Title:
Exploiting Human Actions and Object Context for Recognition Tasks

dc.contributor.author Moore, Darnell Janssen
dc.contributor.author Essa, Irfan
dc.contributor.author Hayes, Monson H.
dc.date.accessioned 2004-10-13T14:08:48Z
dc.date.available 2004-10-13T14:08:48Z
dc.date.issued 1999
dc.description.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. en
dc.format.extent 186617 bytes
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/3377
dc.language.iso en_US
dc.publisher Georgia Institute of Technology en
dc.relation.ispartofseries GVU Technical Report;GIT-GVU-99-11
dc.subject Computer vision en
dc.subject Action recognition en
dc.subject Gesture recognition en
dc.subject Object recognition en
dc.title Exploiting Human Actions and Object Context for Recognition Tasks en
dc.type Text
dc.type.genre Technical Report
dspace.entity.type Publication
local.contributor.author Essa, Irfan
local.contributor.corporatename GVU Center
local.relation.ispartofseries GVU Technical Report Series
relation.isAuthorOfPublication 84ae0044-6f5b-4733-8388-4f6427a0f817
relation.isOrgUnitOfPublication d5666874-cf8d-45f6-8017-3781c955500f
relation.isSeriesOfPublication a13d1649-8f8b-4a59-9dec-d602fa26bc32
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
99-11.pdf
Size:
182.24 KB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.86 KB
Format:
Item-specific license agreed upon to submission
Description: