Categories: Articles scientifiques

Voxel-Based 3D Point Cloud Semantic Segmentation: Unsupervised Geometric and Relationship Featuring

May 2019 – International Journal of Geo-Information
Project: The Smart Point Cloud
Lab: Geomatics Unit

Abstract and figures

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 presentingthe main challenges. In this paper, we propose a voxel-based feature engineering that better characterize point clusters andprovide 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 deriverelationship 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 semanticrepresentation of point clouds in relevant clusters.
Finally, we benchmark the approach against novel and best-performing deep-learning methods while using the full S3DISdataset. We highlight good performances, easy-integration, and high F1-score (>85%) for planar-dominant classes that are comparable to state-of-the-art deep learning.

Point Cloud and its extracted voxel structure, where each octree level represents the grid voxels, each subdivided in subsequent eight voxel children.

En savoir plus…

flyvast

Leave a Comment
Share
Published by
flyvast
Tags: 3DNuage de point
4 ans ago

Recent Posts

3D Point Cloud Semantic Modelling: Integrated Framework for Indoor Spaces and Furniture

September 2018 - Remote Sensing Project: The Smart Point CloudFlorent PouxRomain NeuvilleGilles-Antoine NysRoland Billen Global…

4 ans ago

Automatic Detection of Objects in 3D Point Clouds Based on Exclusively Semantic Guided Processes

October 2019 - International Journal of Geo-Information Project: Knowledge based Object Detection in Images and…

4 ans ago

SELF-LEARNING ONTOLOGY FOR INSTANCE SEGMENTATION OF 3D INDOOR POINT CLOUD

August 2020Florent PouxJean-Jacques Ponciano The classification process and naming conventions.(a) coloured point cloud;(b) segmentation result;(c)…

4 ans ago

MODEL FOR SEMANTICALLY RICH POINT CLOUD DATA

October 2017Project: The Smart Point CloudFlorent PouxRomain NeuvillePierre HallotRoland Billen Abstract and figures This paper…

4 ans ago

Connected Semantic Concepts as a Base for Optimal Recording and Computer-Based Modelling of Cultural

January 2019 Conference: Structural Analysis of Historical Constructions Project: Knowledge based Object Detection in Images…

4 ans ago