Hand Gesture Recognition With Uncertainty Awareness via FMCW Radar Sensing and Deep Learning

Frequency-modulated continuous-wave (FMCW) radar is a promising device for hand gesture reconstruction in autonomous control systems. A few groundbreaking studies have achieved remarkable advancements in automated hand gesture recognition by combining FMCW radar systems with deep learning (DL) techniques. However, one limitation of these DL models is their inability to convey the uncertainty linked to the model’s predictions, which holds great significance in the context of autonomous control systems. This article introduces the solution to address the challenge by developing an uncertainty-aware deep convolutional neural network (CNN). The network uses a CNN model that incorporates advanced techniques including Monte Carlo dropout (MCD), deep ensemble learning (DEL), and spectral-normalized neural Gaussian process. Our novel network architecture aims to predict hand gestures efficiently while providing an estimation of the associated uncertainty in the model’s predictions. The proposed approach was evaluated on a dataset with ten gestures collected from ten volunteers. The model could predict gestures with an accuracy of over 99% which is superior and noise-resistant to the existing deterministic models. The dataset was available at https://github.com/thetuantrinh/Hand-Gesture-Recognition.git