Vision-Based Localization Using a Central Catadioptric Vision System

We present an appearance-based localization algorithm for an indoor environment that is inspired by human’s localization and navigation capabilities. Our localization approach integrates the Monte-Carlo localization technique with an omnidirectional image matching algorithm. The approach yields robust localization outcome with reasonable accuracy even when operating in a large map with sparse reference images.

[1]  Emanuele Frontoni,et al.  Appearance-Based Robotics Robot Localization in Partially Explored Environments , 2006 .

[2]  Horst-Michael Groß,et al.  Omnivision-based probabilistic self-localization for a mobile shopping assistant continued , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[3]  Masayuki Inaba,et al.  Exploration and navigation in corridor environment based on Omni-View sequence , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[4]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Tom Duckett,et al.  Localization for Mobile Robots using Panoramic Vision, Local Features and Particle Filter , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[6]  Emanuele Menegatti,et al.  Image-based Monte Carlo localisation with omnidirectional images , 2004, Robotics Auton. Syst..

[7]  C. W. Lim,et al.  Omnidirectional Image Matching for Vision-Based Robot Localization , 2006, 2006 IEEE International Conference on Mechatronics.

[8]  Gregor Schöner,et al.  Self-calibration based on invariant view recognition: Dynamic approach to navigation , 1997, Robotics Auton. Syst..

[9]  Emanuele Frontoni,et al.  Appearance based robotics , 2006, IEEE Robotics & Automation Magazine.

[10]  Bernhard Schölkopf,et al.  Where did I take that snapshot? Scene-based homing by image matching , 1998, Biological Cybernetics.