Multi-Cue Based Place Learning for Mobile Robot Navigation

Place recognition is important navigation ability for autonomous navigation of mobile robots. Visual cues extracted from images provide a way to represent and recognize visited places. In this article, a multi-cue based place learning algorithm is proposed. The algorithm has been evaluated on a localization image database containing different variations of scenes under different weather conditions taken by moving the robot-mounted camera in an indoor-environment. The results suggest that joining the features obtained from different cues provide better representation than using a single feature cue.

[1]  James M. Keller,et al.  Acquiring and maintaining abstract landmark chunks for cognitive robot navigation , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Barbara Caputo,et al.  COLD: The CoSy Localization Database , 2009, Int. J. Robotics Res..

[3]  Barbara Caputo,et al.  Cue integration through discriminative accumulation , 2004, CVPR 2004.

[4]  Heinz Hügli,et al.  A Visual Attention-Based Approach for Automatic Landmark Selection and Recognition , 2004, WAPCV.

[5]  Hugh F. Durrant-Whyte,et al.  A Bayesian approach for place recognition , 2012, Robotics Auton. Syst..

[6]  Irene Macaluso,et al.  Automatic place detection and localization in autonomous robotics , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Pete R. Jones,et al.  Development of Cue Integration in Human Navigation , 2008, Current Biology.

[8]  Barbara Caputo,et al.  Confidence-based cue integration for visual place recognition , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Young-Min Kim,et al.  Fast Scene Change Detection using Direct Feature Extraction from MPEG Compressed Videos , 2000, IEEE Trans. Multim..

[10]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..

[11]  H. Mittelstaedt,et al.  Homing by path integration in a mammal , 1980, Naturwissenschaften.

[12]  Tom Drummond,et al.  Fusing points and lines for high performance tracking , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Antti Oulasvirta,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[14]  Huei-Yung Lin,et al.  An extended-HCT semantic description for visual place recognition , 2011, Int. J. Robotics Res..

[15]  Joni-Kristian Kämäräinen,et al.  Simple Gabor feature space for invariant object recognition , 2004, Pattern Recognit. Lett..

[16]  John K. Tsotsos,et al.  Attention and Performance in Computational Vision , 2008 .

[17]  Andrzej Pronobis,et al.  Multi-cue Discriminative Place Recognition , 2009, CLEF.

[18]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[19]  Yiannis Aloimonos,et al.  Deformation and Viewpoint Invariant Color Histograms , 2006, BMVC.

[20]  Wai-Kiang Yeap,et al.  How Albot0 Finds Its Way Home: A Novel Approach to Cognitive Mapping Using Robots , 2011, Top. Cogn. Sci..

[21]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.