Incorporating Human Domain Knowledge in 3-D LiDAR-Based Semantic Segmentation

This article studies semantic segmentation using 3D LiDAR data. Popular deep learning methods applied for this task require a large number of manual annotations to train the parameters. We propose a new method that makes full use of the advantages of traditional methods and deep learning methods via...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent vehicles 2020-06, Vol.5 (2), p.178-187
Main Authors: Mei, Jilin, Zhao, Huijing
Format: Article
Language:English
Subjects:
3D LiDAR data
Annotations
Deep learning
Domains
human domain knowledge
Image annotation
Image segmentation
Laser radar
Lidar
Machine learning
Manuals
Neural networks
Semantic segmentation
Semantics
Teaching methods
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:This article studies semantic segmentation using 3D LiDAR data. Popular deep learning methods applied for this task require a large number of manual annotations to train the parameters. We propose a new method that makes full use of the advantages of traditional methods and deep learning methods via incorporating human domain knowledge into the neural network model to reduce the demand for large numbers of manual annotations and improve the training efficiency. We first pretrain a model with autogenerated samples from a rule-based classifier so that human knowledge can be propagated into the network. Based on the pretrained model, only a small set of annotations is required for further fine-tuning. Quantitative experiments show that the pretrained model achieves better performance than random initialization in almost all cases; furthermore, our method can achieve similar performance with fewer manual annotations.
ISSN:2379-8858
2379-8904
DOI:10.1109/TIV.2019.2955851