M.I.T. Media Laboratory Vision and Modeling Group Technical Report No. 197
Recognition of Space-Time Gestures using a Distributed Representation
Trevor J. Darrell and Alex P. Pentland
This paper presents a method for learning, tracking, and recognizing human
gestures using a view-based approach to model both object and behavior.
Object views are represented using sets of view models, rather than single
templates. Stereotypical space-time patterns, i.e. gestures, are then matched
to stored gesture patterns using dynamic time warping. Real-time performance
is achieved by using special-purpose correlation hardware and view prediction
to prune as much of the search space as possible. Both view models and view
predictions are learned from examples. We present results showing tracking
and recognition of human hand gestures at over 10Hz.
A Postscript
version of this report is available.