Files in this item



application/pdfECE499-Sp2014-wangLe.pdf (851kB)Restricted to U of Illinois
(no description provided)PDF


Title:Heart Rate Detection from Face Videos Using Frequency Estimation
Author(s):Wang, Le
Contributor(s):Ahuja, Narendra
Subject(s):Signal Processing
Non-Contact Heart Rate Detection
Abstract:Heart rate is a critical vital sign of physical condition in medical diagnosis and chronic disease monitoring. There are emerging needs for non-contact, low-cost, long-term and accessible cardiac pulse estimation for health monitoring and emotion assessment. Studies confirmed resting heart rate as an independent predictor of cardiovascular mortality and suggested the potential role of heart rate in future cardiovascular guidance. Moreover, both theoretical and empirical rationale support that heart rate viability helps with understanding of emotion in social and psychopathological processes. In our research, we explore a robust video-based contact-free heart rate measurement by exploring the relationship between cardiac pulse and video signals on the face. We analyze the small color variation and motion signals in the face video as a scaled and shifted version of the cardiac pulse. We empirically validate this scaled and shifted relation by a cross-correlation analysis among regions of a face. In light of the analysis, we present a spatio-temporal method to detect the heart rate from the observed video signals. Based on the frequency spectrum from the 2D spatio-temporal analysis, we estimate the cardiac pulse frequency range and use peak detection in the reconstructed wave to measure heart rate. Our method is promising on synthesized signals, and future work is required to validate the proposed method so that it could be robust to various challenging video conditions.
Issue Date:2014-05
Date Available in IDEALS:2014-10-24

This item appears in the following Collection(s)

Item Statistics