TY - GEN
T1 - HotSpotter-Patterned species instance recognition
AU - Crall, Jonathan P.
AU - Stewart, Charles V.
AU - Berger-Wolf, Tanya Y.
AU - Rubenstein, Daniel Ian
AU - Sundaresan, Siva R.
N1 - Copyright:
Copyright 2013 Elsevier B.V., All rights reserved.
PY - 2013
Y1 - 2013
N2 - We 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.
AB - We 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.
UR - http://www.scopus.com/inward/record.url?scp=84875585028&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84875585028&partnerID=8YFLogxK
U2 - 10.1109/WACV.2013.6475023
DO - 10.1109/WACV.2013.6475023
M3 - Conference contribution
AN - SCOPUS:84875585028
SN - 9781467350532
T3 - Proceedings of IEEE Workshop on Applications of Computer Vision
SP - 230
EP - 237
BT - 2013 IEEE Workshop on Applications of Computer Vision, WACV 2013
T2 - 2013 IEEE Workshop on Applications of Computer Vision, WACV 2013
Y2 - 15 January 2013 through 17 January 2013
ER -