2018 Fiscal Year Annual Research Report

Real World Heart Rate Estimation from Video

Research Project

Project/Area Number	17K12709
Research Institution	Saitama University
Principal Investigator	Lam Antony 埼玉大学, 理工学研究科, 助教 (50744124)
Project Period (FY)	2017-04-01 – 2019-03-31
Keywords	video ppg / computer vision / heart rate / cardiac estimation / remote measurement
Outline of Annual Research Achievements	We have continued to build our own dataset and also refine our algorithm for improved robustness and accuracy. We developed some variants of the algorithm for different situations. For situations that require more processing speed, we developed a version of our algorithm that focuses on only key parts of the face with strong PPG signals (areas of the face with strong color changes due to cardiac activity). We also developed a version of the algorithm where time constraints did not matter for higher accuracy. We then explored applications of video PPG for emotion recognition and potential uses in HCI, HRI applications. In the case of emotion recognition, we modified the algorithm to output the full PPG signal and found that emotion recognition is possible.

(2 results)