Skip to main content

An Animal Detection Pipeline for Identification

Author(s): Parham, J.; Stewart, C.; Crall, J.; Rubenstein, Daniel I.; Holmberg, J.; et al

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr13m5n
Full metadata record
DC FieldValueLanguage
dc.contributor.authorParham, J.-
dc.contributor.authorStewart, C.-
dc.contributor.authorCrall, J.-
dc.contributor.authorRubenstein, Daniel I.-
dc.contributor.authorHolmberg, J.-
dc.contributor.authorBerger-Wolf, T.-
dc.date.accessioned2019-01-02T21:23:50Z-
dc.date.available2019-01-02T21:23:50Z-
dc.date.issued2018-05-03en_US
dc.identifier.citationParham, J, Stewart, C, Crall, J, Rubenstein, D, Holmberg, J, Berger-Wolf, T. (2018). An Animal Detection Pipeline for Identification. Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018, 2018-January (1075 - 1083). doi:10.1109/WACV.2018.00123en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr13m5n-
dc.description.abstract© 2018 IEEE. This paper proposes a 5-component detection pipeline for use in a computer vision-based animal recognition system. The end result of our proposed pipeline is a collection of novel annotations of interest (AoI) with species and view-point labels. These AoIs, for example, could be fed as the focused input data into an appearance-based animal identification system. The goal of our method is to increase the reliability and automation of animal censusing studies and to provide better ecological information to conservationists. Our method is able to achieve a localization mAP of 81.67%, a species and viewpoint annotation classification accuracy of 94.28% and 87.11%, respectively, and an AoI accuracy of 72.75% across 6 animal species of interest. We also introduce the Wildlife Image and Localization Dataset (WILD), which contains 5,784 images and 12,007 labeled annotations across 28 classification species and a variety of challenging, real-world detection scenarios.en_US
dc.format.extent1075 - 1083en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018en_US
dc.rightsAuthor's manuscripten_US
dc.titleAn Animal Detection Pipeline for Identificationen_US
dc.typeConference Articleen_US
dc.identifier.doidoi:10.1109/WACV.2018.00123-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
Animal_Detection_Pipeline_for_Identification_2018.pdf2.99 MBAdobe PDFView/Download


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