RF Sensing for Continuous Monitoring of Human Activities for Home Consumer Applications

摘要

Radar for indoor monitoring is an emerging area of research and development, covering and supporting differenthealth and wellbeing applications of smart homes, assisted living, and medical diagnosis. We report on asuccessful RF sensing system for home monitoring applications. The system recognizes Activities of DailyLiving(ADL) and detects unique motion characteristics, using data processing and training algorithms. Wealso examine the challenges of continuously monitoring various human activities which can be categorized intotranslation motions (active mode) and in-place motions (resting mode). We use the range-map, offered by arange-Doppler radar, to obtain the transition time between these two categories, characterized by changingand constant range values, respectively. This is achieved using the Radon transform that identifies straightlines of different slopes in the range-map image. Over the in-place motion time intervals, where activities haveinsignificant or negligible range swath, power threshold of the radar return micro-Doppler signatures,which isemployed to define the time-spans of individual activities with insigni cant or negligible range swath. Findingboth the transition times and the time-spans of the di erent motions leads to improved classi cations, as itavoids decisions rendered over time windows covering mixed activities.