Proceedings of the Seventh IEEE International Conference on Computer Vision (1999)
Sept. 20, 1999 to Sept. 25, 1999
Darnell J. Moore , Georgia Institute of Technology
Irfan A. Essa , Georgia Institute of Technology
Monson H. Hayes Iii , Georgia Institute of Technology
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.
D. J. Moore, I. A. Essa and M. H. Iii, "Exploiting Human Actions and Object Context for Recognition Tasks," Proceedings of the Seventh IEEE International Conference on Computer Vision(ICCV), Corfu, Greece, 1999, pp. 80.