Show simple item record

dc.contributor.authorMoore, Darnell Janssen
dc.contributor.authorEssa, Irfan A.
dc.contributor.authorHayes, M. H. (Monson H.)
dc.date.accessioned2004-10-13T14:08:48Z
dc.date.available2004-10-13T14:08:48Z
dc.date.issued1999
dc.identifier.urihttp://hdl.handle.net/1853/3377
dc.description.abstractOur 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.en
dc.format.extent186617 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technologyen
dc.relation.ispartofseriesGVU Technical Report;GIT-GVU-99-11
dc.subjectComputer visionen
dc.subjectAction recognitionen
dc.subjectGesture recognitionen
dc.subjectObject recognitionen
dc.titleExploiting Human Actions and Object Context for Recognition Tasksen
dc.typeTechnical Reporten


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record