Landscape

IEEE Circuits and Systems Society Joint Chapter of the Vancouver/Victoria Sections

Recognizing Human Actions from Video Data

Speaker: Dr. Greg Mori

School of Computing Science
Simon Fraser University

Dates and Locations

Thursday, April 16, 2009, 2:30 pm to 3:30 pm

Room: ASB 9705

Simon Fraser University, Burnaby, BC, Canada

Refreshment will be served.

Please click here to play the WebEx Record

Abstract

The development of automatic methods for recognizing human actions is a challenging computer vision problem. Robust solutions to this problem would facilitate a variety of applications in automated surveillance, such as gathering statistics on pedestrian behaviour or improving safety in assisted living facilities. In this talk I will present work towards solving this problem. I will focus on methods that use motion cues for recognizing human actions. The first is an efficient method for learning motion cues that can discriminate between actions, using the AdaBoost algorithm. A second model uses the hidden Conditional Random Field (hCRF) to learn a representation for motion parts in conjunction with whole-body templates. Finally, I will describe a "bag-of-words" model for video sequences that can be used for detecting unusual combinations of actions.

This is joint work with Alireza Fathi and Yang Wang.

Biography of Dr. Greg Mori

Dr. Greg Mori was born in Vancouver and grew up in Richmond, BC. He received the Ph.D. degree in Computer Science from the University of California, Berkeley in 2004. He received an Hon. B.Sc. in Computer Science and Mathematics with High Distinction from the University of Toronto in 1999. He spent one year (1997-1998) as an intern at Advanced Telecommunications Research (ATR) in Kyoto, Japan. After graduating from Berkeley, he returned home to Vancouver and is currently an assistant professor in the School of Computing Science at Simon Fraser University.

Dr. Mori's research interests are in computer vision, and include object recognition, human activity recognition, human body pose estimation. The main thrust of his research has been
in exploring methods for analyzing images of people. Dr. Mori has done pioneering work in the use of "exemplar" methods for localizing human figures in still images. He has also developed techniques for incorporating image segmentation into the recognition of human figures, in particular to segment and recognize human limbs and torsos in still images. Dr. Mori has also developed methods for object recognition in cluttered scenes. He has applied those techniques to break the "CAPTCHA" word-recognition puzzles, work that was featured in the New York Times. Dr. Mori has served on the program committee of major computer vision conferences (CVPR, ECCV, ICCV), and was the program co-chair of the Canadian Conference on Computer and Robot Vision (CRV) in 2006 and 2007.

Dr. Mori received the Excellence in Undergraduate Teaching Award from the SFU Computing Science Student Society in 2006. Dr. Mori received the Canadian Image Processing and
Pattern Recognition Society (CIPPRS) Award for Research Excellence and Service in 2008.

Webcast for the talk

Please click here after 2:15pm on April 16, 2009 to join the WebEx-based webcast for the lecture. The password is "Shannon48".

Please click here for a quick guide for WebEx (written by Prof. Jim Cavers).

If we could not establish the webcast due to network problem, we will record the lecture offline using WebEx software and post it on the website later.

Contact

Please contact Dr. Jie Liang (Email: JieL at sfu dot ca) if you have any question.