COLD: The CoSy Localization Database
2009 (English)In: The international journal of robotics research, ISSN 0278-3649, E-ISSN 1741-3176, Vol. 28, no 5, 588-594 p.Article in journal (Refereed) Published
Two key competencies for mobile robotic systems are localization and semantic context interpretation. Recently, vision has become the modality of choice for these problems as it provides richer and more descriptive sensory input. At the same time, designing and testing vision-based algorithms still remains a challenge, as large amounts of carefully selected data are required to address the high variability of visual information. In this paper we present a freely available database which provides a large-scale, flexible testing environment for vision-based topological localization and semantic knowledge extraction in robotic systems. The database contains 76 image sequences acquired in three different indoor environments across Europe. Acquisition was performed with the same perspective and omnidirectional camera setup, in rooms of different functionality and under various conditions. The database is an ideal testbed for evaluating algorithms in real-world scenarios with respect to both dynamic and categorical variations.
Place, publisher, year, edition, pages
2009. Vol. 28, no 5, 588-594 p.
vision-based robot localization, semantic place classification, robotic benchmarks and databases
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-32855DOI: 10.1177/0278364909103912ISI: 000265219000002ScopusID: 2-s2.0-64949116604OAI: oai:DiVA.org:kth-32855DiVA: diva2:412628
FunderSwedish Research Council, 2005-3600-Complex
QC 201104262011-04-262011-04-212011-04-26Bibliographically approved