TY - JOUR
T1 - GroupTracker
T2 - Video tracking system for multiple animals under severe occlusion
AU - Fukunaga, Tsukasa
AU - Kubota, Shoko
AU - Oda, Shoji
AU - Iwasaki, Wataru
N1 - Funding Information:
This study was supported by Grant-in-Aid for Young Scientists (B) [grant number 23710231 ] from the Japan Society for the Promotion of Science , the CREST Program from the Japan Science and Technology Agency , and the Canon Foundation . The authors thank Sriswasdi Sira, Haruka Ozaki, and Hirotaka Matsumoto for critically reading the manuscript, and Yasutake Okuda and Satoru Takahashi for technical advice on the tracking system.
Publisher Copyright:
© 2015 Elsevier Ltd. All rights reserved.
PY - 2015/12/31
Y1 - 2015/12/31
N2 - Quantitative analysis of behaviors shown by interacting multiple animals can provide a key for revealing high-order functions of their nervous systems. To resolve these complex behaviors, a video tracking system that preserves individual identity even under severe overlap in positions, i.e., occlusion, is needed. We developed GroupTracker, a multiple animal tracking system that accurately tracks individuals even under severe occlusion. As maximum likelihood estimation of Gaussian mixture model whose components can severely overlap is theoretically an ill-posed problem, we devised an expectation-maximization scheme with additional constraints on the eigenvalues of the covariance matrix of the mixture components. Our system was shown to accurately track multiple medaka (Oryzias latipes) which freely swim around in three dimensions and frequently overlap each other. As an accurate multiple animal tracking system, GroupTracker will contribute to revealing unexplored structures and patterns behind animal interactions. The Java source code of GroupTracker is available at https://sites.google.com/site/fukunagatsu/software/group-tracker.
AB - Quantitative analysis of behaviors shown by interacting multiple animals can provide a key for revealing high-order functions of their nervous systems. To resolve these complex behaviors, a video tracking system that preserves individual identity even under severe overlap in positions, i.e., occlusion, is needed. We developed GroupTracker, a multiple animal tracking system that accurately tracks individuals even under severe occlusion. As maximum likelihood estimation of Gaussian mixture model whose components can severely overlap is theoretically an ill-posed problem, we devised an expectation-maximization scheme with additional constraints on the eigenvalues of the covariance matrix of the mixture components. Our system was shown to accurately track multiple medaka (Oryzias latipes) which freely swim around in three dimensions and frequently overlap each other. As an accurate multiple animal tracking system, GroupTracker will contribute to revealing unexplored structures and patterns behind animal interactions. The Java source code of GroupTracker is available at https://sites.google.com/site/fukunagatsu/software/group-tracker.
KW - Animal tracking
KW - Bioimage informatics
KW - Computational ethology
UR - http://www.scopus.com/inward/record.url?scp=84930384930&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84930384930&partnerID=8YFLogxK
U2 - 10.1016/j.compbiolchem.2015.02.006
DO - 10.1016/j.compbiolchem.2015.02.006
M3 - Article
C2 - 25736254
AN - SCOPUS:84930384930
VL - 57
SP - 39
EP - 45
JO - Computational Biology and Chemistry
JF - Computational Biology and Chemistry
SN - 1476-9271
ER -