Welcome to idtracker.ai’s documentation!¶
idtracker.ai allows to track groups of up to 100 unmarked animals from videos recorded in laboratory conditions.
New release: idtracker.ai v4¶
Works with Python 3.7 and Pytorch 1.10.0 and CUDA 10.2 or 11.3.
New horizontal GUI layout.
“Add setup points” feature allows to annotate groups of points in the frame that can be useful for analysis. These groups of points are stored together with the trajectories in the trajectories.npy and trajectories_wo_gaps.npy files.
Save trajectories as CSV files using the advanced parameters.
Check What’s new in idtracker.ai v4 and join the idtracker.ai users group to get announcements about new releases.
Start using idtracker.ai¶
Check the Installation and requirements to find the best installation mode for your usage case.
Follow the instructions in the Quickstart to track the example video and get use to the idtracker.ai workflow.
If you are unsure whether idtracker.ai will work on your videos, check the Guidelines for good videos and the Gallery to see how our videos look like.
Our research using idtracker.ai¶
Heras, F. J., Romero-Ferrero, F., Hinz, R. C., & de Polavieja, G. G. (2019). Deep attention networks reveal the rules of collective motion in zebrafish. PLoS computational biology, 15(9), e1007354. [bibtex] [bioRxiv] [gitlab] [data].
Laan, A., Iglesias-Julios, M., & de Polavieja, G. G. (2018). Zebrafish aggression on the sub-second time scale: evidence for mutual motor coordination and multi-functional attack manoeuvres. Royal Society open science, 5(8), 180679. [bibtex] [bioRxiv]
Source code¶
The source code can be found at the idtracker.ai Gitlab repository.
Check the code documentation Index for more information about different classes, functions and methods of idtracker.ai
Data¶
The data used in the idtracker.ai article can be found in the Data section of this web page.
Reference¶
When using information from this web page please reference
Romero-Ferrero, F., Bergomi, M.G., Hinz, R.C., Heras, F.J.H., de Polavieja, G.G., Nature Methods, 2019. idtracker.ai: tracking all individuals in small or large collectives of unmarked animals [pdf] [bibtex] [arXiv]. (F.R.-F. and M.G.B. contributed equally to this work. Correspondence should be addressed to G.G.d.P: gonzalo.polavieja@neuro.fchampalimaud.org)