Authors: Renato Samperio; Huosheng Hu
Addresses: School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, UK. ' School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, UK
Abstract: The environment sensing through visual perception can be obtained by an efficient and reliable landmark modelling. This paper proposes a novel landmark modelling approach to the classification of both the predefined and novelty features in the robot environment. The approach integrates image descriptors for defined landmarks (natural and artificial) and novelty features being dynamically detected. It has been implemented in a quadruped walking robot that has a single camera in its head. Some experimental results are presented to demonstrate the feasibility and performance of the proposed landmark models.
Keywords: image processing; visual-based localisation; walking robots; landmark modelling; real-time systems; RoboCup; legged robots; robot vision.
International Journal of Computer Applications in Technology, 2011 Vol.41 No.3/4, pp.253 - 261
Available online: 25 Sep 2011 *Full-text access for editors Access for subscribers Purchase this article Comment on this article