Heart rate estimation based on camera image

Abstract

The remote measurement of the heart rate while the user is watching TV can bring many promising applications to our home such as user's preference estimation, automatic digest edition and fitness. We developed a non-contact heart rate measurement method using camera image so that users can measure the heart rate without any attachments. We focused attention on the blood oxygenated hemoglobin which absorbs the green light and measures the heart rate by detecting the variation of the green color intensity of a person's face image. In previous research, it was not possible to measure the heart rate with precision when a person was in movement. In this proposed method, we can expect that it will be applied to various applications since we can accurately measure the heart rate even while moving the face. The results showed a performance of detection error smaller than 3 bpm for lightning conditions over 500 lux and distances up to 6.0 m.