GroupTracker: Video tracking system for multiple animals under severe occlusion. (August 2015)
- Record Type:
- Journal Article
- Title:
- GroupTracker: Video tracking system for multiple animals under severe occlusion. (August 2015)
- Main Title:
- GroupTracker: Video tracking system for multiple animals under severe occlusion
- Authors:
- Fukunaga, Tsukasa
Kubota, Shoko
Oda, Shoji
Iwasaki, Wataru - Abstract:
- Abstract : Graphical abstract: Abstract : Highlights: We developed "GroupTracker", a new multiple animal tracking system. This system accurately tracks individuals even under severe occlusion. We devised an EM scheme with constraints on the eigenvalues of the covariance matrix. We aim at revealing behavioral patterns behind animal interactions using our software. Abstract: 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 availableAbstract : Graphical abstract: Abstract : Highlights: We developed "GroupTracker", a new multiple animal tracking system. This system accurately tracks individuals even under severe occlusion. We devised an EM scheme with constraints on the eigenvalues of the covariance matrix. We aim at revealing behavioral patterns behind animal interactions using our software. Abstract: 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 athttps://sites.google.com/site/fukunagatsu/software/group-tracker . … (more)
- Is Part Of:
- Computational biology and chemistry. Volume 57(2015)
- Journal:
- Computational biology and chemistry
- Issue:
- Volume 57(2015)
- Issue Display:
- Volume 57, Issue 2015 (2015)
- Year:
- 2015
- Volume:
- 57
- Issue:
- 2015
- Issue Sort Value:
- 2015-0057-2015-0000
- Page Start:
- 39
- Page End:
- 45
- Publication Date:
- 2015-08
- Subjects:
- Bioimage informatics -- Computational ethology -- Animal tracking
Chemistry -- Data processing -- Periodicals
Biology -- Data processing -- Periodicals
Biochemistry -- Data processing
Biology -- Data processing
Molecular biology -- Data processing
Periodicals
Electronic journals
542.85 - Journal URLs:
- http://www.sciencedirect.com/science/journal/14769271 ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.compbiolchem.2015.02.006 ↗
- Languages:
- English
- ISSNs:
- 1476-9271
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3390.576700
British Library DSC - BLDSS-3PM
British Library STI - ELD Digital store - Ingest File:
- 6997.xml