Multi-cue Discriminative Place Recognition
2010 (English)In: MULTILINGUAL INFORMATION ACCESS EVALUATION II: MULTIMEDIA EXPERIMENTS, PT II / [ed] Peters C; Caputo B; Gonzalez J; Jones GJF; KalpathyCramer J; Muller H; Tsikrika T, 2010, Vol. 6242, 315-323 p.Conference paper (Refereed)
In this paper we report on our successful participation in the Robot Vision challenge in the ImageCLEF 2009 campaign. We present a place recognition system that employs four different discriminative models trained on different global and local visual cues. In order to provide robust recognition, the outputs generated by the models are combined using a discriminative accumulation method. Moreover, the system is able to provide an indication of the confidence of its decision. We analyse the properties and performance of the system on the training and validation data and report the final score obtained on the test run which ranked first in the obligatory track of the Robot Vision task.
Place, publisher, year, edition, pages
2010. Vol. 6242, 315-323 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 6242
Discriminative models, ImageCLEF, Place recognition, Robust recognition, Validation data, Visual cues
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-31376DOI: 10.1007/978-3-642-15751-6_41ISI: 000286416400041ScopusID: 2-s2.0-78049339337ISBN: 978-3-642-15750-9OAI: oai:DiVA.org:kth-31376DiVA: diva2:404002
10th Workshop of the Cross-Language Evaluation Forum, Corfu, GREECE, SEP 30-OCT 02, 2009
QC 201103152011-03-152011-03-142011-03-15Bibliographically approved