Thermal video-based hand gestures recognition using lightweight CNN
Journal of Ambient Intelligence and Humanized Computing · 2024-12 · 15 (12) · 3849-3860
DOI: 10.1007/s12652-024-04851-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Ambient Intelligence and Humanized Computing, online erschienen am 20.09.2024. Verfasst von Simen Birkeland und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Agder.
Abstract (Originalsprache)
Hand gesture recognition has gained a lot of attention in computer vision due to multiple applications. Further, most of the existing works utilized RGB data for hand gesture recognition. However, RGB cameras mainly depend on lighting, angles, and other factors including skin color which impacts the accuracy. Thus, we propose a methodology for video hand gesture recognition using thermal data in this work. Initially, we created a dataset of short video sequences captured from a thermal camera. Thereafter, a lightweight convolutional neural network model (CNN) is proposed for hand gesture recognition. Further, the performance of the proposed CNN model is evaluated on different sizes of the dataset consisting of 15, 10, and 5 frames per sequence. Results show that the proposed model achieves an accuracy of $$97\% \pm (0.05)$$ , $$96\% \pm (0.05)$$ , and $$87\% \pm (0.1)$$ on the dataset consisting of 15, 10, and 5 frames per sequence, respectively.
Förderung
- University of Agder
Zitieren
APA
Birkeland, S., Fjeldvik, L. J., Noori, N., Yeduri, S. R., & Cenkeramaddi, L. R. (2024). Thermal video-based hand gestures recognition using lightweight CNN. Journal of Ambient Intelligence and Humanized Computing, 15(12), 3849-3860. https://doi.org/10.1007/s12652-024-04851-6
Vancouver
Birkeland S, Fjeldvik LJ, Noori N, Yeduri SR, Cenkeramaddi LR. Thermal video-based hand gestures recognition using lightweight CNN. Journal of Ambient Intelligence and Humanized Computing. 2024;15(12):3849-3860. doi:10.1007/s12652-024-04851-6
BibTeX
@article{Birkeland2024,
author = {Birkeland, Simen and Fjeldvik, Lin Julie and Noori, Nadia and Yeduri, Sreenivasa Reddy and Cenkeramaddi, Linga Reddy},
title = {Thermal video-based hand gestures recognition using lightweight CNN},
journal = {Journal of Ambient Intelligence and Humanized Computing},
year = {2024},
volume = {15},
number = {12},
pages = {3849--3860},
doi = {10.1007/s12652-024-04851-6}
}
EUVIMED