MOMBAT: Heart Rate Monitoring from Face Video using Pulse Modeling and\n Bayesian Tracking Article Swipe
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2005.04618
A non-invasive yet inexpensive method for heart rate (HR) monitoring is of\ngreat importance in many real-world applications including healthcare,\npsychology understanding, affective computing and biometrics. Face videos are\ncurrently utilized for such HR monitoring, but unfortunately this can lead to\nerrors due to the noise introduced by facial expressions, out-of-plane\nmovements, camera parameters (like focus change) and environmental factors. We\nalleviate these issues by proposing a novel face video based HR monitoring\nmethod MOMBAT, that is, MOnitoring using Modeling and BAyesian Tracking. We\nutilize out-of-plane face movements to define a novel quality estimation\nmechanism. Subsequently, we introduce a Fourier basis based modeling to\nreconstruct the cardiovascular pulse signal at the locations containing the\npoor quality, that is, the locations affected by out-of-plane face movements.\nFurthermore, we design a Bayesian decision theory based HR tracking mechanism\nto rectify the spurious HR estimates. Experimental results reveal that our\nproposed method, MOMBAT outperforms state-of-the-art HR monitoring methods and\nperforms HR monitoring with an average absolute error of 1.329 beats per minute\nand the Pearson correlation between estimated and actual heart rate is 0.9746.\nMoreover, it demonstrates that HR monitoring is significantly\n
Related Topics To Compare & Contrast
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2005.04618
- https://arxiv.org/pdf/2005.04618
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4297200455