JUNE 4, 2009--Visual behavior recognition is interesting to imaging researchers since it has compelling applications like automated surveillance , human-computer interaction, and medical diagnosis.
It involves assigning one of several behavior classes to a sequence of one or more images. Previous behavior recognition approaches used a sequential, two-phase approach that can cause recognition errors when the attribute extraction phase fails due to difficult imaging or other conditions. Rather than applying an ad hoc solution, researchers Laura Gui in the Signal Processing Laboratory at École Polytechnique Fédérale de Lausanne (Lausanne, Switzerland) and Nikos Paragios in the Laboratoire MAS at École Centrale de Paris (Chatenay-Malabry, France) propose a mathematical framework that joins feature extraction and actual identification.
This method improves attribute extraction due to the added knowledge from the ongoing recognition. That, in turn, results in better identification. Future work will focus on extending a current finger-spelling application to multi-user scenarios, applying the framework to other behavior recognition tasks, and extending it to handle more complex actions.
For more information, go to: http://spie.org/x35250.xml?ArticleID=x35250
-- Posted by Conard Holton, Vision Systems Design, www.vision-systems.com
