Segmentation Algorithm of Three-Dimensional Point Cloud Data Based on Region Growing

Abstract

Segmentation algorithm of 3D point cloud data based on region growing is proposed, the main idea is as follows: First, seed points in each region of object surface are searched, and then, starts from the seed point, the process of regional growing is done, which all the point cloud data belong to same surface are included until some discontinuous set of points appear. The algorithm is implemented under C, and the 3D point cloud data are showed by OPENGL software.

A Review of Deep Learning-Based Semantic Segmentation for Point Cloud

“…The development of 3D data capturing devices, for instance, LiDAR and Microsoft Kinect, makes the acquisition of point cloud data become ever more convenient. Traditionally, point cloud segmentation algorithms mainly include: methods based on attribute clustering [9], [10], methods based on model fitting [11], [12], methods based on region growth [13]- [15], methods based on graph-cut [16]- [18] and methods based on edge [19]- [21]. However, those approaches adopt handcrafted features from geometric constraints and several are limited by the assumed prior knowledge.…”

A Research and Application of the Processing Methods of Railway Measurement Based on Self-Mobile Scanning Measurement System

“…It is necessary to segment the rail from the massive point cloud data at first. At present, the common point cloud segmentation methods include clustering segmentation, segmentation based on random sampling consistency and segmentation based on region growth [9][10][11]. This thesis proposed region growing segmentation based on the reflection intensity of point cloud, segmenting the rail according to the reflection characteristics, geometric dimensions and continuous characteristics of rail.…”