An Efficient Encoding Voxel-Based Segmentation (EVBS) Algorithm Based on Fast Adjacent Voxel Search for Point Cloud Plane Segmentation

Ming Huang,Xianglei Liu,Pengcheng Wei

doi:10.3390/rs11232727

Abstract

Plane segmentation is a basic yet important process in light detection and ranging (LiDAR) point cloud processing. The traditional point cloud plane segmentation algorithm is typically affected by the number of point clouds and the noise data, which results in slow segmentation efficiency and poor segmentation effect. Hence, an efficient encoding voxel-based segmentation (EVBS) algorithm based on a fast adjacent voxel search is proposed in this study. First, a binary octree algorithm is proposed to construct the voxel as the segmentation object and code the voxel, which can compute voxel features quickly and accurately. Second, a voxel-based region growing algorithm is proposed to cluster the corresponding voxel to perform the initial point cloud segmentation, which can improve the rationality of seed selection. Finally, a refining point method is proposed to solve the problem of under-segmentation in unlabeled voxels by judging the relationship between the points and the segmented plane. Experimental results demonstrate that the proposed algorithm is better than the traditional algorithm in terms of computation time, extraction accuracy, and recall rate.

Highlights

With the development of three-dimensional (3D) laser scanning technology, it is simpler and more accurate to acquire point cloud data
According to the difference in segmentation objects, point cloud plane segmentation methods can be divided into two categories: point-based and voxel-based point cloud segmentation algorithms
B0e.4ca0use 2t9h5e.1residual value of vo0.x8e6ls at th0e.5p7 lane0.6ju9nctio4n9.3is large, our algorithm does not we presented a point cloud plane segmentation algorithm based on fast adjacent voxel search that aims to improve the efficiency and effect of point cloud plane segmentation

Summary

Introduction

With the development of three-dimensional (3D) laser scanning technology, it is simpler and more accurate to acquire point cloud data. A large number of 3D reconstruction applications have been developed in various fields using 3D laser scanning, such as cultural heritage protection, navigation and positioning, and urban planning [1,2,3]. For large-scale 3D scene reconstructions, complex objects can be reconstructed better by the segmentation and recognition of planar shapes [4,5,6]. Traditional plane segmentation algorithms are limited by the large amount of point cloud data and the search method of neighbor points, which result in slow computation efficiency. According to the difference in segmentation objects, point cloud plane segmentation methods can be divided into two categories: point-based and voxel-based point cloud segmentation algorithms

Methods

Findings

Discussion

Conclusion