SVD-Matching using SIFT Features

Simple item page
dc.contributor.authorDelponte, Elisabettaen_US
dc.contributor.authorIsgrò, Francescoen_US
dc.contributor.authorOdone, Francescaen_US
dc.contributor.authorVerri, Alessandroen_US
dc.contributor.editorMike Chantleren_US
dc.date.accessioned2016-02-11T13:30:55Z
dc.date.available2016-02-11T13:30:55Z
dc.date.issued2005en_US
dc.description.abstractThe paper tackles the problem of feature points matching between pair of images of the same scene. This is a key problem in computer vision. Among the many possible applications of feature matching we are motivated for helping in the initialisation of a 3D registration procedure. The method we discuss here is a version of the SVD matching proposed by Pilu, modified in order to cope with large scale variations. We detail the algorithm and present experimental evidence of the improvement in performance. The main contribution of this work is in showing that this compact and easy algorithm can be used for large-baseline matching.en_US
dc.description.sectionheadersMultiple Views and 3-Den_US
dc.description.seriesinformationVision, Video, and Graphics (2005)en_US
dc.identifier.doi10.2312/vvg.20051016en_US
dc.identifier.isbn3-905673-57-6en_US
dc.identifier.pages125-132en_US
dc.identifier.urihttps://doi.org/10.2312/vvg.20051016en_US
dc.publisherThe Eurographics Associationen_US
dc.titleSVD-Matching using SIFT Featuresen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
125-132.pdf
Size:
1.17 MB
Format:
Adobe Portable Document Format
Download
Collections
VVG05