CaT-z: 3D Tracking and Automatic Classification of Rodent Behavior

Ana Gerós and colleagues developed CaT-z, an open source packages for tracking behavior from video recordings. CaT-z utilizes video segmentation, tracking of body parts, and automated classification of behaviors through machine learning and computer vision methods. The setup uses low-cost RGB-D depth-sensing cameras for tracking behaviors in various environments (static, dynamic, or dark). The software includes GUI interfaces for video acquisition, annotation, and processing of behavioral data. The package is capable of automated behavior detection based on limited amounts of annotated video (e.g., 30 minutes).

This research tool was created by your colleagues. Please acknowledge the Principal Investigator, cite the article in which the tool was described, and include an RRID in the Materials and Methods of your future publications. RRID: SCR_023399

Special thanks to Weston Link, an undergraduate neuroscience major, for providing this project summary! This summary is part of a collection from students in a Computational Methods for Neuroscience Course at American University.