Title:
Exploiting Human Actions and Object Context for Recognition Tasks
Exploiting Human Actions and Object Context for Recognition Tasks
Files
Author(s)
Moore, Darnell Janssen
Essa, Irfan
Hayes, Monson H.
Essa, Irfan
Hayes, Monson H.
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
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.
Sponsor
Date Issued
1999
Extent
186617 bytes
Resource Type
Text
Resource Subtype
Technical Report