Posture and Gesture Analysis Supporting Emotional Activity Recognition
Qimeng Li, Raffaele Gravina, Giancarlo Fortino · 2018
This paper proposes a method for the detection of emotion-relevant activities performed when seated and its corresponding system based on wrist-worn inertial sensors combined with a pressure detection smart cushion. In particular, aiming at providing an additional source of information in traditional emotion recognition systems, we focus on shame-, fear-, and joy-related activities. Experiments are conducted and the results of performance evaluation show the proposed method achieves high recognition accuracy with a set obtained by fusing time-and frequency-domain features extracted from the different available sensors.