Confidence-based cue integration for visual place recognition
2007 (English)In: 2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9, NEW YORK: IEEE , 2007, 2400-2407 p.Conference paper (Refereed)
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.
Place, publisher, year, edition, pages
NEW YORK: IEEE , 2007. 2400-2407 p.
Arsenic compounds, Evolutionary algorithms, Intelligent robots, Robotics, Support vector machines
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-34155DOI: 10.1109/IROS.2007.4399493ISI: 000254073201157ScopusID: 2-s2.0-51349101162ISBN: 978-1-4244-0911-2OAI: oai:DiVA.org:kth-34155DiVA: diva2:419516
IEEE/RSJ International Conference on Intelligent Robots and Systems. San Diego, CA. OCT 29-NOV 02, 2007