Remote Detection and Classification of Human Stress Using a Depth Sensing Technique

Stress plays an important role in our daily life. Long-term's psychological stress will lead to serious health as well as social problems, it is important to detect and monitor the psychological stress in its early stage. Most existing stress detection equipment are contact-type, such as wrist strap. However, in a real application, such as a working environment, a contact-free stress detection system will bring greater convenience. In this paper, we proposed a novel framework for detecting and classifying human stress based on respiratory signals measured remotely by using a Kinect sensor with a detection range of 3 meters. We test the framework on respiratory signals data set from 20 individuals under 3 different tasks (listen relax music, do exercise and do Stroop Color-word test), corresponding to relaxation, physical stress and psychological stress state. Experimental results suggest that the proposed method is a promising way for monitoring human stress and even discriminating psychological stress from the physical stress.