Embedded-Based Non-contact Heart Rate Detection System

The non-contact heart rate detection system avoids direct contact between the sensor and the skin, improving portability, comfort and real-time heart rate monitoring. This paper presents an embedded-based non-contact heart rate detection system, embedding the camera behind the mirror, so that the user can realize to look at the mirror and get their heart rate information at the same time. First, the face color video is acquired by the USB camera mounted on the Raspberry Pi, the face in the video is detected as well as the feature points are detected, and the region of interest of the face is obtained and intercepted based on the detected feature points. Then, using OpenCV-based image processing, the feature area is separated by RGB three-channel, and one group of components is used as a one-dimensional signal for data processing, and then the heart rate value with periodic changes is extracted by Fourier transform and band-pass filtering. The system finally realizes the measurement of heart rate value and the display of heart rate waveform.