Cardiac pulse rate estimation from source video data

摘要

What is disclosed is a system and method for estimating cardiac pulse rate from a video of a subject being monitored for cardiac function. In one embodiment, batches of overlapping image frames are continuously received and processed by isolating regions of exposed skin. Pixels of the isolated regions are processed to obtain a time-series signal per region and a physiological signal is extracted from each region's time-series signals. The physiological signal is processed to obtain a cardiac pulse rate for each region. The cardiac pulse rate for each region is compared to a last good cardiac pulse rate from a previous batch to obtain a difference. If the difference exceeds a threshold, the cardiac pulse rate is discarded. Otherwise, it is retained. Once all the regions have been processed, the retained cardiac pulse rate with a minimum difference becomes the good cardiac pulse rate for comparison on a next iteration.

主权项

1. A method for continuous estimation of cardiac pulse rate from video of a subject being monitored for cardiac function in a non-contact, remote sensing environment, the method comprising:
repeatedly receiving batches of time-sequential image frames captured by at least one video imaging device of a subject being monitored for cardiac function; and processing successive batches of image frames, comprising: A) isolating, in said image frames, at least two regions of exposed skin of said subject where a signal corresponding to said subject's cardiac function was registered by at least one imaging channel of said video imaging device; B) for each of said isolated regions, performing:
(i) processing pixels of said isolated region to obtain a time-series signal for this region;(ii) extracting, from said time-series signals, a physiological signal corresponding to said subject's cardiac function;(iii) processing said physiological signal to obtain a cardiac pulse rate for this region;(iv) comparing said cardiac pulse rate for this region to a last good cardiac pulse rate for said subject determined by having processed a previous batch to obtain a difference therebetween, on a first iteration said comparison being performed using an initial cardiac pulse rate determined for said subject; and(v) in response to said difference exceeding a threshold level, discarding this region's cardiac pulse rate, otherwise retaining this region's cardiac pulse rate; and C) in response to having performed steps A and B, determining that a retained cardiac pulse rate with a minimum difference between a last good cardiac pulse rate for a previous batch to be a next good cardiac pulse rate for a current batch, said next good cardiac pulse rate being used for comparison purposes on a next iteration.