This work proposes a novel approach for hand gesture recognition using an inexpensive, low-resolution (24×32) ) thermal sensor processed by a Spiking Neural Network (SNN) followed by Sparse Segmentation and feature-based gesture classification via Robust Principal Component Analysis (R-PCA). Compared to the use of standard RGB cameras, the proposed system is insensitive to lighting variations while being significantly less expensive compared to high-frequency radars, time-of-flight cameras and high-resolution thermal sensors previously used in literature. Crucially, this paper shows that the innovative use of the recently proposed Monostable Multivibrator (MMV) neural networks as a new class of SNN achieves more than one order of magnitude smaller memory and compute complexity compared to deep learning approaches, while reaching a top gesture recognition accuracy of 93.9% using a 5-class thermal camera dataset acquired in a car cabin, within an automotive context. Our dataset is released for helping future research.
Safa, A, Mommen, W, Keuninckx, L & Wambacq, P 2024, Resource-Efficient Gesture Recognition using Low-Resolution Thermal Camera via Spiking Neural Networks and Sparse Segmentation. in Resource-Efficient Gesture Recognition Using Low-Resolution Thermal Camera via Spiking Neural Networks and Sparse Segmentation. 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), IEEE, The 18th IEEE International Conference on Automatic Face and Gesture Recognition, Istanbul, Turkey, 27/05/24. https://doi.org/10.1109/FG59268.2024.10582024
Safa, A., Mommen, W., Keuninckx, L., & Wambacq, P. (2024). Resource-Efficient Gesture Recognition using Low-Resolution Thermal Camera via Spiking Neural Networks and Sparse Segmentation. In Resource-Efficient Gesture Recognition Using Low-Resolution Thermal Camera via Spiking Neural Networks and Sparse Segmentation (2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)). IEEE. https://doi.org/10.1109/FG59268.2024.10582024
@inproceedings{a1d6a22725984a52bbb74ba0e7130008,
title = "Resource-Efficient Gesture Recognition using Low-Resolution Thermal Camera via Spiking Neural Networks and Sparse Segmentation",
abstract = "This work proposes a novel approach for hand gesture recognition using an inexpensive, low-resolution (24×32) ) thermal sensor processed by a Spiking Neural Network (SNN) followed by Sparse Segmentation and feature-based gesture classification via Robust Principal Component Analysis (R-PCA). Compared to the use of standard RGB cameras, the proposed system is insensitive to lighting variations while being significantly less expensive compared to high-frequency radars, time-of-flight cameras and high-resolution thermal sensors previously used in literature. Crucially, this paper shows that the innovative use of the recently proposed Monostable Multivibrator (MMV) neural networks as a new class of SNN achieves more than one order of magnitude smaller memory and compute complexity compared to deep learning approaches, while reaching a top gesture recognition accuracy of 93.9% using a 5-class thermal camera dataset acquired in a car cabin, within an automotive context. Our dataset is released for helping future research.",
keywords = "Deep learning, Accuracy, Memory management, Gesture recognition, Spiking neural networks, Radar, Thermal sensors",
author = "Ali Safa and Wout Mommen and Lars Keuninckx and Piet Wambacq",
note = "Funding Information: This research received funding from the Flemish Government under the Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen pro- gramme. Publisher Copyright: {\textcopyright} 2024 IEEE.; The 18th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2024 ; Conference date: 27-05-2024 Through 31-05-2024",
year = "2024",
month = jul,
day = "11",
doi = "10.1109/FG59268.2024.10582024",
language = "English",
isbn = "979-8-3503-9495-5",
series = "2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)",
publisher = "IEEE",
booktitle = "Resource-Efficient Gesture Recognition Using Low-Resolution Thermal Camera via Spiking Neural Networks and Sparse Segmentation",
}