File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Curvature domain image stitching

TitleCurvature domain image stitching
Authors
KeywordsCurvature
Gradient
Image stitching
Panoramic mosaking
Photometric inconsistency
Issue Date2007
Citation
Conference Proceedings - Ieee International Conference On Systems, Man And Cybernetics, 2007, v. 4, p. 3164-3169 How to Cite?
AbstractDigital photograph stitching blends multiple images to form a single one with a wide field of view. However, artifacts may arise, often due to photometric inconsistency and geometric misalignment among the images. Several existing techniques tackle this problem by methods such as pixel selection or pixel blending, which Evolve the matching and adjustment of intensity, frequency, and gradient values. However, our experience indicates that these methods have yet fully incorporated the uniformity properties of the photometric inconsistency. In this paper, we first explain the causes of inconsistency and its uniformity property. Then, by mathematical analysis, we show that the matching on the intensity and even the gradient domain is insufficient for some non-uniform inconsistencies. Our method thus adds the extra requirement of an optimal matching of curvature. We then explain how its variables can affect the computational and visual performance. Simulations are carried out using our method, with some masks designed with these two concerns. Some real examples show that our method can produce pleasant visual results even when both misalignment and non-uniform inconsistency exist. © 2006 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/99043
ISSN
References

 

DC FieldValueLanguage
dc.contributor.authorSuen, STYen_HK
dc.contributor.authorLam, EYen_HK
dc.contributor.authorWong, KKYen_HK
dc.date.accessioned2010-09-25T18:13:32Z-
dc.date.available2010-09-25T18:13:32Z-
dc.date.issued2007en_HK
dc.identifier.citationConference Proceedings - Ieee International Conference On Systems, Man And Cybernetics, 2007, v. 4, p. 3164-3169en_HK
dc.identifier.issn1062-922Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/99043-
dc.description.abstractDigital photograph stitching blends multiple images to form a single one with a wide field of view. However, artifacts may arise, often due to photometric inconsistency and geometric misalignment among the images. Several existing techniques tackle this problem by methods such as pixel selection or pixel blending, which Evolve the matching and adjustment of intensity, frequency, and gradient values. However, our experience indicates that these methods have yet fully incorporated the uniformity properties of the photometric inconsistency. In this paper, we first explain the causes of inconsistency and its uniformity property. Then, by mathematical analysis, we show that the matching on the intensity and even the gradient domain is insufficient for some non-uniform inconsistencies. Our method thus adds the extra requirement of an optimal matching of curvature. We then explain how its variables can affect the computational and visual performance. Simulations are carried out using our method, with some masks designed with these two concerns. Some real examples show that our method can produce pleasant visual results even when both misalignment and non-uniform inconsistency exist. © 2006 IEEE.en_HK
dc.languageengen_HK
dc.relation.ispartofConference Proceedings - IEEE International Conference on Systems, Man and Cyberneticsen_HK
dc.subjectCurvatureen_HK
dc.subjectGradienten_HK
dc.subjectImage stitchingen_HK
dc.subjectPanoramic mosakingen_HK
dc.subjectPhotometric inconsistencyen_HK
dc.titleCurvature domain image stitchingen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailLam, EY:elam@eee.hku.hken_HK
dc.identifier.emailWong, KKY:kywong@eee.hku.hken_HK
dc.identifier.authorityLam, EY=rp00131en_HK
dc.identifier.authorityWong, KKY=rp00189en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICSMC.2006.384603en_HK
dc.identifier.scopuseid_2-s2.0-34548142241en_HK
dc.identifier.hkuros116335en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-34548142241&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume4en_HK
dc.identifier.spage3164en_HK
dc.identifier.epage3169en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridSuen, STY=12804247800en_HK
dc.identifier.scopusauthoridLam, EY=7102890004en_HK
dc.identifier.scopusauthoridWong, KKY=36456599700en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats