|
TITLE: Activity Recognition From Wearable Sensors
PRESENTER: Dieter Fox, http://www.cs.washington.edu/homes/fox/, fox@cs.washington.edu
AFFILIATION:Department of Computer Science & Engineering, University of Washington, http://www.cs.washington.edu/
DATE: Friday 16th March 2007
TIME: 11:00:00
PLACE: CSE Seminar Room, Level 1, K17
ABSTRACT:
Knowledge of a person's location provides important context
information for many applications, ranging from services such as
location-enhanced emergency calling to personal guidance systems that
help cognitively impaired individuals move safely through their
community. Location information is also extremely helpful for
estimating a person's high-level activities. In this talk we show how
dynamic Bayesian networks and conditional random fields can be applied
to estimate the location and activity of a person using information
such as GPS readings or WiFi signal strength. The techniques track a
person on graph structures that represent a street map or a skeleton
of the free space in a building. We also show how to learn a user's
significant places and daily movements through the community. Our
models use multiple levels of abstraction so as to bridge the gap
between raw sensor measurements and high level information such as a
user's mode of transportation, her current goal, and her significant
places (e.g. home or work place). Finally, we will discuss recent
work on using a multi-sensor board so as to better estimate a person's
activities.
BIOGRAPHY OF SPEAKER:
Dieter Fox is Associate Professor and Director of the Robotics and
State Estimation Lab in the Computer Science & Engineering Department
at the University of Washington, Seattle. He obtained his Ph.D. from
the University of Bonn, Germany. Before joining UW, he spent two
years as a postdoctoral researcher at the CMU Robot Learning Lab. His
research focuses on probabilistic state estimation in robotics and
activity recognition. Along with his colleagues, he introduced
particle filters as a powerful tool for state estimation in
robotics. More recently, he showed how to use hierarchical dynamic
Bayesian networks and relational statistical learning techniques in
order to extract high-level activity information from raw sensor data.
Dr. Fox received various awards for his research, including an NSF
CAREER award and best paper awards at robotics (IROS-98, ICRA-00,
RoboCup-04) and Artificial Intelligence conferences (AAAI-98,
AAAI-04).
Seminar information is also available at
http://www.cse.unsw.edu.au/db/ai/seminars/list/index.html
Host:
Bernhard Hengst
Seminar Convenor:
Van Hai Ho
|
