MVIG-SJTU / AlphaTracker

AlphaTracker is a computer vision pipeline with the practical and real-time advantages , which requires minimal hardware requirements and produces reliable tracking of multiple unmarked animals. An easy-to-use user interface further enables manual inspection and curation of results.

AlphaTracker

AlphaTracker is a multi-animal tracking and behavioral analysis tool which incorporates multi-animal tracking, pose estimation and unsupervised behavioral clustering to empower system neuroscience research. Alphatracker achieves the state-of-art accuracy of multi-animal tracking which lays the foundation for stringent biological studies. Moreover, the minimum requirement for hardware (regular webcams) and efficient training procedure allows readily adoption by most neuroscience labs. We also provide simple GUI for most procedure in AlphaTracker so as to facilitate research for non-cs labmates and students.

Architecture and Pipeline of AlphaTracker

Illustration of AlphaTracker main GUI

Instructions

• Installation

  See Installation.md

• Tracking

  If you have access to GPU:

  Multi-animal Pose Estimation and Tracking

  If you don't have access to GPU:

  Use on Google Colab

• Behavioral clustering

  Unsupervised Behavioral Clustering

• UI for inspecting tracking and clustering results

  Tracking UI and Clustering UI

Reference

Nancy Padilla-Coreano, Kanha Batra, Makenzie Patarino et al. A cortical-hypothalamic circuit decodes social rank and promotes dominance behavior, 03 November 2020, PREPRINT (Version 1) available at Research Square [https://doi.org/10.21203/rs.3.rs-94115/v1]

AlphaTracker: A Multi-Animal Tracking and Behavioral Analysis Tool Zexin Chen, Ruihan Zhang, Yu Eva Zhang, Hao-Shu Fang, Haowen Zhou, Rachel R. Rock, Aneesh Bal, Nancy Padilla-Coreano, Laurel Keyes, Kay M. Tye, Cewu Lu bioRxiv 2020.12.04.405159; doi: https://doi.org/10.1101/2020.12.04.405159

For technical questions contact us at [e-mail]