This work investigates how Hidden Semi-Markov Model (HSMM) can be used to monitor and evaluate physical rehabilitation exercises by Kinect v2 to support medical personnel and patients during rehabilitation at home. Authors developed an exercises assessment method based on the extraction of motion features determined by clinicians. Five different rehabilitation exercises are modeled using a HSMM to provide an assessment score. The scores are compared with those obtained using the Dynamic Time Warping to discriminate which, between these two methods, best correlates doctors and physiotherapists' evaluation. Results show that HSMM can be used to evaluate exercise performances and give a feedback to physiotherapists and patients about exercise execution. © 2016 IEEE.
Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2
ROMEO, LUCA;
2016-01-01
Abstract
This work investigates how Hidden Semi-Markov Model (HSMM) can be used to monitor and evaluate physical rehabilitation exercises by Kinect v2 to support medical personnel and patients during rehabilitation at home. Authors developed an exercises assessment method based on the extraction of motion features determined by clinicians. Five different rehabilitation exercises are modeled using a HSMM to provide an assessment score. The scores are compared with those obtained using the Dynamic Time Warping to discriminate which, between these two methods, best correlates doctors and physiotherapists' evaluation. Results show that HSMM can be used to evaluate exercise performances and give a feedback to physiotherapists and patients about exercise execution. © 2016 IEEE.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
