ToxTrac Files

README

The current study and the ground truth of the datasets should be referenced as:

Rodriguez, Alvaro and Zhang, Hanqing and Klaminder, Jonatan and Brodin, Tomas and Andersson, Patrik L. and Andersson, Magnus. ToxId: an efficient algorithm to solve occlusions when tracking multiple animals, (2017).

The different datasets should be referenced as:

• Ant5: Pérez-Escudero, A., Vicente-Page, J., Hinz, R. C., Arganda, S. & de Polavieja, G. G. idTracker: tracking individuals in a group by automatic identification of unmarked animals. Nat. Methods 11, 743–748 (2014).

• Cockroach3: Rodriguez, Alvaro and Zhang, Hanqing and Klaminder, Jonatan and Brodin, Tomas and Andersson, Patrik L. and Andersson, Magnus. ToxId: an efficient algorithm to solve occlusions when tracking multiple animals, (2017).

• Guppy2: Rodriguez, Alvaro and Zhang, Hanqing and Klaminder, Jonatan and Brodin, Tomas and Andersson, Patrik L. and Andersson, Magnus. ToxId: an efficient algorithm to solve occlusions when tracking multiple animals, (2017).

• Mice3: Giancardo, L. et al. Automatic visual tracking and social behaviour analysis with multiple mice. PLoS One 8, e74557 (2013). Available at: https://www.iit.it/research/lines/pattern-analysis-and-computer-vision/pavis-datasets/531-mice-behaviour-analysis

• Waterlouse5: Rodriguez, Alvaro and Zhang, Hanqing and Klaminder, Jonatan and Brodin, Tomas and Andersson, Patrik L. and Andersson, Magnus. ToxId: an efficient algorithm to solve occlusions when tracking multiple animals, (2017).

• WingedAnts7: Busso, J. P. Department of Evolutionary Biology and Environmental Studies, University of Zurich. http://www.ieu.uzh.ch/en/research/evolbiol/invertebrates/member.html. Available at: http://www.roborealm.com/tutorial/Blob_Tracking/index.php

• Zebrafish5: Pérez-Escudero, A., Vicente-Page, J., Hinz, R. C., Arganda, S. & de Polavieja, G. G. idTracker: tracking individuals in a group by automatic identification of unmarked animals. Nat. Methods 11, 743–748 (2014).

• Zebrafish11: Zhiping, X. U. & Cheng, X. E. Zebrafish tracking using convolutional neural networks. Sci. Rep. 7, 42815 (2017).

All our datasets: Cockroach3, Guppy2 and Waterlouse5, are freely available for use and redistribution.

The datasets Ant5, WingedAnts7, Zebrafish5 and Zebrafish11 do not belong to us, they are copies of datasets offered the by their authors freely online. In some cases the original datasets have been converted to a different format, or edited to fit the current study. These datasets are freely available for their use and distribution with research our education purposes.

The Mice3 dataset cannot be freely used and distributed. If you want to use this dataset you need to contact their original authors. If you want to use the edited video version used to generate the data on this paper (this is a 6MB .avi file), you should request a permission of the original authors and contact us.