EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Point Cloud Registration Method Based on ROPNet

Yuan Li, Fang Yang, Wanning Zheng iD

Sensors · 15.01.2023 · 23 (2) · 993

DOI: 10.3390/s23020993 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.01.2023. Verfasst von Yuan Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: The Engineering Research Center of Metallurgical Automation and Measurement Technology, Wuhan University of Science and Technology, Wuhan 430081, Chi…. Hauptthemen laut MEDLINE: Data Analysis. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Stability Module trial-production Project of the State Grid Hubei Power Research Institute, Stability Module trial production Project of the State Grid Hubei Power Research Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Point cloud registration is a crucial preprocessing step for point cloud data analysis and applications. Nowadays, many deep-learning-based methods have been proposed to improve the registration quality. These methods always use the sum of two cross-entropy as a loss function to train the model, which may lead to mismatching in overlapping regions. In this paper, we designed a new loss function based on the cross-entropy and applied it to the ROPNet point cloud registration model. Meanwhile, we improved the ROPNet by adding the channel attention mechanism to make the network focus on both global and local important information, thus improving the registration performance and reducing the point cloud registration error. We tested our method on ModelNet40 dataset, and the experimental results demonstrate the effectiveness of our proposed method.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Data AnalysisEntropy

Stichwörter der Autor:innen

channel attention mechanismcross-entropy lossdeep learningpoint cloud registration

Autor:innen und Institutionen

  • The Engineering Research Center of Metallurgical Automation and Measurement Technology, Wuhan University of Science and Technology, Wuhan 430081, China.

ORCID-Profile: Wanning Zheng

Förderung

  • National Natural Science Foundation of China
  • Stability Module trial-production Project of the State Grid Hubei Power Research Institute
  • Stability Module trial production Project of the State Grid Hubei Power Research Institute

Zitieren

APA

Li, Y., Yang, F., & Zheng, W. (2023). A Novel Point Cloud Registration Method Based on ROPNet. Sensors, 23(2), 993. https://doi.org/10.3390/s23020993

Vancouver

Li Y, Yang F, Zheng W. A Novel Point Cloud Registration Method Based on ROPNet. Sensors. 2023;23(2):993. doi:10.3390/s23020993

BibTeX
@article{Li2023,
  author = {Li, Yuan and Yang, Fang and Zheng, Wanning},
  title = {A Novel Point Cloud Registration Method Based on ROPNet},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {2},
  pages = {993},
  doi = {10.3390/s23020993}
}
Kostenlos starten →