Airborne LIDAR three-dimensional plane detection method based on multi-valued voxel model

Abstract

The invention discloses an airborne LIDAR three-dimensional plane detection method based on a multi-valued voxel model. The method comprises the following steps: regularizing airborne LIDAR point cloud data into the multi-valued voxel model; then searching for a small-curvature voxel from multi-value voxel model DSM data as a seed by utilizing the smoothness characteristic of a plane, and markinga communication area which is in three-dimensional communication with the seed and is consistent with the normal vector direction as the plane; marking voxels, of which reflection intensity values meet statistical characteristics, in the non-DSM data of the multi-valued voxel model as planes, wherein the voxels are located in the buffer area range of the connected region; and finally, merging theplane communication regions, so that the possibility that a real plane is segmented into a plurality of plane communication regions due to non-uniform point cloud density and the like is avoided. According to the method, a multi-valued voxel model construction scheme of airborne LIDAR point cloud data and a plane detection scheme based on the multi-value voxel model construction scheme are provided, and development of airborne LIDAR point cloud data processing and application based on the multi-value voxel model theory is facilitated.

Description

technical field [0001] The invention belongs to the technical field of remote sensing data processing, and in particular relates to an airborne LIDAR three-dimensional plane detection method based on a multi-valued voxel model. Background technique [0002] Plane features contain rich structural and semantic information, and widely exist in actual scenes, such as building roofs, walls, asphalt pavements, and natural ground. Accurate detection of this feature is of great significance for practical applications such as scene recognition and 3D reconstruction. Airborne LiDAR (Light Detection And Ranging, LIDAR) can directly acquire high-density, high-precision 3D point cloud data of ground objects. This data can provide rich information for automatic detection of 3D planar structures. Classical 3D planar feature detection methods based on airborne LIDAR data can be divided into the following two categories: fitting-based methods and cluster growth-based methods. Among them, ...

AI Technical Summary

Problems solved by technology

It can be seen that the above methods all use the data structure form of discrete point cloud, and although the discrete point cloud contains the 3D information of the original LiDAR data, it does not clearly express the neighborhood and topology information between laser points, which leads to a problem based on point cloud. The design of the plane feature detection algorithm is difficult and the efficiency is low

Images