DSpace Repository

Epipolar geometry estimation for wide-baseline omnidirectional street view images

Show simple item record

dc.contributor.author Sato, Tomokazu en
dc.contributor.author Tomas, Pajdla en
dc.contributor.author Yokoya, Naokazu en
dc.date.accessioned 2016-12-26T06:41:26Z en
dc.date.available 2016-12-26T06:41:26Z en
dc.date.issued 2011 en
dc.identifier.isbn 9781457711015 en
dc.identifier.uri http://hdl.handle.net/10061/11247 en
dc.description ICCV 2011 : The 13th International Conference on Computer Vision , Nov 6-13, 2011 , Barcelona, Spain en
dc.description.abstract This paper presents a new robust method of epipolar-geometry estimation for omnidirectional images in wide-baseline setting, e.g. with Google street View images. The main idea is to learn new statistical geometric constraints that are derived from the feature descriptors into the model verification process of RANSAC. We show that these constraints provide more reliable matches, which can be used to retrieve correct epipolar geometry in very difficult situations. Robustness of epipolar-geometry estimation is quantitatively evaluated for omnidirectional image pairs with variable baseline. The performance of the proposed method is demonstrated using the complete pipeline of structure-from-motion with real dataset of Google Street View images. en
dc.language.iso en en
dc.publisher IEEE en
dc.rights Copyright c 2011 IEEE en
dc.subject feature extraction en
dc.subject geometry en
dc.subject road traffic en
dc.subject search engines en
dc.subject statistical analysis en
dc.subject stereo image processing en
dc.subject traffic engineering computing en
dc.subject Google street view images en
dc.subject RANSAC model verification process en
dc.subject epipolar geometry estimation en
dc.subject feature descriptors en
dc.subject omnidirectional image pairs en
dc.subject statistical geometric constraints en
dc.subject structure-from-motion pipeline en
dc.subject wide-baseline omnidirectional street view images en
dc.subject Estimation en
dc.subject Pipelines en
dc.subject Robustness en
dc.title Epipolar geometry estimation for wide-baseline omnidirectional street view images en
dc.type.nii Conference Paper en
dc.textversion Author en
dc.identifier.ncid BB09299583 en
dc.identifier.spage 56 en
dc.identifier.epage 63 en
dc.relation.doi 10.1109/ICCVW.2011.6130222 en
dc.identifier.NAIST-ID 73292633 en
dc.identifier.NAIST-ID 73292286 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account