Semantic Segmentation of Large-Scale Outdoor Point Clouds by Encoder–Decoder Shared MLPs with Multiple Losses

Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand the scene environment in various applications, such as geometry mapping, autonomous driving, and more. With an advantage of being a 3D metric space, 3D LiDAR point clouds, on the other hand, pose a cha...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Vol. 13; no. 16; p. 3121
Main Authors: Rim, Beanbonyka, Lee, Ahyoung, Hong, Min
Format: Journal Article
Language:English
Published: Basel MDPI AG 06.08.2021
Subjects:
3D LiDAR point clouds
Aggregates
Coders
data collection
Datasets
Deep learning
geometry
Image segmentation
Learning
Lidar
Methods
Metric space
Multilayers
Neighborhoods
Remote sensing
Semantic segmentation
Semantics
Three dimensional models
Tradeoffs
ISSN:2072-4292, 2072-4292
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand the scene environment in various applications, such as geometry mapping, autonomous driving, and more. With an advantage of being a 3D metric space, 3D LiDAR point clouds, on the other hand, pose a challenge for a deep learning approach, due to their unstructured, unorder, irregular, and large-scale characteristics. Therefore, this paper presents an encoder–decoder shared multi-layer perceptron (MLP) with multiple losses, to address an issue of this semantic segmentation. The challenge rises a trade-off between efficiency and effectiveness in performance. To balance this trade-off, we proposed common mechanisms, which is simple and yet effective, by defining a random point sampling layer, an attention-based pooling layer, and a summation of multiple losses integrated with the encoder–decoder shared MLPs method for the large-scale outdoor point clouds semantic segmentation. We conducted our experiments on the following two large-scale benchmark datasets: Toronto-3D and DALES dataset. Our experimental results achieved an overall accuracy (OA) and a mean intersection over union (mIoU) of both the Toronto-3D dataset, with 83.60% and 71.03%, and the DALES dataset, with 76.43% and 59.52%, respectively. Additionally, our proposed method performed a few numbers of parameters of the model, and faster than PointNet++ by about three times during inferencing.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2072-4292
2072-4292
DOI:10.3390/rs13163121