DeepLabCut: An Open Source Toolbox for Robust Animal Pose Estimation
Mackenzie Mathis (Harvard University & Swiss Federal Institute of Technology Lausanne)
To support code maintenance, a new code cookbook, and user education for the DeepLabCut software community and set the foundation towards becoming a sustainable software package for years to come.
Quantifying behavior is crucial for many applications in neuroscience, ethology, genetics, medicine, and biology. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be highly time consuming.
DeepLabCut offers an efficient method for 3D markerless pose estimation based on transfer learning with deep neural networks that achieves excellent results (i.e. you can match human labeling accuracy) with minimal training data (typically 50-200 frames). We demonstrate the versatility of this framework by tracking various body parts in multiple species across a broad collection of behaviors. The package is open source, fast, robust, and can be used to compute 3D pose estimates.