Video-based hand gesture recognition via SPD manifold spatial representation and optical flow motion features
PLOS One · 14.05.2026 · 21 (5) · e0348122
DOI: 10.1371/journal.pone.0348122 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 14.05.2026. Verfasst von Zhonghai Bai und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Electrical Engineering and Computer Science, VSB - Technical University of Ostrava, Ostrava, Czech Republic. Hauptthemen laut MEDLINE: Gestures, Hand, Pattern Recognition, Automated, Video Recording. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union – HORIZON EUROPE research and innovation programme, Ministry of Education, Youth, and Sports, European Union.
Abstract (Originalsprache)
Hand gesture recognition plays an important role in human–computer interaction, yet accurately modeling both spatial structure and temporal motion patterns in video-based vision systems remains challenging. Many existing approaches focus on either spatial appearance or motion information, which can limit their ability to capture the full complexity of dynamic hand gestures evolving over time. In this work, we present a unified feature representation framework that combines spatial descriptors modeled on the Symmetric Positive Definite (SPD) manifold with temporal motion features extracted from gesture video sequences using grid-based optical flow histograms in Euclidean space. Spatial covariance descriptors are mapped from the SPD manifold to a Euclidean space through the Log-Euclidean metric, enabling effective feature fusion while preserving intrinsic geometric properties. The resulting representation captures complementary spatial and temporal information in a compact and interpretable form. We evaluate the proposed framework on two publicly available video-based benchmark datasets for dynamic hand gesture recognition, the Cambridge Hand Gesture dataset and the Northwestern University Hand Gesture dataset. Experimental results demonstrate that the combined representation consistently improves classification performance compared to using spatial or temporal features alone, achieving 99.31% accuracy on the Cambridge dataset and 97.23% on the Northwestern dataset. These findings indicate that integrating manifold-aware spatial features with motion-based temporal cues provides a practical and effective solution for robust dynamic hand gesture recognition.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Faculty of Electrical Engineering and Computer Science, VSB - Technical University of Ostrava, Ostrava, Czech Republic.
- Center for Advanced Technologies and Engineering, CATEN, Ostrava, Czech Republic.
- Centre for Artificial Intelligence Research and Optimisation, Torrens University Australia, Brisbane, Australia.
- University Research and Innovation Center, Obuda University, Budapest, Hungary.
- Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam.
- School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China.
ORCID-Profile: Zhonghai Bai, Václav Snášel, Bay Vo, Jeng-Shyang Pan, Lingping Kong
Förderung
- European Union – HORIZON EUROPE research and innovation programme
- Ministry of Education, Youth, and Sports
- European Union
Zitieren
APA
Bai, Z., Snášel, V., Mirjalili, S., Vo, B., Pan, J. S., Kong, L., & Grosan, C. (2026). Video-based hand gesture recognition via SPD manifold spatial representation and optical flow motion features. PLOS One, 21(5), e0348122. https://doi.org/10.1371/journal.pone.0348122
Vancouver
Bai Z, Snášel V, Mirjalili S, Vo B, Pan JS, Kong L, et al. Video-based hand gesture recognition via SPD manifold spatial representation and optical flow motion features. PLOS One. 2026;21(5):e0348122. doi:10.1371/journal.pone.0348122
BibTeX
@article{Bai2026,
author = {Bai, Zhonghai and Snášel, Václav and Mirjalili, Seyedali and Vo, Bay and Pan, Jeng-Shyang and Kong, Lingping and Grosan, Crina},
title = {Video-based hand gesture recognition via SPD manifold spatial representation and optical flow motion features},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {5},
pages = {e0348122},
doi = {10.1371/journal.pone.0348122}
}
EUVIMED