Non Contact Heart Rate Monitoring using Facial Video
T. Sasilatha1, Gnana Kousalya2, Gowtham Venkatesan3, Charan Ramesh4
1T. Sasilatha, Professor and Dean, Department of EEE AMET Deemed to be University Chennai, India.
2Gnana Kousalya, Professor and HOD, Department of Electronics and Communication EngineeringSt. Joseph’s Institute of TechnologyChennai, India.
3Gowtham Venkatesan, Electronics and Communication Engineering St. Joseph’s Institute of Technology Chennai, India.
4Charan Ramesh, Electronics and Communication Engineering, St. Joseph’s Institute of Technology, Chennai, India.
Manuscript received on November 22, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 4087-4089 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B4951129219/2019©BEIESP | DOI: 10.35940/ijeat.B4951.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Heart rate (HR) is a direct measure of heart’s function. Conventional measurement based on contact-based measurement may cause discomfort to patients, especially in the case of long-term monitoring. This paper proposes a non-contact method of measuring heart rate using facial video of the patient. The variation of light intensity from the skin from each heart beat is used to estimate HR. A standard RGB camera is used to record the video. The Region of Interest (ROI) is obtained using face detection and tracking algorithms. A mean is taken across the frame yielding three values per frame. The Photo Plethysmo Graphy(PPG) signal is isolated using Independent Component Analysis (ICA). The signals are further filtered to reduce out of band noise and improve accuracy. The Fast Fourier Transform (FFT) is used to convert the signal to frequency domain and the peak is identified, whose frequency will correspond to the HR. This method of measuring HR has several advantages over conventional methods. HR measurement during exercise, prisons where contact-based methods cannot be employed, and long-term HR measurement in hospitals are some applications where the proposed method will be highly advantageous. The method also reduces the amount of hardware needed for HR measurement; HR can be measured even using smartphones.
Keywords: Independent Component Analysis (ICA), Photo Plethysmo Graphy (PPG), Fast Fourier Transform (FFT).