From images via symbols to contexts: using augmented reality for interactive model acquisition

Wachsmuth, Sven and Hanheide, Marc and Wrede, Sebastian and Bauckhage, Christian (2005) From images via symbols to contexts: using augmented reality for interactive model acquisition. In: KI 2005 Workshop on Mixed-reality as a Challenge to Image Understanding and Artificial Intelligence, September 11 - 14, 2005, Koblenz, Germany.

Documents
Wachsmuth2005-From_Images_via_Symbols_to_Contexts_Using_Augmented_Reality_for_Interactive_Model_Acquisition.pdf
[img]
[Download]
[img]
Preview
PDF
Wachsmuth2005-From_Images_via_Symbols_to_Contexts_Using_Augmented_Reality_for_Interactive_Model_Acquisition.pdf - Whole Document

429kB

Full text URL: aiweb.techfak.uni-bielefeld.de/files/papers/Wachsm...

Abstract

Systems that perform in real environments need to bind the internal state to externally
perceived objects, events, or complete scenes. How to learn this correspondence has been a long
standing problem in computer vision as well as artificial intelligence. Augmented Reality provides
an interesting perspective on this problem because a human user can directly relate displayed
system results to real environments. In the following we present a system that is able to bootstrap
internal models from user-system interactions. Starting from pictorial representations it learns
symbolic object labels that provide the basis for storing observed episodes. In a second step, more
complex relational information is extracted from stored episodes that enables the system to react
on specific scene contexts.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Systems that perform in real environments need to bind the internal state to externally perceived objects, events, or complete scenes. How to learn this correspondence has been a long standing problem in computer vision as well as artificial intelligence. Augmented Reality provides an interesting perspective on this problem because a human user can directly relate displayed system results to real environments. In the following we present a system that is able to bootstrap internal models from user-system interactions. Starting from pictorial representations it learns symbolic object labels that provide the basis for storing observed episodes. In a second step, more complex relational information is extracted from stored episodes that enables the system to react on specific scene contexts.
Keywords:Robotics, Human-robot interaction
Subjects:H Engineering > H670 Robotics and Cybernetics
Divisions:College of Science > School of Computer Science
ID Code:6945
Deposited By: Marc Hanheide
Deposited On:30 Nov 2012 11:02
Last Modified:13 Mar 2013 09:19

Repository Staff Only: item control page