SVM-based Discriminative Accumulation Scheme for Place Recognition A. Pronobis, O. Martínez Mozos, and B. Caputo In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA08), Pasadena, CA, USA, May 2008. Back Abstract Top Integrating information coming from different sensors is a fundamental capability for autonomous robots. For complex tasks like topological localization, it would be desirable to use multiple cues, possibly from different modalities, so to achieve robust performance. This paper proposes a new method for integrating multiple cues. For each cue we train a large margin classifier which outputs a set of scores indicating the confidence of the decision. These scores are then used as input to a Support Vector Machine, that learns how to weight each cue, for each class, optimally during training. We call this algorithm SVM-based Discriminative Accumulation Scheme (SVM-DAS). We applied our method to the topological localization task, using vision and laser-based cues. Experimental results clearly show the value of our approach. Download Top • Paper: [PDF (762.87 kB)] • Presentation: [PDF (2.94 MB)] Bibtex Top @INPROCEEDINGS{pronobis08icra, author = {Pronobis, A. and Mart\'{i}nez Mozos, O. and Caputo, B.}, title = {{SVM}-based Discriminative Accumulation Scheme for Place Recognition}, booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA08)}, year = {2008}, address = {Pasadena, CA, USA}, month = {May}, url = {http://www.csc.kth.se/~pronobis/research/pronobis08icra/pronobis08icra.pdf} } Created by: Andrzej Pronobis Last modified: 20-09-2009 00:26