Air-Writing Segmentation using a single IMU-based system

This paper presents a novel and generic method to employ deep neural networks for segmenting in-air performed gestures to detect writing activity. We consider various factors such as temporal, geometric, and frequency constraints to define the parameters and fine-tune the deep-learning methods. The proposed method is benchmarked on air-gesture data from 50 participants, which included air-writing gestures followed and preceded by non-writing gestures. The reported results establish the potential of deep-learning methods to segment air-writing activity. The proposed novel approach provides a foundation to develop sophisticated systems for recognizing air gestures to enhance interaction in virtual and augmented reality environments.