A fast visual search and recognition mechanism for real-time robotics applications

Authors:
Quoc Vong Do;Peter Lozo;Lakhmi Jain
Affiliations:
Knowledge-Based Intelligent Engineering Systems Center, University of South Australia, Mawson Lakes, S.A., Australia;Weapons Systems Division, Defence Science and Technology Organisation, Edinburgh;Knowledge-Based Intelligent Engineering Systems Center, University of South Australia, Mawson Lakes, S.A., Australia
Venue:
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Year:
2004

Citing 0
Cited 2

Real-time landmark modelling for visual-guided walking robots

International Journal of Computer Applications in Technology
A vision system for partially occluded landmark recognition

AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Robot navigation relies on a robust and real-time visual perception system to understand the surrounding environment This paper describes a fast visual landmark search and recognition mechanism for real-time robotics applications The mechanism models two stages of visual perception named preattentive and attentive stages The pre-attentive stage provides a global guided search by identifying regions of interest, which is followed by the attentive stage for landmark recognition The results show the mechanism validity and applicability to autonomous robot applications.