AN EFFECTIVE ACTION RECOGNITION APPROACH USED IN PHYSICAL EXERCISE FOR COPD PATIENTS

Abstract

This study was conducted to evaluate the effect of computer vision-based respiratory rehabilitation. Chronic obstructive pulmonary disease (COPD) is one of the primary respiratory diseases worldwide. Recently, image-capturing devices are increasingly used for physical therapy during rehabilitation treatment. Among these technologies, Action recognition plays a critical role in physical exercise and rehabilitation evaluation. This study aimed to propose an action series of a respiratory training program consisting of six actions. A video camera was placed in front of the participants to record their movements. Then, a hybrid algorithm combined with a convolution neural network and long short-term memory models was employed for action recognition from a video recording. The results indicated that the model achieved a reliable classification level of 82.35% on six actions. This demonstrated the validity of the proposed approach for multi-category action recognition. It was effective for action evaluation without medical guidance under home-based rehabilitation. Furthermore, the model for weight estimation was light-weight, with no need to consider the processing time.