Show simple item record

dc.contributor.authorLeCras, Jared
dc.contributor.authorPaxman, Jonathan
dc.contributor.authorSaracik, Brad
dc.contributor.editorG. Sen Gupta
dc.contributor.editorDonald Bailey
dc.contributor.editorSerge Demidenko
dc.contributor.editorDale Carnegie
dc.date.accessioned2017-01-30T12:36:05Z
dc.date.available2017-01-30T12:36:05Z
dc.date.created2012-03-26T20:01:26Z
dc.date.issued2011
dc.identifier.citationLe Cras, Jared and Paxman, Jonathan and Saracik, Brad. 2011. Vision Based Localization under Dynamic Illumination, in G. Sen Gupta, D. Bailey, S. Demidenko and D. Carnegie (ed), Proceedings of the 5th International Conference on Automation, Robotics and Applications (ICARA), Dec 6-8 2011, pp. 453-458. Wellington, NZ: IEEE.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/23221
dc.identifier.doi10.1109/ICARA.2011.6144926
dc.description.abstract

Localization in dynamically illuminated environments is often difficult due to static objects casting dynamic shadows. Feature extraction algorithms may detect both the objects and their shadows, producing conflict in localization algorithms. This work examines a colour model that separates brightness from chromaticity and applies it to eliminate features caused by dynamic illumination. The colour model is applied in two novel ways. Firstly, the chromaticity distortion of a single feature is used to determine if the feature is the result of illumination alone i.e. a shadow. Secondly, the chromaticity distortion of features matched between images is examined to determine if the monochrome based algorithm has matched them correctly. These two applications are put through a variety of tests in simulated then real world environments to assess their effectiveness in dynamically illuminated scenarios. The results demonstrate a significant reduction in the number of feature mismatches between images with dynamic light sources. The evaluation of the techniques individually in a Simultaneous Localization and Mapping (SLAM) task show substantial improvements in accuracy, with the combination of the two techniques producing a localization result that is highly robust to the environmental lighting.

dc.publisherIEEE
dc.subjectmining
dc.subjectlocalization
dc.subjectdynamic illumination
dc.titleVision Based Localization under Dynamic Illumination
dc.typeConference Paper
dcterms.source.startPage453
dcterms.source.endPage458
dcterms.source.titleProceedings of the 5th International Conference on Automation, Robotics and Applications (ICARA)
dcterms.source.seriesProceedings of the 5th International Conference on Automation, Robotics and Applications (ICARA)
dcterms.source.isbn978-1-4577-0329-4
dcterms.source.conference5th International Conference on Automation, Robotics and Applications (ICARA)
dcterms.source.conference-start-dateDec 6 2011
dcterms.source.conferencelocationWellington, New Zealand
dcterms.source.placeWellington, New Zealand
curtin.note

© 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

curtin.departmentDepartment of Mechanical Engineering
curtin.accessStatusOpen access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record