TY - GEN
T1 - An Animal Detection Pipeline for Identification
AU - Parham, Jason
AU - Stewart, Charles
AU - Crall, Jonathan
AU - Rubenstein, Daniel Ian
AU - Holmberg, Jason
AU - Berger-Wolf, Tanya
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/5/3
Y1 - 2018/5/3
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85051124859&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051124859&partnerID=8YFLogxK
U2 - 10.1109/WACV.2018.00123
DO - 10.1109/WACV.2018.00123
M3 - Conference contribution
AN - SCOPUS:85051124859
T3 - Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018
SP - 1075
EP - 1083
BT - Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018
Y2 - 12 March 2018 through 15 March 2018
ER -