Multi-Scale Geometric Feature Extraction and Global Transformer for Real-World Indoor Point Cloud Analysis

Yisheng Chen, Yu Xiao, Hui Wu, Chongcheng Chen and Ding Lin ()
Additional contact information
Yisheng Chen: The Academy of Digital China, Fuzhou University, Fuzhou 350108, China
Yu Xiao: The Academy of Digital China, Fuzhou University, Fuzhou 350108, China
Hui Wu: The Academy of Digital China, Fuzhou University, Fuzhou 350108, China
Chongcheng Chen: The Academy of Digital China, Fuzhou University, Fuzhou 350108, China
Ding Lin: The Academy of Digital China, Fuzhou University, Fuzhou 350108, China

Mathematics, 2024, vol. 12, issue 23, 1-21

Abstract: Indoor point clouds often present significant challenges due to the complexity and variety of structures and high object similarity. The local geometric structure helps the model learn the shape features of objects at the detail level, while the global context provides overall scene semantics and spatial relationship information between objects. To address these challenges, we propose a novel network architecture, PointMSGT, which includes a multi-scale geometric feature extraction (MSGFE) module and a global Transformer (GT) module. The MSGFE module consists of a geometric feature extraction (GFE) module and a multi-scale attention (MSA) module. The GFE module reconstructs triangles through each point’s two neighbors and extracts detailed local geometric relationships by the triangle’s centroid, normal vector, and plane constant. The MSA module extracts features through multi-scale convolutions and adaptively aggregates features, focusing on both local geometric details and global semantic information at different scale levels, enhancing the understanding of complex scenes. The global Transformer employs a self-attention mechanism to capture long-range dependencies across the entire point cloud. The proposed method demonstrates competitive performance in real-world indoor scenarios, with a mIoU of 68.6% in semantic segmentation on S3DIS and OA of 86.4% in classification on ScanObjectNN.

Keywords: point cloud analysis; geometric feature; multi-scale attention; transformer; real-world indoor scenario (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/23/3827/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/23/3827/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:23:p:3827-:d:1536112

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().