Skip to main content

HotSpotter-Patterned species instance recognition

Author(s): Crall, JP; Stewart, CV; Berger-Wolf, TY; Rubenstein, Daniel I.; Sundaresan, SR

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1dz29
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCrall, JP-
dc.contributor.authorStewart, CV-
dc.contributor.authorBerger-Wolf, TY-
dc.contributor.authorRubenstein, Daniel I.-
dc.contributor.authorSundaresan, SR-
dc.date.accessioned2020-03-11T16:25:12Z-
dc.date.available2020-03-11T16:25:12Z-
dc.date.issued2013-04-04en_US
dc.identifier.citationCrall, JP, Stewart, CV, Berger-Wolf, TY, Rubenstein, DI, Sundaresan, SR. (2013). HotSpotter-Patterned species instance recognition. Proceedings of IEEE Workshop on Applications of Computer Vision, 230 - 237. doi:10.1109/WACV.2013.6475023en_US
dc.identifier.issn2158-3978-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1dz29-
dc.description.abstractWe present HotSpotter, a fast, accurate algorithm for identifying individual animals against a labeled database. It is not species specific and has been applied to Grevy's and plains zebras, giraffes, leopards, and lionfish. We describe two approaches, both based on extracting and matching keypoints or 'hotspots'. The first tests each new query image sequentially against each database image, generating a score for each database image in isolation, and ranking the results. The second, building on recent techniques for instance recognition, matches the query image against the database using a fast nearest neighbor search. It uses a competitive scoring mechanism derived from the Local Naive Bayes Nearest Neighbor algorithm recently proposed for category recognition. We demonstrate results on databases of more than 1000 images, producing more accurate matches than published methods and matching each query image in just a few seconds. © 2013 IEEE.en_US
dc.format.extent230 - 237en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings of IEEE Workshop on Applications of Computer Visionen_US
dc.rightsAuthor's manuscripten_US
dc.titleHotSpotter-Patterned species instance recognitionen_US
dc.typeConference Paperen_US
dc.identifier.doidoi:10.1109/WACV.2013.6475023-
dc.identifier.eissn2158-3986-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
AM_HotSpotter_Patterned_Species_Instance_Recognition.pdf1.13 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.