EUVIMEDEUVIMED entdecken
Crossref

PointGT: A Method for Point-Cloud Classification and Segmentation Based on Local Geometric Transformation

Huang Zhang, Changshuo Wang, Long Yu, Shengwei Tian, Xin Ning, Joel Rodrigues

IEEE Transactions on Multimedia · 2024 · 26 · 8052-8062

DOI: 10.1109/tmm.2024.3374580 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2024. Verfasst von Huang Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 66-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Tianshan Yingcai Peiyang 2023, National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, three-dimensional (3D) point-cloud analysis has been extensively utilized in the domain of machine vision, encompassing tasks include shape classification and segmentation. However the inherent disorder in point clouds poses a challenge in capturing relationships among points, particularly when dealing with mutilated and occluded data. To this end, We propose the Point Geometry Transformation (PointGT) method for 3D point-cloud classification and part segmentation, by exploring the underlying geometric structure in the local and global of points. Specifically, the efficacy of PointGT arises from the integration of a local abstraction (LA) module and an optimization strategy. The LA module is tailored to address the localized features inherent to point clouds. This module encapsulates the multidimensional attributes of local edge and inside points. The bi-directional cross-attention mechanism amalgamates these two constituents into the native channel with the primary objective of optimizing the exploitation of edge and inside delineations, thereby judiciously mitigating noise artifacts. Ultimately, the channel residual connections disseminate the post-downsampling point attributes, thereby inheriting the edge and inside delineations gleaned via post bi-directional attention. The effectiveness of the proposed method was verified through the validation of point-cloud classification and segmentation datasets. The empirical findings confirmed the efficacy of PointGT; accuracies of 93.2% and 87.8% were achieved for the ModelNet40 and ScanObjectNN datasets, respectively.

Förderung

  • Tianshan Yingcai Peiyang 2023
  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Brazilian National Council for Scientific and Technological Development - CNPq

Zitieren

APA

Zhang, H., Wang, C., Yu, L., Tian, S., Ning, X., & Rodrigues, J. (2024). PointGT: A Method for Point-Cloud Classification and Segmentation Based on Local Geometric Transformation. IEEE Transactions on Multimedia, 26, 8052-8062. https://doi.org/10.1109/tmm.2024.3374580

Vancouver

Zhang H, Wang C, Yu L, Tian S, Ning X, Rodrigues J. PointGT: A Method for Point-Cloud Classification and Segmentation Based on Local Geometric Transformation. IEEE Transactions on Multimedia. 2024;26:8052-8062. doi:10.1109/tmm.2024.3374580

BibTeX
@article{Zhang2024,
  author = {Zhang, Huang and Wang, Changshuo and Yu, Long and Tian, Shengwei and Ning, Xin and Rodrigues, Joel},
  title = {PointGT: A Method for Point-Cloud Classification and Segmentation Based on Local Geometric Transformation},
  journal = {IEEE Transactions on Multimedia},
  year = {2024},
  volume = {26},
  pages = {8052--8062},
  doi = {10.1109/tmm.2024.3374580}
}
Kostenlos starten →