(Georgia Institute of Technology, 1999)
Moore, Darnell Janssen; Essa, Irfan; Hayes, Monson H.
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.
(Georgia Institute of Technology, 1998)
Moore, Darnell Janssen; Essa, Irfan; Hayes, Monson H.
In this paper, we propose a vision-based method for developing computer awareness of human activities. We present an object-oriented approach called ObjectSpaces that encapsulates context into scene objects. Objects provide clues about which human motions to anticipate, making them powerful tools for discriminating actions and activities. Our hierarchical process leverages both low- and high-level representations of motion to label human interaction with objects in the surroundings. The Hidden Markov Model and Bayesian relations are used to characterize and summarize activity.