Paper Info
Title
Voxel-Based 3D Point Cloud Semantic Segmentation: Unsupervised Geometric and Relationship Featuring vs Deep Learning Methods
Abstract
Automation in point cloud data processing is central in knowledge discovery within decision-making systems. The definition of relevant features is often key for segmentation and classification, with automated workflows presenting the main challenges. In this paper, we propose a voxel-based feature engineering that better characterize point clusters and provide strong support to supervised or unsupervised classification. We provide different feature generalization levels to permit interoperable frameworks. First, we recommend a shape-based feature set (SF1) that only leverages the raw X, Y, Z attributes of any point cloud. Afterwards, we derive relationship and topology between voxel entities to obtain a three-dimensional (3D) structural connectivity feature set (SF2). Finally, we provide a knowledge-based decision tree to permit infrastructure-related classification. We study SF1/SF2 synergy on a new semantic segmentation framework for the constitution of a higher semantic representation of point clouds in relevant clusters. Finally, we benchmark the approach against novel and best-performing deep-learning methods while using the full S3DIS dataset. We highlight good performances, easy-integration, and high F-1-score (> 85%) for planar-dominant classes that are comparable to state-of-the-art deep learning.
Year
DOI
Venue
2019
10.3390/ijgi8050213
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
Keywords
Field
DocType
3D point cloud,voxel,feature extraction,semantic segmentation,classification,3D semantics,deep learning
Voxel,Data mining,Decision tree,Computer science,Segmentation,Feature extraction,Feature engineering,Knowledge extraction,Artificial intelligence,Deep learning,Point cloud
Journal
Volume
Issue
ISSN
8
5
2220-9964
Citations 
PageRank 
References 
0
0.34
0
Authors
2
Name
Order
Citations
PageRank
Florent Poux121.06
Roland Billen210916.51