Human Gesture Recognition using CNNs for Human-Robot Interaction
Revista de Informática Teórica e Aplicada · 10.03.2026 · 33 (2) · 44-51
DOI: 10.22456/2175-2745.150950 ↗Kurz gefasst
Fachartikel in der Zeitschrift Revista de Informática Teórica e Aplicada, online erschienen am 10.03.2026. Verfasst von Werikson Frederiko de Oliveira Alves und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This paper proposes a deep learning approach for human gesture recognition to support real-time teleoperation of mobile robots in outdoor environments. A lightweight ResNet18 architecture is adapted via transfer learning, combining a personalized dataset captured with a RealSense camera and a reorganized subset of HMDB. A modular pipeline was developed and evaluated under nine experimental configurations, considering different optimizers, datasets, and backbone freezing levels. Results demonstrate that models trained with combined data and adaptive fine-tuning strategies achieve high accuracy and strong generalization under varied lighting and background conditions. The best configuration reached 97.9% test accuracy, reinforcing the potential of CNNs for robust gesture-based human–robot interaction.
Zitieren
APA
Alves, W. F. D. O., Silva, M. M. D., & Brandão, A. S. (2026). Human Gesture Recognition using CNNs for Human-Robot Interaction. Revista de Informática Teórica e Aplicada, 33(2), 44-51. https://doi.org/10.22456/2175-2745.150950
Vancouver
Alves WFDO, Silva MMD, Brandão AS. Human Gesture Recognition using CNNs for Human-Robot Interaction. Revista de Informática Teórica e Aplicada. 2026;33(2):44-51. doi:10.22456/2175-2745.150950
BibTeX
@article{Alves2026,
author = {Alves, Werikson Frederiko de Oliveira and Silva, Michel Melo da and Brandão, Alexandre Santos},
title = {Human Gesture Recognition using CNNs for Human-Robot Interaction},
journal = {Revista de Informática Teórica e Aplicada},
year = {2026},
volume = {33},
number = {2},
pages = {44--51},
doi = {10.22456/2175-2745.150950}
}
EUVIMED