Authors:
M. Zaheer Aziz
and
Bärbel Mertsching
Affiliation:
GET Lab, Universität Paderborn, Germany
Keyword(s):
Visual attention, Virtual reality simulator, 3D space, Spatial memory, Robotic vision.
Related
Ontology
Subjects/Areas/Topics:
Autonomous Agents
;
Informatics in Control, Automation and Robotics
;
Mobile Robots and Autonomous Systems
;
Robotics and Automation
;
Vehicle Control Applications
;
Virtual Environment, Virtual and Augmented Reality
;
Vision, Recognition and Reconstruction
Abstract:
This paper presents a conceptual framework to integrate a spatial memory, derived from a 3D simulator, with a visual attention model. The proposed system is inspired from brain research that explicitly accounts for the use of spatial memory structures in intelligent object recognition and navigation by humans in the three dimensional space. The experiments presented here extend the capability of visual attention modeling to work in 3D space by connecting it to simulated maneuvers in virtual reality. The introduction of this concept opens new directions for work to reach the goal of intelligent machine vision, especially by mobile vision systems.