| Popis: |
In recent years, with the improvement of photographic equipment and computer’s computational efficiency, there are many non-contact heartbeat detection technologies based on image had been proposed. However, their performances are suffering from the influences under complex environment such as illumination changes, non-frontal face, and so on. In this paper proposed a non-contact heart rate detection through pulse. It using regression tree to located the feature points of facial, and tracked its trajectory. Then, separate blind source by use FastICA, select the appropriate channel for frequency domain analysis, and calculate heart rate. Experimental results showed that the error of the proposed method is about \( \pm 4 \) beats/min. |
