Segmentation-based airborne LiDAR point cloud building extraction method

Abstract

The invention discloses a segmentation-based airborne LiDAR point cloud building extraction method. The method comprises the steps of: (1) loading airborne laser LiDAR point cloud data; (2) identifying noise points in the airborne laser LiDAR point cloud, and removing the noise points; (3) carrying out material distribution simulation filtering to separate ground points from non-ground points; (4)carrying out region growth segmentation on filtered non-ground point cloud; and (5) calculating the direction cosine of the local normal vector and normal vector of each cluster which is obtained after the segmentation, generating a histogram, separating building point cloud from non-building point cloud through the generated histogram, thereby realizing the accurate extraction of the building point cloud. The invention provides the simple and efficient histogram method for distinguishing buildings from non-buildings. According to the difference of the normal vector characteristics of a building roof and a vegetation surface, a PCL-based region growing algorithm is utilized to perform three-dimensional point cloud segmentation on the non-ground points; and the histogram method is used incombination to distinguish the buildings from the non-buildings, so that the building point cloud data are accurately extracted.

Description

technical field [0001] The invention belongs to the technical field of airborne laser LiDAR point cloud data information extraction, in particular to a segmentation-based airborne LiDAR point cloud building extraction method. Background technique [0002] During the operation of airborne lidar equipment, the laser scanning process is blind, that is, the laser pulse may hit the ground, or it may hit buildings, bridges, power lines, lighthouses, vehicles and other artificial features or vegetation. Therefore, the acquired airborne lidar point cloud data contains both ground points and object points. Point cloud classification is the basis for subsequent applications. At present, building extraction from airborne lidar point cloud is one of the key steps in airborne lidar point cloud classification, and it is also a research hotspot and difficulty. [0003] At present, building extraction methods can be roughly divided into two categories: one is to directly classify LiDAR da...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the technical problem that the above-mentioned existing building extraction method process is relatively complicated and needs to combine multiple parameters, the present invention provides a segmentation-based airborne LiDAR point cloud building extraction method, according to the normal vector characteristics of the building roof and vegetation surface Different, use the PCL-based region growing algorithm to segment the 3D point cloud of non-ground points, and combine the histogram method to distinguish buildings and non-buildings, so as to accurately extract the building point cloud data

Images