Scene Context Based Semantic Segmentation for 3D LiDAR Data in Dynamic Scene

We propose a graph neural network(GNN) based method to incorporate scene context for the semantic segmentation of 3D LiDAR data. The problem is defined as building a graph to represent the topology of a center segment with its neighborhoods, then inferring the segment label. The node of graph is gen...

Full description

Saved in:
Bibliographic Details
Main Authors Mei, Jilin, Zhao, Huijing
Format Journal Article
LanguageEnglish
Published 30.03.2020
Subjects
Computer Science - Robotics
Online AccessGet full text

Cover

More Information
Summary:We propose a graph neural network(GNN) based method to incorporate scene context for the semantic segmentation of 3D LiDAR data. The problem is defined as building a graph to represent the topology of a center segment with its neighborhoods, then inferring the segment label. The node of graph is generated from the segment on range image, which is suitable for both sparse and dense point cloud. Edge weights that evaluate the correlations of center node and its neighborhoods are automatically encoded by a neural network, therefore the number of neighbor nodes is no longer a sensitive parameter. A system consists of segment generation, graph building, edge weight estimation, node updating, and node prediction is designed. Quantitative evaluation on a dataset of dynamic scene shows that our method has better performance than unary CNN with 8% improvement, as well as normal GNN with 17% improvement.
DOI:10.48550/arxiv.2003.13926