Method for segmenting different objects in three-dimensional scene

Abstract

The invention discloses a method for segmenting different objects in a three-dimensional scene. The method comprises the following steps of: establishing adjacency relations and a spatial searching mechanism of point cloud data to estimate a normal vector and a residual of each point for the outdoor scene three-dimensional point cloud data acquired by laser scanning; determining the point with the minimum residual as a seed point and performing plane clustering by using a plane consistency restrictive condition and a region growing strategy to form the state that the entire plane building is segmented from other objects in the three-dimensional scene; establishing locally connected search for a plane building region for the segmented entire building part, and clustering the points with connectivity in the same plane by using different seed point rules to realize the detailed segmentation of the plane of the building; and constructing distance label-based initial cluster blocks for the other segmented objects and establishing weighting control restriction for cluster merging to realize the optimal segmentation result of trees. Tests on a plurality of data sets show that the method can be used for effectively segmenting the trees and buildings in the three-dimensional scene.

Description

technical field [0001] The invention belongs to the interdisciplinary technical field of combining pattern recognition and scientific calculation visualization, and relates to a method for segmenting different objects in a three-dimensional scene. Background technique [0002] With the reduction of the cost of 3D laser scanners and the rapid development of laser scanning measurement technology in spatial information acquisition, it is possible to quickly obtain 3D point cloud data of complex outdoor scenes. When using laser scanning point cloud data of complex scenes for modeling, it is an important and basic operation to efficiently and quickly select a point cloud subset that can completely represent a scene object. However, the 3D point cloud data obtained by laser scanning technology has massive characteristics, and it is necessary to select and segment the shape features of the point cloud data. Due to the inherent incompleteness and noise of point cloud data, object-o...

AI Technical Summary

Problems solved by technology

This method can get the rough outline of simple buildings, but the information of the details cannot be obtained.

Chen Jie (Jie Chen, 2008) and other methods on building reconstruction involve the segmentation of the building, which is mainly based on the confidence rate (confidence rate) for clustering and segmentation of the plane part. This method deletes noise points while also Some key points will be deleted by mistake, and this method cannot be used for segmentation of other types of objects, nor can the details of each object be obtained

Images