Development of real-time image sequence analysis for evaluating posture change and respiratory rate of a subject in bed

An image sequence analysis technique was developed to evaluate posture change and respiratory rate of a subject in bed without any physical contact. Although the image sequence analysis requires many calculations, the system can perform them in real time. The system consisted of a CCD video camera and a PC equipped with a high-speed image processor. To evaluate the system, we tested it on five subjects at a nursing home. The system evaluated 99.4% of the movements of subjects during the total monitoring time (about 61 hours). The waveform was flat when the subject was out of view of the video camera. The system has the possibility of evaluating not only posture changes and respiratory rate. but also sleeping patterns.

[1]  Hidetoshi Miike,et al.  Evaluation of Body Motion by Optical Flow Analysis , 1997 .

[2]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[3]  Daniel J Buysse,et al.  Sleep–Related Breathing Disorders in Adults: Recommendations for Syndrome Definition and Measurement Techniques in Clinical Research , 2000 .

[4]  B. Phillips,et al.  Monitoring sleep and breathing: methodology. Part I: Monitoring breathing. , 1998, Clinics in chest medicine.

[5]  B. Carlson,et al.  Evaluation of a non-invasive respiratory monitoring system for sleeping subjects , 1999, Physiological measurement.

[6]  C. Guilleminault,et al.  Sleep‐Wake Disorders in the Elderly: A Polysomnographic Analysis , 1981, Journal of the American Geriatrics Society.

[7]  T Togawa,et al.  Assessment of bed temperature monitoring for detecting body movement during sleep: comparison with simultaneous video image recording and actigraphy. , 1999, Medical engineering & physics.

[8]  Erkki Ikonen,et al.  Passive frequency and intensity stabilization of extended-cavity diode lasers , 1997 .

[9]  Hidetoshi Miike,et al.  Determining motion fields under non-uniform illumination , 1995, Pattern Recognit. Lett..

[10]  Hidetoshi Miike,et al.  Detection of motion fields under spatio-temporal non-uniform illumination , 1999, Image Vis. Comput..

[11]  Rajiv Mehrotra,et al.  A trajectory-based computational model for optical flow estimation , 1995, IEEE Trans. Robotics Autom..

[12]  Hidetoshi Miike,et al.  Detection of apparent skin motion using optical flow analysis: Blood pulsation signal obtained from optical flow sequence , 1997 .