Alignment of uncalibrated images for multi-view classification

Simple item page
dc.citation.epage2368en_US
dc.citation.spage2365en_US
dc.contributor.authorArık, Sercan Ömeren_US
dc.contributor.authorVuraf, E.en_US
dc.contributor.authorFrossard P.en_US
dc.coverage.spatialBrussels, Belgiumen_US
dc.date.accessioned2016-02-08T12:16:12Z
dc.date.available2016-02-08T12:16:12Z
dc.date.issued2011en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 11-14 Sept. 2011en_US
dc.description.abstractEfficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pair-wise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of images is necessary prior to distance computation. We propose a method for the registration of uncalibrated images that capture the same 3D scene or object. We model the depth map of the scene as an algebraic surface, which yields a warp model in the form of a rational function between image pairs. The warp model is computed by minimizing the registration error, where the registered image is a weighted combination of two images generated with two different warp functions estimated from feature matches and image intensity functions in order to provide robust registration. We demonstrate the flexibility of our alignment method by experimentation on several wide-baseline image pairs with arbitrary scene geometries and texture levels. Moreover, the results on multi-view image classification suggest that the proposed alignment method can be effectively used in graph-based classification algorithms for the computation of pairwise distances where it achieves significant improvements over distance computation without prior alignment. © 2011 IEEE.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T12:16:12Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2011en
dc.identifier.doi10.1109/ICIP.2011.6116116en_US
dc.identifier.urihttp://hdl.handle.net/11693/28279
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/ICIP.2011.6116116en_US
dc.source.title2011 18th IEEE International Conference on Image Processingen_US
dc.subject3D scenesen_US
dc.subjectAlgebraic surfacesen_US
dc.subjectAlignment methodsen_US
dc.subjectClassification algorithmen_US
dc.subjectDepth Mapen_US
dc.subjectDistance computationen_US
dc.subjectEuclidean distanceen_US
dc.subjectFeature matchen_US
dc.subjectGraph-baseden_US
dc.subjectImage alignmenten_US
dc.subjectImage intensity functionsen_US
dc.subjectImage pairsen_US
dc.subjectImage warpingen_US
dc.subjectMulti-view imageen_US
dc.subjectMulti-viewsen_US
dc.subjectPairwise distancesen_US
dc.subjectRegistered imagesen_US
dc.subjectRegistration erroren_US
dc.subjectRobust registrationen_US
dc.subjectSimilarity measureen_US
dc.subjectUncalibrated imagesen_US
dc.subjectWide-baseline imagesen_US
dc.subjectAlgorithmsen_US
dc.subjectAlignmenten_US
dc.subjectImage analysisen_US
dc.subjectImage classificationen_US
dc.subjectImage matchingen_US
dc.subjectImage registrationen_US
dc.subjectRational functionsen_US
dc.subjectThree dimensionalen_US
dc.titleAlignment of uncalibrated images for multi-view classificationen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Alignment of uncalibrated images for multi-view classification.pdf
Size:
363.94 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering