EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human Motion Enhancement and Restoration via Unconstrained Human Structure Learning

Tianjia He, Tianyuan Yang, Shin'ichi Konomi iD

Sensors · 2024

DOI: 10.3390/s24103123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Tianjia He und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka 819-0395, Japan. Hauptthemen laut MEDLINE: Movement. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, JSPS KAKENHI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human motion capture technology, which leverages sensors to track the movement trajectories of key skeleton points, has been progressively transitioning from industrial applications to broader civilian applications in recent years. It finds extensive use in fields such as game development, digital human modeling, and sport science. However, the affordability of these sensors often compromises the accuracy of motion data. Low-cost motion capture methods often lead to errors in the captured motion data. We introduce a novel approach for human motion reconstruction and enhancement using spatio-temporal attention-based graph convolutional networks (ST-ATGCNs), which efficiently learn the human skeleton structure and the motion logic without requiring prior human kinematic knowledge. This method enables unsupervised motion data restoration and significantly reduces the costs associated with obtaining precise motion capture data. Our experiments, conducted on two extensive motion datasets and with real motion capture sensors such as the SONY (Tokyo, Japan) mocopi, demonstrate the method’s effectiveness in enhancing the quality of low-precision motion capture data. The experiments indicate the ST-ATGCN’s potential to improve both the accessibility and accuracy of motion capture technology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MovementHumansBiomechanical PhenomenaAlgorithmsNeural Networks, ComputerMotionImage Processing, Computer-Assisted

Stichwörter der Autor:innen

denoisinggraph convolutional networkshuman motion datamotion capturemotion enhancementself-attention

Autor:innen und Institutionen

  • Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka 819-0395, Japan.
  • Faculty of Arts and Science, Kyushu University, Fukuoka 819-0395, Japan.

ORCID-Profile: Shin'ichi Konomi

Förderung

  • Japan Society for the Promotion of Science
  • JSPS KAKENHI

Zitieren

APA

He, T., Yang, T., & Konomi, S. (2024). Human Motion Enhancement and Restoration via Unconstrained Human Structure Learning. Sensors. https://doi.org/10.3390/s24103123

Vancouver

He T, Yang T, Konomi S. Human Motion Enhancement and Restoration via Unconstrained Human Structure Learning. Sensors. 2024. doi:10.3390/s24103123

BibTeX
@article{He2024,
  author = {He, Tianjia and Yang, Tianyuan and Konomi, Shin'ichi},
  title = {Human Motion Enhancement and Restoration via Unconstrained Human Structure Learning},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24103123}
}
Kostenlos starten →