EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton

Kai Hu iD, Chaowen Shen iD, Tianyan Wang iD, Shuai Shen iD, Chengxue Cai iD, Huaming Huang iD, Min Xia iD

Sensors · 2023

DOI: 10.3390/s23249738 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Kai Hu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China. Hauptthemen laut MEDLINE: Algorithms, Extremities. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In action recognition, obtaining skeleton data from human poses is valuable. This process can help eliminate negative effects of environmental noise, including changes in background and lighting conditions. Although GCN can learn unique action features, it fails to fully utilize the prior knowledge of human body structure and the coordination relations between limbs. To address these issues, this paper proposes a Multi-level Topological Channel Attention Network algorithm: Firstly, the Multi-level Topology and Channel Attention Module incorporates prior knowledge of human body structure using a coarse-to-fine approach, effectively extracting action features. Secondly, the Coordination Module utilizes contralateral and ipsilateral coordinated movements in human kinematics. Lastly, the Multi-scale Global Spatio-temporal Attention Module captures spatiotemporal features of different granularities and incorporates a causal convolution block and masked temporal attention to prevent non-causal relationships. This method achieved accuracy rates of 91.9% (Xsub), 96.3% (Xview), 88.5% (Xsub), and 90.3% (Xset) on NTU-RGB+D 60 and NTU-RGB+D 120, respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsExtremitiesHumansKnowledgeLearningSkeleton

Stichwörter der Autor:innen

prior knowledgeskeleton action recognitiontemporal modeling

Autor:innen und Institutionen

  • School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China.
  • CICAEET, Nanjing University of Information Science and Technology, Nanjing 210044, China.
  • Department of Physical Education, Nanjing University of Information Science and Technology, Nanjing 210044, China.

ORCID-Profile: Kai Hu, Chaowen Shen, Tianyan Wang, Shuai Shen, Chengxue Cai, Huaming Huang, Min Xia

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Hu, K., Shen, C., Wang, T., Shen, S., Cai, C., Huang, H., & Xia, M. (2023). Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton. Sensors. https://doi.org/10.3390/s23249738

Vancouver

Hu K, Shen C, Wang T, Shen S, Cai C, Huang H, et al. Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton. Sensors. 2023. doi:10.3390/s23249738

BibTeX
@article{Hu2023,
  author = {Hu, Kai and Shen, Chaowen and Wang, Tianyan and Shen, Shuai and Cai, Chengxue and Huang, Huaming and Xia, Min},
  title = {Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23249738}
}
Kostenlos starten →