Method and device for determining offset of landslide body, electronic equipment and storage medium

Abstract

The application provides a landslide body offset generation determination method and device, electronic equipment and a storage medium. The determination method comprises: preprocessing obtained current point cloud data to obtain current point cloud model data; determining a target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data; for each target local monitoring area corresponding to the initial point cloud model data, obtaining the point cloud data corresponding to the target local monitoring area in the current point cloud model data, and determining whether the difference between the average distance of the point cloud data to the fitting plane corresponding to the target local monitoring area and the initial distance corresponding to the target local monitoring area is greater than a preset distance threshold; if yes, it is determined that the landslide body generates offset in the target local monitoring area. The technical solution provided by the application can improve the convenience and efficiency of determining the generation of landslide body offset.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of landslide detection, in particular to a landslide displacement determination method and device, electronic equipment and a storage medium. BACKGROUND

[0002] The landslide is the part of soil or rock that slides downward on the slope. In order to avoid accidents caused by landslides and other natural disasters, it is necessary to dynamically monitor the landslide. As one of the spatial information technologies, the laser radar technology has important role and advantage in the dynamic monitoring of landslides and other natural disasters because it is not affected by weather and surrounding natural environment and has high data collection efficiency and resolution.

[0003] At present, the landslide monitoring scheme usually manually sets the monitoring area before monitoring to exclude the ground, buildings, vegetation and the like, obtains point cloud data in different time periods in the monitoring area, and compares. In the comparison process, the distance from a point to another point or from a point to a plane in a unit cell is usually calculated to represent the local displacement. However, this method needs to manually frame the local area by the operator because the local landslide often has weeds or complex features, and the operation is complex. Moreover, the laser incidence angle is too large in the local area of the landslide with complex features, which increases the laser distance error and affects the monitoring accuracy and stability. In addition, when there are complex features in the local area of the landslide, the distribution of point clouds in the unit cell is inconsistent between the front and back, which easily causes large displacement during point cloud comparison, resulting in false positives. Therefore, how to determine the displacement of the landslide has become a problem to be solved. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a landslide displacement determination method and device, electronic equipment and a storage medium, which can automatically extract a target local monitoring area by analyzing the attributes of point cloud data, compare point cloud models based on the automatically extracted target local monitoring area, analyze whether the landslide has displacement, and replace the operator's manual setting of multiple monitoring areas. The operation complexity is reduced, and the convenience and efficiency of determining the displacement of the landslide are improved.

[0005] The present application mainly includes the following aspects:

[0006] In a first aspect, the present application provides a landslide displacement determination method, which comprises:

[0007] Obtaining current point cloud data obtained by scanning the monitoring area of the landslide by a measuring device;

[0008] Pretreating the current point cloud data to obtain current point cloud model data;

[0009] obtaining an initial point cloud model data obtained in advance, determining a target local monitoring area corresponding to the initial point cloud model data based on attributes of each point cloud data in the initial point cloud model data;

[0010] For each target local monitoring area corresponding to the initial point cloud model data, obtaining the point cloud data corresponding to the target local monitoring area in the current point cloud model data, and determining whether the difference between the average distance from the point cloud data corresponding to the target local monitoring area in the current point cloud model data to the fitting plane corresponding to the target local monitoring area and the initial distance corresponding to the target local monitoring area is greater than a preset distance threshold value;

[0011] If yes, it is determined that the landslide body has a deviation in the target local monitoring area.

[0012] Further, the step of determining the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data comprises:

[0013] Based on the curvature and spatial position of each point cloud data in the initial point cloud model data, clustering each point cloud data in the initial point cloud model data to obtain a plurality of clustering areas of the initial point cloud model data;

[0014] For each clustering area, performing plane fitting on the point cloud data in the clustering area to obtain a fitting plane corresponding to the clustering area, and determining a vector perpendicular to the fitting plane corresponding to the clustering area as a normal vector corresponding to the clustering area;

[0015] Obtaining the centroid of the point cloud data in the clustering area, and determining a direction vector from the centroid of the point cloud data in the clustering area to the coordinate origin of the measuring device as a target vector corresponding to the clustering area;

[0016] Based on the target vector corresponding to the clustering area, determining whether the included angle between the target vector corresponding to the clustering area and the normal vector corresponding to the clustering area is less than a preset included angle threshold value;

[0017] If yes, the clustering area is determined as the target local monitoring area corresponding to the initial point cloud model data.

[0018] Further, the step of clustering each point cloud data in the initial point cloud model data based on the curvature and spatial position of each point cloud data in the initial point cloud model data to obtain a plurality of clustering areas of the initial point cloud model data comprises:

[0019] Based on the curvature of each point cloud data in the initial point cloud model data, the point cloud data with a curvature greater than a preset curvature threshold is removed to obtain target point cloud data in the initial point cloud model data.

[0020] Based on the spatial position of each point cloud data in the initial point cloud model data, each target point cloud data in the initial point cloud model data is clustered to obtain a plurality of clustering regions of the initial point cloud model data.

[0021] Further, the initial distance corresponding to the target local monitoring region is determined by the following steps:

[0022] The distance from each point cloud data in the initial point cloud model corresponding to the target local monitoring region to the fitting plane corresponding to the target local monitoring region is obtained.

[0023] The sum of the distance from each point cloud data in the initial point cloud model corresponding to the target local monitoring region to the fitting plane corresponding to the target local monitoring region is determined as the target distance corresponding to the target local monitoring region.

[0024] The quotient of the target distance and the number of point cloud data in the initial point cloud model corresponding to the target local monitoring region is determined as the initial distance corresponding to the target local monitoring region.

[0025] Further, after determining the target local monitoring region corresponding to the initial point cloud model data, the determination method further comprises:

[0026] Based on the spatial position of each point cloud data in the initial point cloud model data, the axial minimum bounding box of the initial point cloud model data is determined.

[0027] The axial minimum bounding box of the initial point cloud model data is voxel grid divided according to a preset voxel resolution to obtain a voxel grid model of the initial point cloud model data.

[0028] For each target local monitoring region corresponding to the initial point cloud model data, based on the spatial position of each point cloud data in the target local monitoring region, the voxel grid occupied by each point cloud data in the target local monitoring region in the voxel grid model of the initial point cloud model data is marked to obtain the spatial position mark of the target local monitoring region.

[0029] Further, the step of obtaining the point cloud data corresponding to the target local monitoring region in the current point cloud model data comprises:

[0030] Based on the axial minimum bounding box of the initial point cloud model data and the preset voxel resolution, the current point cloud model data is divided into voxel meshes to obtain the voxel mesh model of the current point cloud model data.

[0031] Based on the spatial location markers of the local monitoring area of ​​the target, the current voxel grid corresponding to each spatial location marker in the voxel grid model of the current point cloud model data is determined;

[0032] The point cloud data in the current voxel grid is determined as the point cloud data corresponding to the local monitoring area of ​​the target in the voxel grid model of the current point cloud model data.

[0033] Furthermore, the initial point cloud model data is obtained through the following steps:

[0034] Acquire initial point cloud data of the monitoring area of ​​the landslide;

[0035] The initial point cloud data is preprocessed to obtain initial point cloud model data; wherein the preprocessing includes at least one of the following: spatial clipping, point cloud downsampling, outlier filtering, and moving least squares smoothing.

[0036] Secondly, embodiments of this application also provide a device for determining the displacement of a landslide body, the device comprising:

[0037] The acquisition module is used to acquire the current point cloud data obtained by the measuring equipment scanning the monitoring area of ​​the landslide body;

[0038] The first preprocessing module is used to preprocess the current point cloud data to obtain the current point cloud model data;

[0039] The processing module is used to acquire pre-obtained initial point cloud model data and determine the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data.

[0040] The judgment module is used to obtain the point cloud data corresponding to the target local monitoring area in the current point cloud model data for each target local monitoring area corresponding to the initial point cloud model data, and to determine whether the difference between the average distance of the point cloud data corresponding to the current point cloud model data to the fitting plane corresponding to the target local monitoring area and the predetermined initial distance corresponding to the target local monitoring area is greater than a preset distance threshold.

[0041] The determining module is configured to determine that the landslide body produces a deviation in the target local monitoring area when a difference between an average distance of the corresponding point cloud data in the current point cloud model data to a fitting plane corresponding to the target local monitoring area and a pre-determined initial distance corresponding to the target local monitoring area is greater than a pre-set distance threshold.

[0042] In a third aspect, an electronic device is provided, which includes a processor, a memory, and a bus. The memory stores machine readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory through the bus. The machine readable instructions are executed by the processor to perform the steps of the method for determining a deviation of a landslide body as described above.

[0043] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. When the computer program is run by a processor, the steps of the method for determining a deviation of a landslide body as described above are performed.

[0044] The method for determining a deviation of a landslide body provided by the embodiments of the present application includes: obtaining current point cloud data obtained by scanning a monitoring area of a landslide body by a measuring device; pre-processing the current point cloud data to obtain current point cloud model data; obtaining pre-obtained initial point cloud model data, determining a target local monitoring area corresponding to the initial point cloud model data based on attributes of each point cloud data in the initial point cloud model data; for each target local monitoring area corresponding to the initial point cloud model data, obtaining corresponding point cloud data of the target local monitoring area in the current point cloud model data, and determining whether a difference between an average distance of the corresponding point cloud data in the current point cloud model data to a fitting plane corresponding to the target local monitoring area and a pre-determined initial distance corresponding to the target local monitoring area is greater than a pre-set distance threshold; and if yes, determining that the landslide body produces a deviation in the target local monitoring area.

[0045] In this way, the technical solution provided by the embodiments of the present application can automatically extract a target local monitoring area by analyzing attributes of point cloud data, compare point cloud models based on the automatically extracted target local monitoring area, and analyze whether a landslide body produces a deviation, which can replace the operation of manually setting multiple monitoring areas by an operator, reduces operation complexity, and improves the convenience and efficiency of determining a deviation of a landslide body.

[0046] In order to make the above objectives, characteristics and advantages of the present application more apparent and understandable, the following preferred embodiments are described in detail below, together with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as limiting the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0048] Figure 1 A flow chart of a method for determining landslide body offset is shown;

[0049] Figure 2 A flow chart of another method for determining landslide body offset is shown;

[0050] Figure 3 A structure diagram of a device for determining landslide body offset is shown;

[0051] Figure 4 A structure diagram of another device for determining landslide body offset is shown;

[0052] Figure 5 A structure diagram of an electronic device is shown. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. It should be understood that the drawings in the present application only play the purpose of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual proportion. The flow chart shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow chart can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flow chart or removed from the flow chart under the guidance of the content of the present application by those skilled in the art.

[0054] In addition, the described embodiments are only some of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0055] In order for those skilled in the art to be able to use the present application, the following embodiments are given in connection with the specific application scenario "determination of landslide body offset", and the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of the present application.

[0056] The method, device, electronic device or computer readable storage medium described in the embodiments of the present application can be applied to any scenario where landslide body offset needs to be determined, and the embodiments of the present application do not limit the specific application scenario. Any solution using the method, device, electronic device and storage medium provided by the embodiments of the present application for determining landslide body offset is within the protection scope of the present application.

[0057] It is worth noting that the landslide body is the part of soil or rock that slides down the slope. In order to avoid accidents caused by natural disasters such as landslides, it is necessary to dynamically monitor the landslide body. As one of the spatial information technologies, the laser radar technology plays an important role and has advantages in dynamic monitoring of natural disasters such as landslides because it is not affected by weather and surrounding natural environment and has high data collection efficiency and resolution.

[0058] At present, the landslide body monitoring scheme usually manually sets the monitoring area before monitoring to exclude the ground, buildings, vegetation, etc., obtains point cloud data in the monitoring area at different time periods, and compares. In the comparison process, the distance from point to point and point to surface in a single cell is usually calculated to represent the local displacement. However, this way often needs the operator to manually frame when excluding the local area of the landslide body for monitoring due to the existence of weeds or complex features in the local area of the landslide body, which is complex to operate. Moreover, the landslide body has complex features, and there is a problem of too large laser incidence angle in the local area, which leads to increased laser distance error, affecting the monitoring accuracy and stability. In addition, when there are complex features in the local area of the landslide body, the distribution of point clouds in the front and back cells is inconsistent, which easily causes large displacement during point cloud comparison, leading to false positives. Therefore, how to determine the landslide body offset has become a problem to be solved.

[0059] Based on this, the application provides a landslide body offset determination method and device, electronic equipment and storage medium.

[0060] In this way, the technical scheme provided by the application can automatically extract the target local monitoring area by analyzing the attributes of the point cloud data, compare the point cloud models based on the automatically extracted target local monitoring area, analyze whether the landslide body has offset, and replace the operator's manual operation of setting multiple monitoring areas, thereby reducing the operation complexity and improving the convenience and efficiency of determining the offset of the landslide body.

[0061] To facilitate the understanding of the present application, the technical scheme provided by the application will be described in detail below in conjunction with specific embodiments.

[0062] Please refer to Figure 1 , Figure 1 The flowchart of the landslide body offset determination method provided by the embodiment of the application is shown in Figure 1 The determination method comprises the following steps:

[0063] S101, obtaining current point cloud data obtained by scanning the monitoring area of the landslide body by a measuring device;

[0064] S102, preprocessing the current point cloud data to obtain current point cloud model data;

[0065] In this step, the measuring device can be a laser radar device, which is used to collect the current point cloud data of the monitoring area of the landslide body in real time and preprocess the current point cloud data, so that the current point cloud data is converted into the data required by the model, i.e. the current point cloud model data; here, the preprocessing includes but is not limited to spatial clipping, point cloud down-sampling, outlier filtering, moving least squares smoothing, etc.

[0066] S103, acquire the initial point cloud model data obtained in advance, and determine the target local monitoring area corresponding to the initial point cloud model data based on the attribute of each point cloud data in the initial point cloud model data;

[0067] It should be noted that the initial point cloud model data is obtained through the following steps:

[0068] 1) acquire the initial point cloud data of the monitoring area of the landslide body;

[0069] 2) pre-process the initial point cloud data to obtain the initial point cloud model data;

[0070] In this step, the initial point cloud data of the monitoring area of the landslide body is collected, and the initial point cloud data is pre-processed and converted into the data required by the model, i.e. the initial point cloud model data. The pre-processing here is consistent with the pre-processing of the current point cloud data in step S102.

[0071] In this step, the initial point cloud model data obtained in step S103 is analyzed in terms of local flatness and incident angle, and the effective local monitoring area (i.e. the target local monitoring area) is automatically extracted. By analyzing the local attributes of the point cloud, the effective monitoring area is automatically extracted, which can replace the operation of manually setting multiple monitoring areas by the operator, reduces the operation complexity, and improves the convenience and efficiency of screening the effective local monitoring area.

[0072] It should be noted that please refer to Figure 2 , Figure 2 The flowchart of another method for determining the offset of the landslide body provided by the embodiment of the present application is shown in Figure 2 The step of determining the target local monitoring area corresponding to the initial point cloud model data based on the attribute of each point cloud data in the initial point cloud model data includes:

[0073] S201, cluster each point cloud data in the initial point cloud model data based on the curvature and spatial position of each point cloud data in the initial point cloud model data, to obtain a plurality of clustering areas of the initial point cloud model data;

[0074] In this step, the curvature of any point cloud data in the initial point cloud model is calculated, and for each point cloud data, the curvature and spatial position of the point cloud data are taken as the feature information of the point cloud data. The feature information of each point cloud data in the initial point cloud model is compared, and the point cloud data with similar feature information is taken as a class to obtain a plurality of clustering areas.

[0075] It should be noted that, based on the curvature and spatial position of each point cloud data in the initial point cloud model data, each point cloud data in the initial point cloud model data is clustered to obtain a plurality of clustering regions of the initial point cloud model data, comprising:

[0076] S2011, based on the curvature of each point cloud data in the initial point cloud model data, the point cloud data with curvature greater than a preset curvature threshold is removed to obtain target point cloud data in the initial point cloud model data;

[0077] S2012, based on the spatial position of each point cloud data in the initial point cloud model data, each target point cloud data in the initial point cloud model data is clustered to obtain a plurality of clustering regions of the initial point cloud model data.

[0078] In this step, the preset curvature threshold can be set in advance through historical experience or experimental data. Since there are complex features and weeds and other obstacles in the monitoring area that affect the stability of the monitoring, these complex feature areas are removed, and the relatively flat point cloud data remaining after removal is analyzed by clustering to obtain the clustering region. The curvature information of the point cloud can reflect the sharpness of the local region. The greater the curvature, the more sharp and complex the local feature. Therefore, the point cloud data greater than the preset curvature threshold is removed, so that the relatively complex feature points are removed. Or extract the point cloud data less than or equal to the preset curvature threshold. Secondly, the remaining relatively flat points (i.e. point cloud data less than or equal to the preset curvature threshold) are clustered by a spatial clustering algorithm. In the clustering process, it is prevented that a class contains too many point cloud data or the point cloud data of a class spans too much space. A maximum point threshold is set in advance during clustering. When the number of point cloud data points in a class exceeds the maximum point threshold, the class is terminated, and a new class is generated, thereby obtaining a plurality of clustering regions. The spatial clustering algorithm here can be the Euclidean distance clustering algorithm. This embodiment removes the local complex features from the monitoring area by analyzing the local flatness of the point cloud, which can effectively reduce the uneven distribution of cell point clouds caused by local complex features during overall monitoring, and reduce the problem of false positives, thereby improving the accuracy of landslide body change monitoring.

[0079] S202, for each clustering region, the point cloud data in the clustering region is fitted to a plane to obtain a fitting plane corresponding to the clustering region, and a vector perpendicular to the fitting plane corresponding to the clustering region is determined as a normal vector corresponding to the clustering region;

[0080] S203, the centroid of the point cloud data in the clustering region is obtained, and a direction vector from the centroid of the point cloud data in the clustering region to the coordinate origin of the measuring device is determined as a target vector corresponding to the clustering region;

[0081] S204, determine whether the included angle between the target vector corresponding to the clustering area and the normal vector corresponding to the clustering area is less than a preset included angle threshold based on the target vector corresponding to the clustering area;

[0082] S205, if yes, determine the clustering area as a target local monitoring area corresponding to the initial point cloud model data.

[0083] In this step, the point cloud data of each clustering area obtained in step S202 is subjected to plane fitting to obtain a fitting plane corresponding to each clustering area and a normal vector corresponding to each clustering area; a direction vector of the centroid of the point cloud data of each clustering area to the coordinate origin of the measuring device (laser radar) is calculated, and the included angle between the direction vector and the normal vector is calculated. The region represented by the point cloud with an included angle less than a preset included angle threshold is the effective local monitoring area (target local monitoring area), and the set of effective local monitoring areas is the effective monitoring area. In this embodiment, the region with a large laser incidence angle is removed from the monitoring area by analyzing the laser incidence angle of the local area point cloud, which can effectively reduce the adverse effects caused by the laser angle incidence angle problem, thereby improving the monitoring accuracy and stability.

[0084] It should be noted that after the target local monitoring area corresponding to the initial point cloud model data is determined in step S103, the determination method further comprises:

[0085] I. determining an axial minimum bounding box of the initial point cloud model data based on the spatial position of each point cloud data in the initial point cloud model data;

[0086] II. performing voxel grid division on the axial minimum bounding box of the initial point cloud model data according to a preset voxel resolution to obtain a voxel grid model of the initial point cloud model data;

[0087] III. for each target local monitoring area corresponding to the initial point cloud model data, marking the voxel grid occupied by each point cloud data in the target local monitoring area in the voxel grid model of the initial point cloud model data based on the spatial position of each point cloud data in the target local monitoring area to obtain the spatial position marking of the target local monitoring area.

[0088] In this step, the axial minimum bounding box of the initial point cloud model data is calculated, the initial point cloud model data is subjected to voxel grid division according to the preset voxel resolution based on the axial minimum bounding box to obtain a voxel grid model of the initial point cloud model data, and the voxel grid occupied by each effective local monitoring area is marked according to the spatial position of the effective local monitoring area to obtain the spatial position marking of the effective local monitoring area. Here, the preset voxel resolution can be pre-set through historical experience or experimental data.

[0089] S104, for each target local monitoring area corresponding to the initial point cloud model data, obtain the point cloud data corresponding to the target local monitoring area in the current point cloud model data, and determine whether the difference between the average distance of the corresponding point cloud data in the current point cloud model data to the fitting plane corresponding to the target local monitoring area and the initial distance corresponding to the target local monitoring area is greater than a preset distance threshold value;

[0090] It should be noted that the step of obtaining the point cloud data corresponding to the target local monitoring area in the current point cloud model data comprises the following steps:

[0091] S1041, performing voxel grid division on the current point cloud model data based on the axial minimum bounding box of the initial point cloud model data and a preset voxel resolution, to obtain a voxel grid model of the current point cloud model data;

[0092] S1042, determining the current voxel grid corresponding to each spatial position mark in the voxel grid model of the current point cloud model data based on the spatial position mark of the target local monitoring area;

[0093] S1043, determining the point cloud data in the current voxel grid as the point cloud data corresponding to the target local monitoring area in the voxel grid model of the current point cloud model data.

[0094] In this step, the voxel grid model of the current point cloud model data is obtained by performing voxel grid division on the current point cloud model data based on the axial minimum bounding box of the initial point cloud model data and a preset voxel resolution; and the point cloud data of each effective local monitoring area is obtained in the voxel grid model of the current point cloud model data according to the spatial position mark of each effective local monitoring area.

[0095] It should be noted that the initial distance corresponding to the target local monitoring area is determined by the following steps:

[0096] 1) obtaining the distance from each point cloud data in the initial point cloud model corresponding to the target local monitoring area to the fitting plane corresponding to the target local monitoring area;

[0097] 2) determining the sum of the distances from each point cloud data in the initial point cloud model corresponding to the target local monitoring area to the fitting plane corresponding to the target local monitoring area as the target distance corresponding to the target local monitoring area;

[0098] 3) determining the quotient of the target distance and the number of point cloud data in the initial point cloud model corresponding to the target local monitoring area as the initial distance corresponding to the target local monitoring area.

[0099] In this step, the average distance of the point cloud data in the initial point cloud model data corresponding to each effective local monitoring area to the fitting plane thereof is calculated, that is, the initial distance corresponding to the effective local monitoring area.

[0100] S105, if yes, it is determined that the landslide body produces displacement in the target local monitoring area.

[0101] In this step, the average distance of the point cloud data in the initial point cloud model data corresponding to each effective local monitoring area to the fitting plane thereof is calculated, that is, the initial distance corresponding to the effective local monitoring area.

[0102] The embodiment of the present application provides a method for determining landslide body displacement, which comprises the following steps: obtaining current point cloud data obtained by scanning the monitoring area of the landslide body by a measuring device; preprocessing the current point cloud data to obtain current point cloud model data; obtaining initial point cloud model data obtained in advance; determining the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data; obtaining the point cloud data corresponding to each target local monitoring area of the initial point cloud model data in the current point cloud model data, and determining whether the difference between the average distance of the point cloud data corresponding to the target local monitoring area in the current point cloud model data to the fitting plane corresponding to the target local monitoring area and the initial distance corresponding to the target local monitoring area is greater than a preset distance threshold; if yes, it is determined that the landslide body produces displacement in the target local monitoring area.

[0103] In this way, the technical scheme provided by the present application can automatically extract the target local monitoring area by analyzing the attributes of the point cloud data, compare the point cloud models based on the automatically extracted target local monitoring area, analyze whether the landslide body produces displacement, replace the operation of manually setting multiple monitoring areas by the operator, reduce the operation complexity, and improve the convenience and efficiency of determining the landslide body displacement.

[0104] Based on the same application concept, the embodiment of the present application also provides a device for determining landslide body displacement corresponding to the method for determining landslide body displacement provided in the above embodiment. Since the principle of solving problems in the device of the present embodiment is similar to that of the method for determining landslide body displacement provided in the above embodiment of the present application, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0105] Please refer to Figure 3 , Figure 4 ,Figure 3 FIG. 1 is a structural diagram of a landslide body offset determination device provided by an embodiment of the present application, Figure 4 FIG. 2 is another structural diagram of a landslide body offset determination device provided by an embodiment of the present application. As shown in Figure 3 The determination device 310 comprises:

[0106] A first preprocessing module 312, configured to pre-process the current point cloud data to obtain current point cloud model data.

[0107] A processing module 313, configured to obtain initial point cloud model data obtained in advance, and determine a target local monitoring area corresponding to the initial point cloud model data based on attributes of each point cloud data in the initial point cloud model data.

[0108] A judging module 314, configured to, for each target local monitoring area corresponding to the initial point cloud model data, obtain point cloud data corresponding to the target local monitoring area in the current point cloud model data, and determine whether a difference between an average distance from the point cloud data corresponding to the target local monitoring area in the current point cloud model data to a fitting plane corresponding to the target local monitoring area and an initial distance corresponding to the target local monitoring area determined in advance is greater than a preset distance threshold.

[0109] A determining module 315, configured to determine that the landslide body has an offset in the target local monitoring area when the difference between the average distance from the point cloud data corresponding to the target local monitoring area in the current point cloud model data to the fitting plane corresponding to the target local monitoring area and the initial distance corresponding to the target local monitoring area determined in advance is greater than the preset distance threshold.

[0110] Optionally, when the processing module 313 is used to determine the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data, the processing module 313 is specifically configured to:

[0111] cluster each point cloud data in the initial point cloud model data based on curvatures and spatial positions of each point cloud data in the initial point cloud model data, to obtain a plurality of clustering areas of the initial point cloud model data;

[0112] fit a plane to the point cloud data in each clustering area to obtain a fitting plane corresponding to the clustering area, and determine a vector perpendicular to the fitting plane corresponding to the clustering area as a normal vector corresponding to the clustering area;

[0113] fit a plane to the point cloud data in each clustering area to obtain a fitting plane corresponding to the clustering area, and determine a vector perpendicular to the fitting plane corresponding to the clustering area as a normal vector corresponding to the clustering area;

[0114] acquire a centroid of the point cloud data in the clustering region, acquire a direction vector of the centroid of the point cloud data in the clustering region to a coordinate origin of the measuring device, and determine the target vector corresponding to the clustering region;

[0115] determine, based on the target vector corresponding to the clustering region, whether an included angle between the target vector corresponding to the clustering region and the normal vector corresponding to the clustering region is less than a preset included angle threshold;

[0116] if yes, determine the clustering region as a target local monitoring region corresponding to the initial point cloud model data.

[0117] Optionally, when the processing module 313 is used to cluster each point cloud data in the initial point cloud model data based on the curvature and the spatial position of each point cloud data in the initial point cloud model data, to obtain a plurality of clustering regions of the initial point cloud model data, the processing module 313 is specifically used to:

[0118] based on the curvature of each point cloud data in the initial point cloud model data, eliminate the point cloud data with a curvature greater than a preset curvature threshold, to obtain target point cloud data in the initial point cloud model data;

[0119] based on the spatial position of each point cloud data in the initial point cloud model data, cluster each target point cloud data in the initial point cloud model data, to obtain a plurality of clustering regions of the initial point cloud model data.

[0120] Optionally, as shown in Figure 4 the determining apparatus 310 further includes a predetermination module 316, which is used to:

[0121] acquire a distance from each point cloud data in an initial point cloud model corresponding to the target local monitoring region to a fitting plane corresponding to the target local monitoring region;

[0122] acquire a sum of the distances from each point cloud data in the initial point cloud model corresponding to the target local monitoring region to the fitting plane corresponding to the target local monitoring region, and determine the target distance corresponding to the target local monitoring region;

[0123] acquire a quotient of the target distance and a number of point cloud data in the initial point cloud model corresponding to the target local monitoring region, and determine the initial distance corresponding to the target local monitoring region.

[0124] Optionally, as shown in Figure 4 the determining apparatus 310 further includes a marking module 317, which is used to:

[0125] determine an axial minimum bounding box of the initial point cloud model data based on the spatial position of each point cloud data in the initial point cloud model data;

[0126] perform voxel grid division on the axial minimum bounding box of the initial point cloud model data according to a preset voxel resolution, to obtain a voxel grid model of the initial point cloud model data;

[0127] For each target local monitoring region corresponding to the initial point cloud model data, mark the voxel grid occupied by each point cloud data in the target local monitoring region in the voxel grid model of the initial point cloud model data based on the spatial position of each point cloud data in the target local monitoring region, to obtain the spatial position mark of the target local monitoring region.

[0128] Optionally, when the judging module 314 is used to obtain the point cloud data corresponding to the target local monitoring region in the current point cloud model data, the judging module 314 is specifically configured to:

[0129] perform voxel grid division on the current point cloud model data based on the axial minimum bounding box of the initial point cloud model data and the preset voxel resolution, to obtain a voxel grid model of the current point cloud model data;

[0130] determine the current voxel grid corresponding to each spatial position mark in the voxel grid model of the current point cloud model data based on the spatial position mark of the target local monitoring region;

[0131] determine the point cloud data in the current voxel grid as the point cloud data corresponding to the target local monitoring region in the voxel grid model of the current point cloud model data.

[0132] Optionally, as shown in Figure 4 the determining apparatus 310 further includes a second preprocessing module 318, which is configured to:

[0133] obtain initial point cloud data of a monitoring region of a landslide body;

[0134] perform preprocessing on the initial point cloud data to obtain initial point cloud model data; wherein the preprocessing includes at least one of the following: spatial clipping, point cloud down-sampling, outlier filtering, and moving least squares smoothing.

[0135] The embodiment of the present application provides a kind of landslide body to determine the device that offset is generated, the determining device includes: acquisition module, for obtaining the current point cloud data that measurement equipment scans to the monitoring area of landslide body;First pre-processing module, for the current point cloud data is pre-processed, obtains current point cloud model data;Processing module, for obtaining the initial point cloud model data obtained in advance, based on the attribute of each point cloud data in the initial point cloud model data, determine the target local monitoring area corresponding to the initial point cloud model data;Judgment module, for each target local monitoring area corresponding to the initial point cloud model data, obtain the point cloud data corresponding to this target local monitoring area in the current point cloud model data, and determine whether the difference between the average distance of the point cloud data corresponding in the current point cloud model data to the fitting plane corresponding to this target local monitoring area and the initial distance of the target local monitoring area corresponding to the initial distance determined in advance is greater than preset distance threshold;Determination module, for the average distance of the point cloud data corresponding in the current point cloud model data to the fitting plane corresponding to this target local monitoring area and the initial distance of the target local monitoring area corresponding to the initial distance determined in advance is greater than preset distance threshold, determine that the landslide body generates offset in this target local monitoring area.

[0136] In this way, by using the technical scheme provided by the present application, the target local monitoring area can be automatically extracted by analyzing the attributes of the point cloud data, the point cloud model comparison is carried out based on the automatically extracted target local monitoring area, and whether the landslide body generates offset is analyzed, which can replace the operation of manually setting multiple monitoring areas by the operator, reduces the operation complexity, and improves the convenience and efficiency of determining whether the landslide body generates offset.

[0137] Please refer to Figure 5 , Figure 5 The structure of the electronic device provided by the embodiment of the present application is shown in FIG. 5. Figure 5 As shown in FIG. 5, the electronic device 500 includes a processor 510, a memory 520 and a bus 530.

[0138] The memory 520 stores machine-readable instructions executable by the processor 510, and when the electronic device 500 is running, the processor 510 communicates with the memory 520 through the bus 530, and the machine-readable instructions are executed by the processor 510, which can execute the steps of the landslide body offset determination method in the method embodiment as shown in the above Figure 1 and Figure 2 The specific implementation can be referred to the method embodiment, which will not be described here.

[0139] The embodiment of the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is run by the processor, which can execute the landslide body offset determination method as shown in the aboveFigure 1 and Figure 2 The step of determining the offset of the landslide body in the method embodiment shown in the figure can be implemented in the manner described above with reference to the method embodiment, and will not be described here again.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described here again.

[0141] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0142] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0143] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0144] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0145] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present application, and are used to illustrate the technical solutions of the present application, but are not limitations thereof. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can make modifications or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features within the technical scope disclosed by the present application. The modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining the displacement of a landslide body, characterized in that, The determination method includes: Acquire current point cloud data obtained by scanning the monitoring area of ​​the landslide body using measuring equipment; The current point cloud data is preprocessed to obtain the current point cloud model data; Acquire pre-obtained initial point cloud model data, and determine the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data; For each target local monitoring region corresponding to the initial point cloud model data, the point cloud data corresponding to the target local monitoring region in the current point cloud model data is obtained, and it is determined whether the difference between the average distance from the point cloud data corresponding to the current point cloud model data to the fitting plane corresponding to the target local monitoring region and the predetermined initial distance corresponding to the target local monitoring region is greater than a preset distance threshold. If so, it is determined that the landslide body has shifted within the local monitoring area of ​​the target; The step of determining the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data includes: Based on the curvature of each point cloud data in the initial point cloud model data, point cloud data with curvature greater than a preset curvature threshold are removed to obtain the target point cloud data in the initial point cloud model data. Based on the spatial location of each point cloud data in the initial point cloud model data, each target point cloud data in the initial point cloud model data is clustered to obtain multiple clustering regions of the initial point cloud model data. For each cluster region, a plane fit is performed on the point cloud data in the cluster region to obtain the fitting plane corresponding to the cluster region, and the vector perpendicular to the fitting plane corresponding to the cluster region is determined as the normal vector corresponding to the cluster region. Obtain the centroid of the point cloud data in the cluster region, and determine the direction vector from the centroid of the point cloud data in the cluster region to the origin of the coordinate system of the measuring device as the target vector corresponding to the cluster region. Based on the target vector corresponding to the cluster region, determine whether the angle between the target vector corresponding to the cluster region and the normal vector corresponding to the cluster region is less than a preset angle threshold. If so, the clustered region is determined as the target local monitoring region corresponding to the initial point cloud model data; The initial distance corresponding to the local monitoring area of ​​the target is determined by the following steps: Obtain the distance from each point cloud data in the initial point cloud model corresponding to the local monitoring area of ​​the target to the fitting plane corresponding to the local monitoring area of ​​the target; The sum of the distances from each point cloud data in the initial point cloud model corresponding to the local monitoring area of ​​the target to the fitted plane corresponding to the local monitoring area of ​​the target is determined as the target distance corresponding to the local monitoring area of ​​the target. The quotient of the target distance and the number of point cloud data in the initial point cloud model corresponding to the local monitoring area of ​​the target is determined as the initial distance corresponding to the local monitoring area of ​​the target.

2. The determination method according to claim 1, characterized in that, After determining the target local monitoring area corresponding to the initial point cloud model data, the determination method further includes: Based on the spatial location of each point cloud data in the initial point cloud model data, determine the minimum bounding box of the initial point cloud model data along the axis. The axial minimum bounding box of the initial point cloud model data is divided into voxel meshes according to a preset voxel resolution to obtain the voxel mesh model of the initial point cloud model data. For each target local monitoring area corresponding to the initial point cloud model data, based on the spatial location of each point cloud data in the target local monitoring area, the voxel grid occupied by each point cloud data in the target local monitoring area in the voxel grid model of the initial point cloud model data is marked to obtain the spatial location mark of the target local monitoring area.

3. The determination method according to claim 2, characterized in that, The steps to obtain the point cloud data corresponding to the target local monitoring area in the current point cloud model data include: Based on the axial minimum bounding box of the initial point cloud model data and the preset voxel resolution, the current point cloud model data is divided into voxel meshes to obtain the voxel mesh model of the current point cloud model data. Based on the spatial location markers of the local monitoring area of ​​the target, the current voxel grid corresponding to each spatial location marker in the voxel grid model of the current point cloud model data is determined; The point cloud data in the current voxel grid is determined as the point cloud data corresponding to the local monitoring area of ​​the target in the voxel grid model of the current point cloud model data.

4. The determination method according to claim 1, characterized in that, The initial point cloud model data is obtained through the following steps: Acquire initial point cloud data of the monitoring area of ​​the landslide; The initial point cloud data is preprocessed to obtain initial point cloud model data; wherein the preprocessing includes at least one of the following: spatial clipping, point cloud downsampling, outlier filtering, and moving least squares smoothing.

5. A device for determining the displacement of a landslide body, characterized in that, The determining device includes: The acquisition module is used to acquire the current point cloud data obtained by the measuring equipment scanning the monitoring area of ​​the landslide body; The first preprocessing module is used to preprocess the current point cloud data to obtain the current point cloud model data; The processing module is used to acquire pre-obtained initial point cloud model data and determine the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data. The judgment module is used to obtain the point cloud data corresponding to the target local monitoring area in the current point cloud model data for each target local monitoring area corresponding to the initial point cloud model data, and to determine whether the difference between the average distance of the point cloud data corresponding to the current point cloud model data to the fitting plane corresponding to the target local monitoring area and the predetermined initial distance corresponding to the target local monitoring area is greater than a preset distance threshold. The determination module is used to determine that the landslide body has shifted within the target local monitoring area when the difference between the average distance from the corresponding point cloud data in the current point cloud model data to the fitting plane corresponding to the target local monitoring area and the predetermined initial distance corresponding to the target local monitoring area is greater than a preset distance threshold. When the processing module determines the target local monitoring area corresponding to the initial point cloud model data based on the attributes of each point cloud data in the initial point cloud model data, the processing module is specifically used for: Based on the curvature of each point cloud data in the initial point cloud model data, point cloud data with curvature greater than a preset curvature threshold are removed to obtain the target point cloud data in the initial point cloud model data. Based on the spatial location of each point cloud data in the initial point cloud model data, each target point cloud data in the initial point cloud model data is clustered to obtain multiple clustering regions of the initial point cloud model data. Obtain the centroid of the point cloud data in the cluster region, and determine the direction vector from the centroid of the point cloud data in the cluster region to the origin of the coordinate system of the measuring device as the target vector corresponding to the cluster region. Based on the target vector corresponding to the cluster region, determine whether the angle between the target vector corresponding to the cluster region and the normal vector corresponding to the cluster region is less than a preset angle threshold. If so, the clustered region is determined as the target local monitoring region corresponding to the initial point cloud model data; The determining device further includes a pre-determining module, the pre-determining module being used for: Obtain the distance from each point cloud data in the initial point cloud model corresponding to the local monitoring area of ​​the target to the fitting plane corresponding to the local monitoring area of ​​the target; The sum of the distances from each point cloud data in the initial point cloud model corresponding to the local monitoring area of ​​the target to the fitted plane corresponding to the local monitoring area of ​​the target is determined as the target distance corresponding to the local monitoring area of ​​the target. The quotient of the target distance and the number of point cloud data in the initial point cloud model corresponding to the local monitoring area of ​​the target is determined as the initial distance corresponding to the local monitoring area of ​​the target.

6. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of the method for determining the displacement of a landslide body as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method for determining the displacement of a landslide body as described in any one of claims 1 to 4.

Images