Semantic map segmentation using function-based energy maximization
2012 (English)In: 2012 IEEE International Conference on Robotics and Automation (ICRA), IEEE Computer Society, 2012, 4066-4073 p.Conference paper (Refereed)
This work describes the automatic segmentation of 2-dimensional indoor maps into semantic units along lines of spatial function, such as connectivity or objects used for certain tasks. Using a conceptually simple and readily extensible energy maximization framework, segmentations similar to what a human might produce are demonstrated on several real-world datasets. In addition, it is shown how the system can perform reference resolution by adding corresponding potentials to the energy function, yielding a segmentation that responds to the context of the spatial reference.
Place, publisher, year, edition, pages
IEEE Computer Society, 2012. 4066-4073 p.
, IEEE International Conference on Robotics and Automation, ISSN 2152-4092
Automatic segmentations, Energy functions, Energy maximization, Real-world datasets, Reference resolution, Semantic map, Semantic units, Spatial functions, Spatial reference, Robotics, Semantics
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-101529DOI: 10.1109/ICRA.2012.6224811ISI: 000309406704013ScopusID: 2-s2.0-84864460779ISBN: 978-1-4673-1405-3OAI: oai:DiVA.org:kth-101529DiVA: diva2:549304
IEEE International Conference on Robotics and Automation (ICRA) Location: St Paul, MN Date: May 14-18, 2012
QC 201209042012-09-042012-08-302013-10-01Bibliographically approved