Confidence-based cue integration for visual place recognition

A distinctive feature of intelligent systems is their capability to analyze their level of expertise for a given task; in other words, they know what they know. As a way towards this ambitious goal, this paper presents a recognition algorithm able to measure its own level of confidence and, in case of uncertainty, to seek for extra information so to increase its own knowledge and ultimately achieve better performance. We focus on the visual place recognition problem for topological localization, and we take an SVM approach. We propose a new method for measuring the confidence level of the classification output, based on the distance of a test image and the average distance of training vectors. This method is combined with a discriminative accumulation scheme for cue integration. We show with extensive experiments that the resulting algorithm achieves better performances for two visual cues than the classic single cue SVM on the same task, while minimising the computational load. More important, our method provides a reliable measure of the level of confidence of the decision.

[1]  Barbara Caputo,et al.  Visual Servoing to Help Camera Operators Track Better , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Nikos Karampatziakis,et al.  Probabilistic Outputs for SVMs and Comparisons to Regularized Likelihood Methods , 2007 .

[3]  Illah R. Nourbakhsh,et al.  Appearance-based place recognition for topological localization , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[4]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[5]  James J. Little,et al.  Vision-based mobile robot localization and mapping using scale-invariant features , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[6]  Padraig Cunningham,et al.  Generating Estimates of Classification Confidence for a Case-Based Spam Filter , 2005, ICCBR.

[7]  Vapnik,et al.  SVMs for Histogram Based Image Classification , 1999 .

[8]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[9]  C. Schmid,et al.  Indexing based on scale invariant interest points , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[10]  David Kortenkamp,et al.  Topological Mapping for Mobile Robots Using a Combination of Sonar and Vision Sensing , 1994, AAAI.

[11]  John Y. Aloimonos,et al.  Unification and integration of visual modules: an extension of the Marr Paradigm , 1989 .

[12]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[13]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[14]  Tony Lindeberg,et al.  Object recognition using composed receptive field histograms of higher dimensionality , 2004, ICPR 2004.

[15]  Roland Siegwart,et al.  Incremental robot mapping with fingerprints of places , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[17]  Seong-Whan Lee,et al.  Retrieval of the top N matches with support vector machines , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

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

[19]  Barbara Caputo,et al.  Recognition with local features: the kernel recipe , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.