Multi-View Incremental Segmentation of 3-D Point Clouds for Mobile Robots

Mobile robots need to create high-definition three-dimensional (3-D) maps of the environment for applications such as remote surveillance and infrastructure mapping. Accurate semantic processing of the acquired 3-D point cloud is critical for allowing the robot to obtain a high-level understanding o...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters 2019-04, Vol.4 (2), p.1240-1246
Main Authors: Chen, Jingdao, Cho, Yong Kwon, Kira, Zsolt
Format: Article
Language:English
Subjects:
Accuracy
Ambient intelligence
Artificial neural networks
Decision making
Deep learning in robotics and automation
High definition
Labels
Lasers
Mapping
Mobile robots
object detection
Ray tracing
Robot kinematics
Robots
segmentation and categorization
semantic scene understanding
Semantic segmentation
Semantics
Three dimensional models
Three-dimensional displays
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mobile robots need to create high-definition three-dimensional (3-D) maps of the environment for applications such as remote surveillance and infrastructure mapping. Accurate semantic processing of the acquired 3-D point cloud is critical for allowing the robot to obtain a high-level understanding of the surrounding objects and perform context-aware decision making. Existing techniques for point cloud semantic segmentation are mostly applied on a single frame or offline basis, with no way to integrate the segmentation results over time. This letter proposes an online method for mobile robots to incrementally build a semantically rich 3-D point cloud of the environment. The proposed deep neural network, MCPNet, is trained to predict class labels and object instance labels for each point in the scanned point cloud in an incremental fashion. A multi-view context pooling (MCP) operator is used to combine point features obtained from multiple viewpoints to improve the classification accuracy. The proposed architecture was trained and evaluated on ray-traced scans derived from the Stanford 3-D Indoor Spaces dataset. Results show that the proposed approach led to 15% improvement in pointwise accuracy and 7% improvement in normalized mutual information compared to the next best online method, with only a 6% drop in accuracy compared to the PointNet-based offline approach.
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2019.2894915