Activity Recognition and 3D Lower Limb Tracking with an Instrumented Walker

Pascal Poupart (University of Waterloo)

NICTA SEMINAR

DATE: 2011-03-02
TIME: 14:00:00 - 15:00:00
LOCATION: NICTA Seminar Room A (Ground Floor)
CONTACT: JavaScript must be enabled to display this email address.

ABSTRACT:
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, walking abilities and the context in which falls are more likely to happen. In the first part of this talk, I will describe feature extraction, supervised and unsupervised techniques for hidden Markov models (HMMs) and conditional random fields (CRFs) to recognize walker related activities. In the second part of this talk, I will describe a particle filtering approach that implicitly recovers depth information to estimate 3D poses of the lower limbs without doing explicit stereo matching. Finally, a comprehensive evaluation with control subjects and walker users from a retirement community will be presented.

This work is done in collaboration with a multidisciplinary research team at the University of Waterloo, the Toronto Rehabilitation Institute and UW-Schlegel Research Institute for Aging.

Reference:

Comparative Analysis of Probabilistic Models for Activity Recognition with an Instrumented Walker Farheen Omar, Mathieu Sinn, Jakub Truszkowski, Pascal Poupart, James Tung and Allan Caine Uncertainty in Artificial Intelligence (UAI), Catalina, CA, 2010 http://www.cs.uwaterloo.ca/~ppoupart/publications/behaviour-recognition-uai/UAI2010_0251.pdf
BIO:
Pascal Poupart received the Early Researcher Award, a competitive honor for top Ontario researchers, awarded by the Ontario Ministry of Research and Innovation in 2008. He was also a co-recipient of the Best Paper Award Runner Up at the 2008 Conference on Uncertainty in Artificial Intelligence (UAI) and the IAPR Best Paper Award at the 2007 International Conference on Computer Vision Systems (ICVS). He is a member of the editorial board of the Journal of Artificial Intelligence Research (JAIR) and the Journal of Machine Learning Research (JMLR). His research partners include Google, Intel, the Alzheimer's Association, the UW-Schlegel Research Institute for Aging, Sunnybrook Health Science Centre and the Toronto Rehabilitation Institute.