To Advance People's Well-Being: Human health sensing, analysis, and applications

摘要

This talk presents research on estimating health status from facial video analysis, focusing on non-invasive approaches to support well-being. The talk introduces robust estimation methods from facial videos for health- and well-being related indicators and real-time systems capable of simultaneously estimating vital signs-including heart rate, respiration, blood oxygen level, blood pressure, and pulse variability. It also explains the feasibility of estimating states such as drowsiness and stress from facial videos. These techniques utilize widely available devices such as smartphones and PCs, enabling continuous and low-burden monitoring in daily life. By demonstrating the feasibility of vision-based health estimation across various contexts, this work highlights its potential for workplace well-being, preventive healthcare, and telemedicine applications. Ultimately, this research aims to develop solutions that leverage cutting-edge technology to promote well-being, contributing to a future where people can lead healthier and more fulfilling lives-both physically and mentally.