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

03/31/2020
by   Jilin Mei, et al.
0

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

READ FULL TEXT

page 1

page 5

page 6

page 7

research
09/14/2021

Semantics-aware Multi-modal Domain Translation:From LiDAR Point Clouds to Panoramic Color Images

In this work, we present a simple yet effective framework to address th...
research
10/29/2021

False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation

We present a novel post-processing tool for semantic segmentation of LiD...
research
09/03/2018

Semantic Segmentation of 3D LiDAR Data in Dynamic Scene Using Semi-supervised Learning

This work studies the semantic segmentation of 3D LiDAR data in dynamic ...
research
06/12/2019

VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view

This paper introduces VolMap, a real-time approach for the semantic segm...
research
08/13/2020

LGNN: a Context-aware Line Segment Detector

We present a novel real-time line segment detection scheme called Line G...
research
09/19/2023

Change of Scenery: Unsupervised LiDAR Change Detection for Mobile Robots

This paper presents a fully unsupervised deep change detection approach ...
research
06/07/2022

TRAVEL: Traversable Ground and Above-Ground Object Segmentation Using Graph Representation of 3D LiDAR Scans

Perception of traversable regions and objects of interest from a 3D poin...

Please sign up or login with your details

Forgot password? Click here to reset