Activity Recognition with an Instrumented Walker

Prof. Pascal Poupart

University of Waterloo


September 6, 2010 11:00 AM



Wheeled walkers are popular mobility aids used by older adults to improve balance control.  There is a need to automatically recognize the activities performed by walker users to better understand activity patterns, mobility issues and the context in which falls are more likely to happen.  In this talk I will describe supervised and unsupervised techniques based on hidden Markov models (HMMs) and conditional random fields (CRFs) to walker related activities.  A comprehensive evaluation with control subjects and walker users from a retirement community will be presented.

This page is maintained by Ji-seon Yoo (
Last update: September 9, 2010