A cognitive vision system for action recognition in office environments

Bauckhage, Christian and Hanheide, Marc and Wrede, Sebastian and Sagerer, Gerhard (2004) A cognitive vision system for action recognition in office environments. In: 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004, 27 th June - 2 nd July, 2004, Washington DC.

Documents
Bauckhage2004-A_Cognitive_Vision_System_for_Action_Recognition_in_Office_Environments.pdf
[img]
[Download]
[img] PDF
Bauckhage2004-A_Cognitive_Vision_System_for_Action_Recognition_in_Office_Environments.pdf - Whole Document
Restricted to Repository staff only

426Kb

Official URL: http://dx.doi.org/10.1109/CVPR.2004.1315250

Abstract

The emerging cognitive vision paradigm is concerned
with vision systems that evaluate, gather and integrate con-
textual knowledge for visual analysis. In reasoning about
events and structures, cognitive vision systems should rely
on multiple computations in order to perform robustly even
in noisy domains. Action recognition in an unconstrained
office environment thus provides an excellent testbed for re-
search on cognitive computer vision. In this contribution,
we present a system that consists of several computational
modules for object and action recognition. It applies atten-
tion mechanisms, visual learning and contextual as well as
probabilistic reasoning to fuse individual results and verify
their consistency. Database technologies are used for infor-
mation storage and an XML based communication frame-
work integrates all modules into a consistent architecture.

Item Type:Conference or Workshop Item (Paper)
Additional Information:The emerging cognitive vision paradigm is concerned with vision systems that evaluate, gather and integrate con- textual knowledge for visual analysis. In reasoning about events and structures, cognitive vision systems should rely on multiple computations in order to perform robustly even in noisy domains. Action recognition in an unconstrained office environment thus provides an excellent testbed for re- search on cognitive computer vision. In this contribution, we present a system that consists of several computational modules for object and action recognition. It applies atten- tion mechanisms, visual learning and contextual as well as probabilistic reasoning to fuse individual results and verify their consistency. Database technologies are used for infor- mation storage and an XML based communication frame- work integrates all modules into a consistent architecture.
Keywords:Robotics, Human-robot interaction
Subjects:H Engineering > H670 Robotics and Cybernetics
Divisions:College of Science > School of Computer Science
ID Code:6946
Deposited By: Marc Hanheide
Deposited On:23 Nov 2012 19:04
Last Modified:13 Mar 2013 09:19

Repository Staff Only: item control page