively stable phase information and high self-scattering characteristics is selected as the target point, which can reduce the influence of space, time correlation and atmosphere. By monitoring the ground subsidence in an area for a long time, the time-series deformation information of the PS point is obtained, and its monitoring capability of the ground is improved.
[0066] However, InSAR technology also has certain shortcomings in its application. For example, D-InSAR is seriously affected by time decorrelation, spatial decorrelation and atmospheric delay; PS-InSAR technology data processing is more complicated and requires a large number of SAR images. At the same time, it also has high requirements on the stability of the ground objects.
[0067] In summary, traditional detection schemes are not convenient for large-area and high-frequency settlement detection due to the cost of labor input; GNSS solutions involve the establishment of base stations and observation stations, which require high investment and subsequent maintenance costs, and the horizontal spatial resolution of the monitoring range is also low; InSAR-related solutions mainly depend on the richness of SAR images and are mainly suitable for long-term granularity detection and analysis.
[0068] It can be seen that the existing detection schemes have technical defects of one kind or another, and there is an urgent need for a ground subsidence detection scheme with a higher degree of automation, better real-time performance and wider coverage.
[0069] In order to at least partially solve one or more of the above-mentioned problems and other potential problems, the present disclosure provides a ground subsidence detection method, device, equipment and storage medium to extract high-precision geographic element data through multi-information sensing to achieve high-frequency and quasi-real-time ground subsidence detection within the operating range.
[0070] In order to clearly explain the embodiments of the present disclosure, some concepts that may appear in subsequent embodiments will first be introduced.
[0071] 1) Simultaneous localization and mapping (SLAM) technology
[0072] As one of the key technologies for robot perception and navigation, SLAM technology aims to use the robot's own perception and control information in an unknown environment to simultaneously build a map and locate itself, so that the robot can accurately and autonomously navigate and move in the environment. SLAM technology estimates the robot's position (position and posture) by processing sensor data (such as lidar, camera, etc.). In this process, data association, state estimation and map representation are the core issues.
[0073] The basis of SLAM technology is to use sensors to obtain current environmental information and process this information to obtain a map and the position of the robot. In addition, SLAM technology has a wide range of applications in many fields. In the field of robotics, it is a key technology for achieving autonomous navigation, path planning and environmental perception.
[0074] Based on the sensor type, SLAM technology can be divided into:
[0075] LiDAR SLAM: LiDAR scans the surrounding environment, obtains point cloud data, and then uses algorithms to process it to achieve robot positioning and mapping. LiDAR can be divided into 2D LiDAR and 3D LiDAR. The appropriate type of LiDAR should be selected according to the characteristics of the environment.
[0076] Visual SLAM: Use cameras to obtain image information and achieve positioning and mapping through image processing algorithms. Depending on the working mode of the camera, visual SLAM can be divided into three types: monocular camera, binocular camera and depth camera.
[0077] Inertial Navigation SLAM: Use the Inertial Measurement Unit (IMU) to obtain the robot's acceleration and angular velocity information, and achieve positioning and mapping through the kinematic model.
[0078] In addition, there is multi-sensor fusion SLAM, which is a technical solution designed to solve the limitations of a single sensor in complex environments.
[0079] Based on the algorithm type, SLAM technology can be divided into:
[0080] Filter-based SLAM: Positioning and mapping are achieved through algorithms such as Kalman filter and extended Kalman filter.
[0081] Optimization-based SLAM: Positioning and mapping are achieved through least squares method, nonlinear optimization and other algorithms.
[0082] SLAM based on deep learning: Using deep learning technology for positioning and mapping is a research direction that has emerged in recent years.
[0083] 2) High-precision map related technologies
[0084] High-precision map technology refers to a technology that uses advanced remote sensing, geographic information system (GIS), positioning and data processing technology to measure, model and display the geographical environment with high precision. Compared with traditional navigation maps, high-precision maps have higher spatial resolution, richer geographic information and more accurate positioning capabilities. Its characteristics are mainly reflected in the following aspects:
[0085] High precision: HD maps can provide centimeter-level or even millimeter-level geospatial data, providing reliable navigation and positioning information for applications such as autonomous driving and drones.
[0086] Data richness: HD maps not only contain infrastructure information such as road networks and traffic signals, but also detailed information such as lane lines, curbs, traffic signs, etc., providing comprehensive support for various intelligent applications.
[0087] Real-time: HD maps can update dynamic information such as road conditions and weather in real time to ensure the accuracy and timeliness of the information.
[0088] The production of high-precision map data is closely related to SLAM technology. Map information constructed based on SLAM technology, combined with image recognition, segmentation, point cloud data recognition, segmentation and other achievements, can extract map elements with a high degree of automation.
[0089] 3) Pavement disease related technologies
[0090] Road damage refers to the deformation, damage and cracking of road materials under the influence of vehicle loads, natural environment, etc. Common types of road damage include cracks, potholes, rutting, looseness, etc. The causes of these damages are varied, mainly including material aging, unreasonable design, poor construction quality, overloaded transportation, environmental factors, etc.
[0091] Road damage is usually divided into structural damage and functional damage, among which structural damage is one of the important manifestations of road damage. It is mainly manifested in deformation, fracture and damage of the road surface, such as longitudinal cracks, transverse cracks, cracks, potholes, etc. These damages will destroy the overall structure of the road surface and affect the bearing capacity and stability of the road surface. For the prevention and repair of road damage, first of all, we must strengthen the standardized management of design and construction and improve the quality of the project. Secondly, we must regularly inspect and maintain the roads to detect and deal with the damage in a timely manner.
[0092] To facilitate understanding of this embodiment, a ground subsidence detection method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the ground subsidence detection method provided in the embodiment of the present disclosure is generally an electronic device with certain computing capabilities, and the electronic device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, etc. In some possible implementations, the ground subsidence detection method can be implemented by a processor calling a computer-readable instruction stored in a memory.
[0093] See also Figure 1 , which shows a flow chart of a ground subsidence detection method provided by an embodiment of the present disclosure, the method comprising the following steps S101 to S104:
[0094] S101: Acquire multiple types of first ground information currently collected, where each type of first ground information is obtained based on information sensing performed by a corresponding collection device on a target detection area;
[0095] S102: extracting first target element data within the target detection area in the current time phase based on a plurality of first ground information;
[0096] S103: searching for second target element data matching the first target element data from the pre-constructed multi-level and multi-block element structure; the second target element data and the first target element data have different time phases;
[0097] S104: Determine the displacement generated by the same target element based on the difference operation between the first target element data and the second target element data, where the displacement is used to indicate the degree of settlement of the target detection area.
[0098] The ground subsidence detection method provided by the embodiment of the present disclosure can, when obtaining a variety of first ground information currently collected, extract the first target element data within the target detection area in the current phase based on the multiple first ground information; then search for the second target element data matching the first target element data from the pre-constructed multi-level and multi-block element structure, and determine the displacement generated by the same target element based on the difference operation between the first target element data and the second target element data.
[0099] Among them, the first target element data is extracted from a variety of first ground information, thereby ensuring the high accuracy of the element data itself, and then the second target element data matching the first target element data can be quickly found through the pre-built multi-level and multi-block element structure, which will significantly improve the efficiency of subsequent ground subsidence detection. In addition, based on the data difference between two element data with different phases, the determined degree of subsidence can be made more accurate.
[0100] In the disclosed embodiment, high-precision geographic element information is obtained through a multi-sensor fusion system (corresponding to multiple acquisition devices). Each acquisition device here can determine a first ground information by sensing the corresponding information for the target detection area. The acquisition devices may include, for example, LiDAR, IMU, camera, Global Positioning System (GPS), etc., and may also be other devices, which are not specifically limited here. Based on the various first ground information actually collected by these acquisition devices, relevant first target element data can be extracted. The first target element here can be a relatively stable geographic element in the entire detection area, such as a road surface, road surface defects (cracks, potholes, etc.), immovable guardrails on the road side, and relatively fixed rods, etc., which are not specifically limited here.
[0101] Here, before extracting the first target element data based on various first ground information, it is necessary to ensure that the data content and accuracy meet the requirements of the subsequent operation. The strategies that can be adopted in the embodiments of the present disclosure are as follows:
[0102] First, various acquisition devices can be assembled on a mobile platform (such as a vehicle). Key devices such as LiDAR, IMU, and cameras need to be calibrated in advance to obtain internal and external parameters of the device, arm values, etc., to ensure that the acquisition parameters are accurate. Before acquisition, make sure that the GPS device and IMU device have entered the convergence state.
[0103] During the data collection process, it is necessary to ensure that each device is time-aligned based on the GPS clock synchronization function so that the location, point cloud, video and other information can be accurately matched; in addition, in order to improve the accuracy of positioning, the centimeter-level high-precision positioning service of Qianxun Zhicun (FindCM) can be combined to record the differential location data of the device in real time. In areas where Qianxun service coverage is incomplete, the base station mode can also be adopted to obtain differential location data.
[0104] To facilitate parallel processing of collected data in the later stage, all raw data can be split according to fixed time, fixed size and other strategies based on time sequence, such as organizing data according to a fixed 1 minute; during data collection, to ensure that the needs of later data processing are met, GPS and IMU devices can use the highest frequency of the device to obtain information. Video and LiDAR devices can adopt a variable frequency data collection mode according to the running speed of mobile platforms such as vehicles, while meeting the corresponding spatial coverage and overlap, to reduce data storage and improve later processing efficiency.
[0105] Based on the various first ground information extracted above, the extraction of the first target element can be achieved through information fusion. For example, the SLAM technology combining vision and LiDAR can be used to achieve data fusion and element extraction. The visual SLAM technology uses the image information captured by the camera for positioning and map construction. The camera can capture rich environmental details, including color, texture, and shape, and visual SLAM has advantages in identifying objects and scenes. LiDAR (laser radar) SLAM technology obtains the distance information of the environment by emitting a laser beam and measuring its reflection time. LiDAR has the advantages of high ranging accuracy and is not easily affected by lighting conditions, and can work stably in various environments. The combination of vision and LiDAR technology achieves mutual complementation and gives full play to their respective advantages.
[0106] Considering that the first target elements available for extraction in the disclosed embodiment have different element characteristics, the elements can be classified in advance, for example, they can be divided into four types of elements: road surface, road surface disease (cracks, potholes, etc.) data, immovable guardrails on the road side, and relatively fixed rods as key extraction targets. For different target elements, the fusion information actually used here may not be the same. For example, for linear elements, the element data can be extracted by combining laser point cloud and image information. For point elements, the element data can be extracted directly based on laser point cloud.
[0107] Next, we will explain the specific feature data extraction process in combination with different types of first target features.
[0108] When the element type of the first target element belongs to the road surface element type, the elevation data of any coordinate point in the road surface in the target detection area is determined based on the laser point cloud information in the multiple first ground information, and is used as the first target element data.
[0109] In practical applications, high-precision ground feature data can be extracted based on filter methods based on point cloud information, such as the Cloth Simulation Filtering (CSF) method or supervised / unsupervised machine learning algorithms. The road surface needs to be expressed as an irregular triangulated network (TIN) mode according to the road section so that the elevation information of any coordinate point on the road surface can be determined.
[0110] It should be noted that for road scenes with overpasses, it is necessary to ensure that the road sections themselves do not intersect with each other. If such a situation occurs, the road sections need to be split to ensure that the road surface itself does not have spatial self-intersection (overlap).
[0111] When the element type of the first target element belongs to the road surface disease element type, element recognition is performed based on the image information in the multiple first ground information, and the element recognition result is projected onto the laser point cloud ground area indicated in the multiple first ground information, and the disease data on the target detection area is extracted and used as the first target element data.
[0112] In practical applications, for road surface defects (cracks, potholes, etc.), it is necessary to combine the image recognition detection model and segmentation model, project the recognition results onto the point cloud ground, and extract the linear or surface elements on the ground.
[0113] When the element type of the first target element belongs to the linear guardrail element type, point cloud segmentation is performed based on the laser point cloud information in the multiple first ground information, and the highest point connection line data close to the inner side of the road in the target detection area indicated in the point cloud segmentation result is used as the first target element data.
[0114] In practical applications, linear guardrail elements can be expressed by the line connecting the highest points close to the inner side of the road based on the classified point cloud segmentation results, and the digitized direction of the line is the same as the road travel direction.
[0115] When the element type of the first target element belongs to the rod-shaped object element type, the rod-shaped object data in the target detection area is determined based on the laser point cloud information in the plurality of first ground information, and is used as the first target element data.
[0116] In practical applications, pole-shaped objects such as lamp poles can be expressed by taking their pole vertices as point elements, or by taking the line connecting their highest and lowest points.
[0117] It should be noted that in the process of factor extraction, "abnormal" data needs to be verified and eliminated. For example, guardrails that have collapsed or been damaged due to traffic accidents cannot be used as result data. Another example is urban road construction, and the road surface under construction cannot be used as result data.
[0118] When determining the first target element data in the target detection area in the current phase, the disclosed embodiment can match the elements in combination with the relevant element data in the historical phase, so as to confirm the displacement generated for the same target element. That is, the disclosed embodiment realizes multi-phase data analysis. In practical applications, for example, a laser scanner and a positioning and attitude determination system mounted on a mobile platform can obtain high-frequency multi-phase point cloud data, extract road point cloud data from the multi-phase point cloud data in the same area, perform regular grid processing on the registered point cloud data, generate elevation grid data, perform Gaussian filtering on the elevation grid data, and then calculate and analyze the data difference (corresponding to the displacement) of the same road section in multiple times, obtain the road settlement area, and can analyze the settlement amount, settlement velocity, settlement acceleration, etc. of the settlement area in detail, classify the road collapse into early warning levels, and so on.
[0119] Among them, the management of multi-phase target elements can be achieved through the pre-built multi-level and multi-block element structure. Data of different phases in the detection area can be distinguished by data labels so that fast access to data of the specified phase can be achieved. Data of the same phase (or time period) in the detection area usually requires multi-task collection. For example, each task corresponds to collecting a section of the detection area, and each task covers the entire detection area. Data between different tasks often need to be fused.
[0120] Here, for the data collected for a single task, the data accuracy and recall rate need to be verified. Only the data that passes the quality inspection can enter the database corresponding to the multi-level and multi-block feature structure. For data between different tasks, it is necessary to ensure that the coordinate systems between tasks match and remove redundant data.
[0121] In order to facilitate the rapid retrieval of data later, feature data can be stored in blocks and layers. The data block mechanism can be a fixed grid size mode, such as a grid with fixed latitude and longitude intervals, or a manually specified area mode, such as road segmentation; here it is necessary to ensure that the data of the same type of features in multiple phases follow a unified data block mechanism.
[0122] In addition, the data stratification mechanism here can be stratified according to the morphological type and classification of the target elements. For example, the ground type element is a surface element that can be divided into a single layer, thus forming a multi-level and multi-block element structure. Specifically, the multi-level and multi-block element structure can be constructed according to the following steps:
[0123] Step 1: Acquire a plurality of second ground information collected in advance in the target detection area;
[0124] Step 2: extracting at least one second target element data in the target detection area based on the pre-collected multiple second ground information;
[0125] Step three: based on the element type to which each second target element data belongs and the pre-segmentation of the target detection area, determine the corresponding position of each second target element data in the multi-level and multi-block element structure.
[0126] Among them, for the multi-level multi-block element structure including a multi-level substructure and a multi-block substructure, for each second target element data, the corresponding position of the second target element data in the multi-level substructure can be determined based on the correspondence between the element type to which the second target element data belongs and the multi-element type corresponding to the multi-level substructure; it is also possible to determine the corresponding position of the second target element data in the multi-block substructure based on the correspondence between the element position indicated by the second target element data and the multiple detection ground area blocks corresponding to the multi-block substructure when it is determined that the target detection area includes a plurality of pre-divided detection ground area blocks. Based on this, the block in which each second target element is located in the multi-level multi-block element structure and the specific level within the block can be determined.
[0127] As time goes by, the multi-level and multi-block feature structure here can be continuously updated. For example, the first target feature data extracted in the current phase is stored in a pre-built multi-level and multi-block feature structure to achieve structural update.
[0128] Here, since the elements of the same time phase are managed in blocks and layers, the matching of elements of different time phases can be processed in parallel in blocks and layers, which will significantly improve the detection efficiency. For the matching of elements in each block, it can be carried out according to the matching strategy of three types of elements: points, lines, and surfaces. This is mainly because the physical shapes involved, whether it is the road surface, road disease (cracks, potholes, etc.) data, immovable guardrails on the road side, and relatively fixed rods, can be divided into three expression shapes: points, lines, and surfaces. Next, the matching process of multi-temporal target elements will be explained in combination with different element types.
[0129] First, for the first target element of the point element type, element matching can be achieved by following the steps below:
[0130] Step 1: based on the attribute information of the first target element and the orientation information between the first target element and the reference element, point search is performed on the multi-level and multi-block element structure within the spatial position to obtain element data with the same attributes within a preset search range;
[0131] Step 2: Determine the retrieved element data as second target element data that matches the first target element data.
[0132] Here, the point feature can be searched by its orientation in the road, its attributes, and its spatial position, and the matching can be completed by finding the point data with the same attributes within the search range.
[0133] For scenarios with large position offsets and dense point features, a bipartite graph matching strategy can be combined. For example, the Hungarian algorithm is used to solve the maximum matching problem of bipartite graphs. The core idea is to gradually increase the number of matching edges by finding and replacing a series of augmenting paths until no augmenting paths can be found. In the process of applying this algorithm, the fact that the lengths of all edges in the final matching result are close to being equal is one of the reference criteria for the final selection result.
[0134] like Figure 2(a) and 2(b) Shown are schematic diagrams of the effects of an example rod-shaped object before and after matching.
[0135] Secondly, for the first target element of the linear element type, element matching can be achieved by following the steps below:
[0136] Step 1: Calculate the distance between the first target element and the second target element to be matched in the multi-level and multi-block element structure;
[0137] Step 2: Determine the second target feature data with the largest distance confidence as the second target feature data matching the first target feature data.
[0138] For line feature matching, the main idea is to calculate the confidence based on the distance from the upper point on the line to be matched to all matching candidates within a certain search range, and select the candidate with the highest confidence as the matching result.
[0139] Here, in order to improve the matching rate and matching effect, the matching process can be optimized using the Viterbi algorithm.
[0140] Taking the matching of linear road damage elements as an example, the key point of applying the Viterbi algorithm is to define the transition probability and emission probability. The transition probability mainly refers to the probability of transferring from one matching segment to another matching segment, which is usually calculated based on the topological structure of the damage quality inspection, and the emission probability is mainly estimated by referring to the distance between the current data and the original data.
[0141] like Figure 3(a) and 3(b) Shown are schematic diagrams of the effects of the example linear disease elements before and after matching.
[0142] Thirdly, for the first target element of the planar element type, element matching can be achieved by following the steps below:
[0143] Step 1: searching for second target element segments matching each contour segment included in the first target element from the multi-level and multi-block element structure;
[0144] Step 2: Combine the determined second target element segments to determine the second target element data that matches the first target element data.
[0145] In practical applications, the matching of planar road surfaces is mainly based on road segments. Once the road segment matching is determined, any point in the current segment can be projected onto the comparison road segment to obtain the corresponding point.
[0146] After matching the first target element with the second target element according to the above-mentioned various matching schemes, the difference between the two target element data can be determined, and then the displacement generated by the same target element can be determined. In the embodiment of the present disclosure, after determining the matching relationship between the elements, the displacements such as horizontal displacement and vertical displacement can be calculated. For example, for an element that was originally perpendicular to the ground (such as a lamp pole), its displacement relative to the ground angle can also be calculated.
[0147] The ground subsidence detection method provided by the embodiment of the present disclosure can determine the subsidence deformation area where subsidence actually exists, and specifically includes the following steps:
[0148] Step 1: Based on the displacement generated by each target element, determine to filter out the initial settlement deformation area from the target detection area;
[0149] Step 2: In the initial settlement deformation area, the deformation variable is verified by superimposing other element data to determine the final settlement deformation area and the overall deformation variable of the final settlement deformation area.
[0150] In practical applications, the initial settlement deformation area can be filtered out by specifying the vertical deformation threshold and the size of the horizontal deformation impact area. In this deformation area, the linear guardrail data and the deformation of the point / line type light pole elements can be superimposed to verify the deformation amount, thereby giving the final settlement deformation area and its deformation amount.
[0151] The subsidence deformation area here may be a collection of blocks with a greater degree of subsidence selected from various blocks.
[0152] In addition, the embodiments of the present disclosure also provide various settlement monitoring feedback strategies. For example, based on the displacement generated for the same target element in different phases, the deformation trend analysis results for the target detection area are determined, and then the implementable ground settlement monitoring feedback strategies are determined based on the deformation trend analysis results.
[0153] In practical applications, the deformation trend analysis of regional subsidence can be formed by calculating and comparing multiple adjacent phase data. In addition, by analyzing the changes in the coverage area of ground disease data and the number of diseases, it can also be used as a basis for dividing key areas to increase the frequency of data collection, so as to make more timely monitoring feedback on ground subsidence.
[0154] Compared with the prior art that only uses the ground as the basis for settlement judgment, this application, in addition to the ground, innovatively uses characteristic elements such as road surface diseases and lamp poles for comparative analysis. The increase in ground diseases has a certain correlation with ground settlement and can be used as one of the key contents of the analysis. In addition, the changes in the spatial position of isolated elements such as lamp poles (vertical changes and tilt changes) can also provide a strong basis for settlement monitoring. At the same time, mutual verification between multiple elements can also help improve the accuracy of settlement analysis and reduce false alarms.
[0155] In the description of this specification, the description with reference to the terms "some possible embodiments", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure, and the above terms do not necessarily represent the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.
[0156] About the method flow chart of the embodiment of the present disclosure, some operations are described as different steps performed in a certain order. Such a flow chart is illustrative and not restrictive. Some steps described in this article can be grouped together and performed in a single operation, or some steps can be divided into multiple sub-steps, and some steps can be performed in an order different from that shown in this article. The various steps shown in the flow chart can be implemented in any way by any circuit structure and / or tangible mechanism (for example, by software running on a computer device, hardware (for example, a logical function implemented by a processor or a chip), etc., and / or any combination thereof).
[0157] Those skilled in the art will appreciate that, in the method described in the above specific implementation, the writing order of each step does not mean a strict execution order, and the specific execution order of each step should be determined by its function and possible internal logic.
[0158] Based on the same inventive concept, a ground subsidence detection device corresponding to the ground subsidence detection method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned ground subsidence detection method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.
[0159] Reference Figure 4 , which is a schematic diagram of a ground subsidence detection device provided by an embodiment of the present disclosure, the device includes: an acquisition module 401, an extraction module 402, a search module 403, and a detection module 404; wherein,
[0160] An acquisition module 401 is used to acquire a plurality of first ground information currently collected, each of which is obtained based on information sensing performed by a corresponding collection device on a target detection area;
[0161] An extraction module 402 is used to extract first target element data in the target detection area in the current phase based on a plurality of first ground information;
[0162] A search module 403 is used to search for second target element data matching the first target element data from the pre-built multi-level and multi-block element structure; the second target element data is different in time phase from the first target element data;
[0163] The detection module 404 is used to determine the displacement generated by the same target element based on the difference operation between the first target element data and the second target element data, and the displacement is used to indicate the degree of settlement of the target detection area.
[0164] By adopting the above-mentioned ground subsidence detection device, when a plurality of first ground information currently collected is obtained, the first target element data in the target detection area in the current phase can be extracted based on the plurality of first ground information; and then the second target element data matching the first target element data is searched from the pre-constructed multi-level and multi-block element structure, and the displacement generated by the same target element is determined based on the difference operation between the first target element data and the second target element data. The first target element data disclosed in the present invention is extracted from a plurality of first ground information, thereby ensuring the high precision of the element data itself, and then the second target element data matching the first target element data can be quickly searched through the pre-constructed multi-level and multi-block element structure, which will significantly improve the efficiency of subsequent ground subsidence detection. In addition, based on the data difference between two element data with different phases, the determined degree of subsidence can be made more accurate.
[0165] In a possible implementation, the search module 403 is specifically configured to pre-build a multi-level and multi-block element structure according to the following steps:
[0166] Acquire a plurality of second ground information collected in advance in the target detection area;
[0167] Extracting at least one second target element data in the target detection area based on the plurality of second ground information collected in advance;
[0168] Based on the element type to which each second target element data belongs and the pre-segmentation of the target detection area, the corresponding position of each second target element data in the multi-level and multi-block element structure is determined.
[0169] In a possible implementation, the multi-level multi-block element structure includes a multi-level substructure and a multi-block substructure; the search module 403 is specifically used to determine the corresponding position of each second target element data in the multi-level multi-block element structure according to the following steps:
[0170] For each second target element data, based on the correspondence between the element type to which the second target element data belongs and the multiple element types corresponding to the multi-level substructure, determine the corresponding position of the second target element data in the multi-level substructure;
[0171] When it is determined that the target detection area includes multiple pre-divided detection ground area blocks, the corresponding position of the second target element data in the multi-block substructure is determined based on the correspondence between the element position indicated by the second target element data and the multiple detection ground area blocks corresponding to the multi-block substructure.
[0172] In a possible implementation, the extraction module 402 is specifically configured to extract the first target element data within the target detection area in the current time phase according to the following steps:
[0173] In response to the fact that the element type of the first target element belongs to the road surface element type, the elevation data of any coordinate point in the road surface in the target detection area is determined based on the laser point cloud information in the plurality of first ground information, and the elevation data is used as the first target element data;
[0174] In response to the element type of the first target element belonging to the road surface disease element type, element recognition is performed based on the image information in the plurality of first ground information, and the element recognition result is projected onto the laser point cloud ground area indicated in the plurality of first ground information, and the disease data on the target detection area is extracted and used as the first target element data;
[0175] In response to the fact that the element type of the first target element belongs to the linear guardrail element type, point cloud segmentation is performed based on the laser point cloud information in the plurality of first ground information, and the highest point connection line data close to the inner side of the road in the target detection area indicated in the point cloud segmentation result is used as the first target element data;
[0176] In response to the element type of the first target element belonging to the rod-shaped object element type, rod-shaped object data in the target detection area is determined based on the laser point cloud information in the plurality of first ground information and used as the first target element data.
[0177] In a possible implementation, the search module 403 is further configured to:
[0178] The first target feature data extracted in the current time phase is stored in a pre-constructed multi-level multi-block feature structure to obtain an updated multi-level multi-block feature structure.
[0179] In a possible implementation, the search module 403 is specifically configured to search for second target feature data matching the first target feature data from the pre-built multi-level and multi-block feature structure according to the following steps:
[0180] In response to the fact that the element type of the first target element belongs to the point element type, based on the attribute information of the first target element and the orientation information between the first target element and the reference element, point search is performed in the spatial position of the multi-level and multi-block element structure to obtain element data with the same attributes within a preset search range;
[0181] The retrieved element data is determined as second target element data matching the first target element data.
[0182] In a possible implementation, the search module 403 is specifically configured to search for second target feature data matching the first target feature data from the pre-built multi-level and multi-block feature structure according to the following steps:
[0183] In response to the feature type of the first target feature being a linear feature type, calculating a distance between the first target feature and a second target feature to be matched in the multi-level multi-block feature structure;
[0184] The second target feature data with the largest distance confidence is determined as the second target feature data matching the first target feature data.
[0185] In a possible implementation, the search module 403 is specifically configured to search for second target feature data matching the first target feature data from the pre-built multi-level and multi-block feature structure according to the following steps:
[0186] In response to the fact that the element type of the first target element belongs to the planar element type, searching for second target element segments matching each contour segment included in the first target element from the multi-level multi-block element structure;
[0187] The determined second target element segments are combined to determine second target element data matching the first target element data.
[0188] In a possible implementation, the detection module 404 is further configured to:
[0189] After determining the displacement generated by the same target element, the initial settlement deformation area is filtered out from the target detection area based on the displacement generated by each target element; in the initial settlement deformation area, the deformation amount is verified by superimposing other element data to determine the final settlement deformation area and the overall deformation amount of the final settlement deformation area.
[0190] In a possible implementation, the detection module 404 is further configured to:
[0191] After determining the displacement generated by the same target element, the deformation trend analysis results for the target detection area are determined based on the displacement generated for the same target element in different phases; and the implementable ground subsidence monitoring feedback strategy is determined based on the deformation trend analysis results.
[0192] It should be noted that the device in the embodiment of the present disclosure can implement each process of the embodiment of the aforementioned method and achieve the same effects and functions, which will not be repeated here.
[0193] The present disclosure also provides an electronic device, such as Figure 5, which is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure, includes: a processor 501, a memory 502, and a bus 503. The memory 502 stores machine-readable instructions executable by the processor 501 (for example, Figure 4 In the device, the acquisition module 401, the extraction module 402, the search module 403, the detection module 404 corresponding to the execution instructions, etc.), when the electronic device is running, the processor 501 and the memory 502 communicate through the bus 503, and the machine-readable instructions are executed by the processor 501 to perform the following processing:
[0194] Acquire multiple types of first ground information currently collected, each type of first ground information is obtained based on information sensing performed by a corresponding collection device on a target detection area;
[0195] Based on the multiple first ground information, extracting the first target element data in the target detection area in the current time phase;
[0196] Searching for second target element data matching the first target element data from a pre-built multi-level multi-block element structure; the second target element data is in a different time phase from the first target element data;
[0197] Based on the difference operation between the first target element data and the second target element data, the displacement generated by the same target element is determined, and the displacement is used to indicate the degree of settlement of the target detection area.
[0198] The present disclosure also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the ground subsidence detection method described in the above method embodiment are executed. The storage medium may be a volatile or non-volatile computer-readable storage medium.
[0199] The embodiments of the present disclosure also provide a computer program product, which carries a program code. The instructions included in the program code can be used to execute the steps of the ground subsidence detection method described in the above method embodiment. Please refer to the above method embodiment for details, which will not be repeated here.
[0200] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).
[0201] Each embodiment in the present disclosure is described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and computer-readable storage medium embodiments, since they are basically similar to the method embodiments, their descriptions are simplified, and the relevant parts can be referred to the partial description of the method embodiments.
[0202] The apparatus, equipment and computer-readable storage medium provided in the embodiments of the present disclosure correspond one-to-one to the method. Therefore, the apparatus, equipment and computer-readable storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the apparatus, equipment and computer-readable storage medium will not be repeated here.
[0203] It should be understood by those skilled in the art that the embodiments of the present disclosure can be implemented in the form of methods and apparatus (devices or systems), or computer-readable storage media. Therefore, the present disclosure can be implemented in a complete hardware implementation, a complete software implementation, or an implementation that combines software and hardware. Moreover, the present disclosure can be implemented in the form of a computer-readable storage medium implemented on one or more computer-usable storage media (including but not limited to disk storage, read-only compact disk storage (CD-ROM), optical storage, etc.) containing computer-usable program code.
[0204] The present disclosure is described with reference to the flowchart and / or block diagram of the method, device (equipment or system) and computer-readable storage medium according to the embodiment of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, and the combination of the process and / or box in the flowchart and / or block diagram 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.
[0205] These computer program instructions may also be stored in a computer-readable memory that can direct 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 a product including an instruction device, wherein the instruction device implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.
[0206] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.
[0207] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0208] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory (Flash RAM). The memory is an example of a computer-readable medium.
[0209] Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory, read-only memory, electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. In addition, although the operations of the disclosed method are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. In addition, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple sub-steps.
[0210] Although the spirit and principle of the present disclosure have been described above with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.
Claims
1. A method for detecting ground subsidence, characterized in that: include: Acquire multiple types of first ground information currently collected, each type of first ground information is obtained based on information sensing performed by a corresponding collection device on a target detection area; Based on the multiple types of first ground information, extracting first target element data within the target detection area in the current phase; Searching for second target element data matching the first target element data from a pre-constructed multi-level and multi-block element structure; The second target element data is in a different time phase from the first target element data; Based on the difference operation between the first target element data and the second target element data, the displacement generated by the same target element is determined, and the displacement is used to indicate the degree of settlement of the target detection area.
2. The method according to claim 1, characterized in that: The multi-level and multi-block element structure is pre-built according to the following steps: Acquire a plurality of second ground information collected in advance in the target detection area; Extracting at least one second target element data in the target detection area based on a plurality of second ground information collected in advance; Based on the element type to which each of the second target element data belongs and the pre-segmentation of the target detection area, the corresponding position of each of the second target element data in the multi-level and multi-block element structure is determined.
3. The method according to claim 2, characterized in that The multi-level and multi-block element structure includes a multi-level substructure and a multi-block substructure; Determining the corresponding position of each of the second target element data in the multi-level multi-block element structure includes: For each second target element data, based on the correspondence between the element type to which the second target element data belongs and the multiple element types corresponding to the multi-level substructure, determining the corresponding position of the second target element data in the multi-level substructure; When it is determined that the target detection area includes multiple pre-divided detection ground area blocks, the corresponding position of the second target element data in the multi-block substructure is determined based on the correspondence between the element position indicated by the second target element data and the multiple detection ground area blocks corresponding to the multi-block substructure.
4. The method according to any one of claims 1 to 3, characterized in that The extracting the first target element data in the target detection area at the current time phase includes: In response to the element type of the first target element belonging to the road surface element type, determining the elevation data of any coordinate point in the road surface in the target detection area based on the laser point cloud information in the plurality of first ground information, and using the elevation data as the first target element data; In response to the element type of the first target element belonging to the road surface damage element type, element recognition is performed based on the image information in the plurality of first ground information, and the element recognition result is projected onto the laser point cloud ground area indicated in the plurality of first ground information, and the damage data on the target detection area is extracted as the first target element data; In response to the fact that the element type of the first target element belongs to the linear guardrail element type, point cloud segmentation is performed based on the laser point cloud information in the plurality of first ground information, and the highest point connection line data close to the inner side of the road in the target detection area indicated in the point cloud segmentation result is used as the first target element data; In response to the fact that the element type of the first target element belongs to the rod-shaped object element type, rod-shaped object data in the target detection area is determined based on the laser point cloud information in the plurality of first ground information, and is used as the first target element data.
5. The method according to any one of claims 1 to 3, characterized in that The method further comprises: The first target feature data extracted in the current time phase is stored in a pre-constructed multi-level multi-block feature structure to obtain an updated multi-level multi-block feature structure.
6. The method according to any one of claims 1 to 3, characterized in that The searching for second target element data matching the first target element data from the pre-built multi-level and multi-block element structure includes: In response to the element type of the first target element belonging to the point element type, based on the attribute information of the first target element and the orientation information between the first target element and the reference element, point search is performed on the multi-level and multi-block element structure within the spatial position to obtain element data with the same attributes within a preset search range; The retrieved element data is determined as second target element data matching the first target element data.
7. The method according to any one of claims 1 to 3, characterized in that The searching for second target element data matching the first target element data from the pre-built multi-level and multi-block element structure includes: In response to the feature type of the first target feature belonging to the linear feature type, calculating the distance between the first target feature and a second target feature to be matched in the multi-level multi-block feature structure; The second target feature data with the largest distance confidence is determined as the second target feature data matching the first target feature data.
8. The method according to any one of claims 1 to 3, characterized in that The searching for second target element data matching the first target element data from the pre-built multi-level and multi-block element structure includes: In response to the fact that the element type of the first target element belongs to the planar element type, searching for a second target element segment matching each contour segment included in the first target element from the multi-level multi-block element structure; The determined second target element segments are combined to determine second target element data matching the first target element data.
9. The method according to any one of claims 1 to 3, characterized in that After determining the displacement amount generated by the same target element, the method further includes: Based on the displacement generated by each target element, determine to filter out the initial settlement deformation area from the target detection area; In the initial settlement deformation area, the deformation amount is verified by superimposing other element data to determine the final settlement deformation area and the overall deformation amount of the final settlement deformation area.
10. The method according to any one of claims 1 to 3, characterized in that After determining the displacement amount generated by the same target element, the method further includes: Determine a deformation trend analysis result for the target detection area based on the displacements generated for the same target element at different time phases; Based on the deformation trend analysis results, an implementable ground subsidence monitoring feedback strategy is determined.
11. A ground subsidence detection device, characterized in that: include: An acquisition module, used to acquire a plurality of first ground information currently collected, each of which is obtained based on information sensing performed by a corresponding acquisition device on a target detection area; An extraction module, configured to extract first target element data in the target detection area at a current time phase based on the multiple types of first ground information; A search module, used for searching second target element data matching the first target element data from a pre-built multi-level and multi-block element structure; The second target element data is in a different time phase from the first target element data; The detection module is used to determine the displacement generated by the same target element based on the difference operation between the first target element data and the second target element data, and the displacement is used to indicate the degree of settlement of the target detection area.
12. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the ground subsidence detection method as described in any one of claims 1 to 10 is executed.
13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the ground subsidence detection method according to any one of claims 1 to 10 is executed.
Citation Information
Patent Citations
System for settlement monitoring based on laser three-dimensional modeling
CN110617796A
Method applied to road settlement detection
CN111336986A
Method for predicting local collapse of urban road by using vehicle-mounted LiDAR system
CN112164098A
Ground surface settlement observation method and system based on multiple sensors
CN113269867A
Roadbed engineering settlement monitoring method and device and electronic equipment
CN113739755A
