GVU Technical Report Number:
GIT-GVU-99-11
Title:
Exploiting Human Actions and Object Context for Recognition Tasks
Authors:
Darnell J. Moore
Irfan A. Essa
Monson H. Hayes
Abstract:
Our goal is to exploit human motion and object context to perform action
recognition and object classification. Towards this end, we introduce a
framework for recognizing actions and objects by measuring image-,
object- and action-based information from video. Hidden Markov models are
combined with object context to classify hand actions, which are aggregated
by a Bayesian classifier to summarize activities. We also use Bayesian
methods to differentiate the class of unknown objects by evaluating
detected actions along with low-level, extracted object features. Our
approach is appropriate for locating and classifying objects under a variety
of conditions including full occlusion. We show experiments where both
familiar and previously unseen objects are recognized using action and
context information.
Keywords:
Computer vision, action recognition, gesture recognition, object recognition
You can access this technical report via:
PDF
Postscript
|
