Scientists at the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology, Cambridge, have developed a new algorithm that, they say, can accurately measure the heart rates of people shown in ordinary digital video by analyzing the tiny head movements that go along with the rush of blood from the heart’s contractions.

In tests, the algorithm gave pulse measurements that were consistently within a few beats per minute of those produced by electrocardiograms, the researchers revealed. It was also able to provide useful estimates of the time intervals between beats, a measurement that can be used to identify patients at risk for cardiac events.

One potential use for this technology would be as a video-based pulse-measurement system to monitor newborns or the elderly, whose sensitive skin could be damaged by frequent attachment and removal of EKG leads. In addition, they say that the technique could, in principle, measure the volume of blood pumped by the heart, used in diagnosing several types of heart disease.

The algorithm works by combining several techniques common in the field of computer vision. First, it uses standard face recognition to distinguish the subject’s head from the rest of the image. Then it randomly selects 500 to 1,000 distinct points, clustered around the subjects’ mouths and noses, whose movement it tracks from frame to frame. Next, it filters out any frame-to-frame movements whose temporal frequency falls outside the range of a normal heartbeat, roughly 30 to 300 cycles per minute, which eliminates movements that repeat at a lower frequency, such as those caused by regular breathing and gradual changes in posture.

Finally, using a technique called principal component analysis, the algorithm decomposes the resulting signal into several constituent signals, which represent aspects of the remaining movements that don’t appear to be correlated with each other. Of those signals, it selects the one that appears to be the most regular and that falls within the typical frequency band of the human pulse.

Source