Hand gesture recognition with 3D convolutional neural networks

TLDR

Touchless hand gesture recognition is increasingly important for automotive interfaces, yet robust classification across subjects and lighting remains challenging. The study proposes a 3D CNN algorithm for driver hand gesture recognition from challenging depth and intensity data. The method fuses multi‑scale spatial features and uses spatio‑temporal data augmentation to improve training and reduce overfitting. Our method achieves a correct classification rate of 77.5 % on the VIVA challenge dataset.

Abstract

Touchless hand gesture recognition systems are becoming important in automotive user interfaces as they improve safety and comfort. Various computer vision algorithms have employed color and depth cameras for hand gesture recognition, but robust classification of gestures from different subjects performed under widely varying lighting conditions is still challenging. We propose an algorithm for drivers' hand gesture recognition from challenging depth and intensity data using 3D convolutional neural networks. Our solution combines information from multiple spatial scales for the final prediction. It also employs spatio-temporal data augmentation for more effective training and to reduce potential overfitting. Our method achieves a correct classification rate of 77.5% on the VIVA challenge dataset.