A FAST NON-CONTACT VITAL SIGNS DETECTION METHOD BASED ON REGIONAL HIDDEN MARKOV MODEL IN A 77GHZ LFMCW RADAR SYSTEM

The technologies of vital signs detection have been proven of great use while it is still limited by several challenges. One of the major challenges in vital signs detection is strong interferences, such as multiple targets in continuous wave radar system and random body movement (RBM), which significantly degrade the accuracy of the measurement. In this paper, a 77GHz linear frequency modulated continuous-wave (LFMCW) radar system is investigated to mitigate multiple-targets interferences. Furthermore, a novel regional hidden Markov model (RHMM) is proposed to acquire accurate estimates of the respiration rate (RR) and heart rate (HR) by exploiting the underlying slow-variant characteristics of these vital signs in the RBM environment. Experiments demonstrate the error rates of the proposed method are less than 9% for RR and less than 3% for HR in the multi-targets RBM environment.