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...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	PloS one Ročník 20; číslo 1; s. e0314086
Hlavní autori:	Wang, Lei, Huang, Ming, Yang, Zhenqing, Wu, Rui, Qiu, Dashi, Xiao, Xingxing, Li, Dong, Chen, Cai
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	San Francisco Public Library of Science 06.01.2025 Public Library of Science (PLoS)
Predmet:	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
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	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.
Bibliografia:	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