| A noninvasive and easy-operation measurement of the heart rate has great potentialin home healthcare. We present a simple and high running efficiency method formeasuring heart rate from a video. By only tracking one feature point which is selectedfrom a small ROI (Region of Interest) in the head area, we extract trajectories of thispoint in both X-axis and Y-axis. After a series of processes including signal filtering,interpolation, the data dimension reduction is used to obtain a periodic signal, and thenthe heart rate can be calculated. We evaluated on10subjects and compared to acommercial heart rate measuring instrument (YUYUE YE680B) and achieved highdegree of agreement. A running time comparison experiment to the previous proposedmotion-based method is carried out and the result shows that the time cost is greatlyreduced in our method. |