A framework utilizing face tracking and Normalized Least Mean Square adaptive filtering substantially outperformed previous methods for remote heart rate measurement from face videos.
A novel framework using face tracking and adaptive filtering improves the accuracy of remote heart rate measurement from face videos under realistic conditions involving motion and illumination changes.
Heart rate is an important indicator of people's physiological state. Recently, several papers reported methods to measure heart rate remotely from face videos. Those methods work well on stationary subjects under well controlled conditions, but their performance significantly degrades if the videos are recorded under more challenging conditions, specifically when subjects' motions and illumination variations are involved. We propose a framework which utilizes face tracking and Normalized Least Mean Square adaptive filtering methods to counter their influences. We test our framework on a large difficult and public database MAHNOB-HCI and demonstrate that our method substantially outperforms all previous methods. We also use our method for long term heart rate monitoring in a game evaluation scenario and achieve promising results.
Li et al. (Sun,) conducted a other in Heart rate measurement. Face tracking and Normalized Least Mean Square adaptive filtering vs. Previous methods was evaluated on Heart rate measurement performance. A framework utilizing face tracking and Normalized Least Mean Square adaptive filtering substantially outperformed previous methods for remote heart rate measurement from face videos.