Non-Contact Abnormal Physiological Status Detection During Sport and Training

Abstract

In sport and training, it is necessary to continue monitoring the physiological parameters of athletes to ensure that they can maintain a high level of competitive state. The previous monitoring physiological status methods mainly are contactable by sensors that are worn on body. This paper adopts a non-contact physiological parameter monitoring method by using imaging photoplethysmography (iPPG). In order to eliminate the noises in iPPG signals, the correlation energy entropy threshold adaptive denoising and variance characterization sereies are introduced to resist the noises from external conditions. The noises are remove by a threshold which is estimated by noise energy entropy. The constructed signals after denoising are used to estimate physiological parameters, such as heart rate and respiratory rate. The experimental results demonstrate that it estimates the physiological parameters better by usng iPPG based physiological parameter monitoring method than previous methods.