LBNP: Learning features between neighboring points for point cloud classification

Inspired by classical works, when constructing local relationships in point clouds, there is always a geometric description of the central point and its neighboring points. However, the basic geometric representation of the central point and its neighborhood is insufficient. Drawing inspiration from...

Full description

Saved in:
Bibliographic Details
Published in:PloS one Vol. 20; no. 1; p. e0314086
Main Authors: Wang, Lei, Huang, Ming, Yang, Zhenqing, Wu, Rui, Qiu, Dashi, Xiao, Xingxing, Li, Dong, Chen, Cai
Format: Journal Article
Language:English
Published: San Francisco Public Library of Science 06.01.2025
Public Library of Science (PLoS)
Subjects:
Algorithms
Analysis
Biology and Life Sciences
Classification
Cloud classification
Computer and Information Sciences
Computer vision
Deep learning
Image processing
Learning
Machine vision
Methods
Neighborhoods
Neural networks
Physical Sciences
Research and Analysis Methods
Social Sciences
China
ISSN:1932-6203, 1932-6203
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Inspired by classical works, when constructing local relationships in point clouds, there is always a geometric description of the central point and its neighboring points. However, the basic geometric representation of the central point and its neighborhood is insufficient. Drawing inspiration from local binary pattern algorithms used in image processing, we propose a novel method for representing point cloud neighborhoods, which we call Point Cloud Local Auxiliary Block (PLAB). This module explores useful neighborhood features by learning the relationships between neighboring points, thereby enhancing the learning capability of the model. In addition, we propose a pure Transformer structure that takes into account both local and global features, called Dual Attention Layer (DAL), which enables the network to learn valuable global features as well as local features in the aggregated feature space. Experimental results show that our method performs well on both coarse- and fine-grained point cloud datasets. We will publish the code and all experimental training logs on GitHub.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Competing Interests: The authors have declared that no competing interests exist.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0314086