In-Home Cluttered Environment Gait Analysis using mm-Wave Radar

This paper presents a novel method for human gait analysis in cluttered in-home environments using mm-wave radar systems, leveraging novel signal processing and unsupervised machine learning to extract gait parameters accurately amidst obstacles, multipath, and ghosts. Our approach accurately identifies gait parameters such as stride length and walking speed while walking on a curvy path, outperforming traditional techniques. The findings highlight the potential of mm-wave radar for non-invasive, privacy-preserving gait monitoring, with significant implications for healthcare, elderly care, and ambient assisted living. This work advances human motion analysis technology and opens new avenues for in-home monitoring applications.