motr is a fully automated tracking application that is capable of tracking multiple mice in a single enclosure over long periods of time (days) without confusing their identities. The system analyzes input video sequences and outputs trajectory information for each mouse in the enclosure. The system automatically learns the external appearance of mice from training videos and generalizes to identify mice when they are videoed in a group.
motr is described in:
Ohayon S, Avni O, Taylor AL, Perona P, Egnor SER (2013). Automated multi-day tracking of marked mice for the analysis of social behavior. Journal of Neuroscience Methods 219(1):10–19. pubmed | journal | pdf | supplementary movie (MPEG-4, H.264, 130 MB)
The system uses a friendly GUI that requires minimal user interaction. Videos are loaded, and then submitted to a compute cluster. (Distributed analysis is currently supported on Linux, and on SGE clusters.)
motr is an open-source (GPLv2), freely available program developed by Shay Ohayon, Pietro Perona (Caltech), Ofer Avni, Adam Taylor and Roian Egnor (Janelia Farm).
Note that motr for the Windows platform does not support analysis of data across multiple computers. Distributed analysis is currently supported only on SGE clusters.
updated August 1, 2013