Locating the Upper Body of Covered Humans in application to Diagnosis of Obstructive Sleep Apnea

Obstructive Sleep Apnea is increasingly seen as a common and important condition, contributing to sleep disturbance and consequential daytime sleepiness. According to recent research findings, the best predictors of morbidity in individual patients, as assessed by improvements with CPAP (continuous positive airway pressure therapy), are nocturnal oxygen saturation and movements during sleep. Although pulse oximetry is a well-established technique to analyze oxygen saturation, video monitoring and interpretation is less well developed both from a processing and analysis viewpoint. This is due to the relative computational complexity of video processing analysis, as well as application-related technical challenges, involving night vision, the body being obscured by cover, variation on human size and behavior and massive video and audio data. In this paper, we propose a novel approach to locate upper body parts of the covered human body. The locations of the upper body parts allow further analysis of covered body postures and human activity recognition in sleep. The experimental results show that the proposed model is promising to estimate the head and torso locations of the covered human body with various postures, body activities and filming environmental settings. http://www.iaeng.org/publication/WCE2007/WCE2007_pp662-667.pdf