Documentos de Académico
Documentos de Profesional
Documentos de Cultura
CONTENTS
Introduction Design Study description and experimental setup Measurement methodology Advantages Conclusion and future scope Reference
INTRODUCTION
1. Digital medical devices promise to transform the detailed individual physiological data.
2. Access and control over their own physiological data, they can play a more active role in the management of their health.
3. This revolution must take place in our everyday lives, not just in the Doctors office or research lab. 4. However, current techniques for physiological monitoring typically require users to strap on bulky sensors, straps etc.. This discourages regular use because the sensors can be uncomfortable. 5. In this work, a new mirror interface for real-time, Contact-free measurements of heart rate without the need for External sensors have been proposed. 6. Users can have the experience of remote health Monitoring by simply looking into the medical mirror(cardio cam).
Ming-Zher Poh
Rosalind W. Picard
Daniel J. McDuff
Mirrors are part of our another daily life, but with the combination of technology , mirrors too can be taken to level, so we intelligent mirror that can analyze your heart rate.
EXPERIMENTAL SETUP
Built-in Webcam Laptop Finger BVP Sensor Subject
BVP sensor
Participants were seated at a distance of approx. 0.5m from webcam. Two videos each lasting 1 min for measuring heart rate at rest and at motion respectively.
Also recorded a video with multiple participants at a time.
The monitor and webcam are connected to a laptop running the analysis software in real-time.
Measurement Methodology
(a)The ROI is automatically detected using a face tracker. (b) the ROI is decomposed into RGB channels and spatially averaged to obtain (c) The raw RGB traces. ICA is applied on normal RGB traces to recover (d) three independent source signals .
(a) 30 s raw RGB traces and (b) their respective power spectra. (c) The independent components recovered using ICA along with the reference finger BVP signal (d) Their respective power spectra. (e) (Media 1) A single-frame excerpt from the webcam video recording with localized ROI (white box). (f) Evolution of the localized ROI over 1 min.
Bland-Altman plots demonstrating the agreement between 30s epoch heart rate measurements obtained from participants sitting at rest using finger BVP and (a) The raw green channel trace (black circles), (b) The proposed ICA method (red circles) The lines represent the mean and 95% limits of agreement
Recovery of the cardiac pulse from a webcam video recording of a moving participant. (a) 30 s raw RGB traces and (b) their respective power spectra. (c) The independent components recovered using ICA along with the reference finger BVP signal and (d) Their respective power spectra. (e) (Media 1) A single-frame excerpt from the webcam video recording with localized ROI (white box). (f) Evolution of the localized ROI over 1 min.
Bland-Altman plots demonstrating the agreement between 30s epoch heart rate measurements obtained from participants sitting at rest using finger BVP and (a) The raw green channel trace (black circles), (b) The proposed ICA method (red circles) The lines represent the mean and 95% limits of agreement
(a) (Media 3) A single-frame excerpt from the webcam video recording with the ROI for each participant highlighted (white boxes).
(b) Comparison between heart rate measurements obtained using the proposed methodology (colored lines) and a reference BVP sensor (black lines).
ADVANTAGES
Low cost compares to other equipments.
The Medical Mirror fits seamlessly into the ambient home environment, blending the data collection process into the course of daily routines when they use the mirror for shaving, brushing teeth, etc..
This is beneficial for babies or for people with sensitive skin or burn wounds. The mirror approach is great because the technology is hidden and you don't even have to think about checking yourself; it just does it in the background. And if we advance the technology to get even more vital signs, the potential for tele-medicine is huge.
Although this concept only addressed the recovery of the cardiac pulse rate, many other important physiological parameters such as respiratory rate, heart rate variability and arterial blood oxygen saturation can potentially be estimated using the proposed technique. Creating a real-time, multi parameter physiological measurement platform based on this technology will be the subject of future work.
REFERENCES
[1] POH, M.-Z., MCDUFF, D.J. AND PICARD, R.W. 2010. Non-contact, Automated Cardiac Pulse Measurements Using Video Imaging and Blind Source Separation. Optics Express, vol. 18, no. 10, 10762-10774. [2] S. Cook, M. Togni, M. C. Schaub, P. Wenaweser, and O. M. Hess, High heart rate: a cardiovascular risk factor? Eur. Heart J. 27(20), 23872393 (2006). [3] I. Pavlidis, J. Dowdall, N. Sun, C. Puri, J. Fei, and M. Garbey, Interacting with human physiology, Comput. Vis. Image Underst. 108(1-2), 150170 (2007). [4] M. Garbey, N. Sun, A. Merla, and I. Pavlidis, Contact-free measurement of cardiac pulse based on the analysis of thermal imagery, IEEE Trans. Biomed. Eng. 54(8), 14181426 (2007).
Any questions??