Format

Send to

Choose Destination
Nat Neurosci. 2018 Sep;21(9):1281-1289. doi: 10.1038/s41593-018-0209-y. Epub 2018 Aug 20.

DeepLabCut: markerless pose estimation of user-defined body parts with deep learning.

Author information

1
Institute for Theoretical Physics and Werner Reichardt Centre for Integrative Neuroscience, Eberhard Karls Universität Tübingen, Tübingen, Germany.
2
Department of Molecular & Cellular Biology and Center for Brain Science, Harvard University, Cambridge, MA, USA.
3
Department of Neuroscience and the Mortimer B. Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, USA.
4
Institute for Theoretical Physics and Werner Reichardt Centre for Integrative Neuroscience, Eberhard Karls Universität Tübingen, Tübingen, Germany. mackenzie@post.harvard.edu.
5
The Rowland Institute at Harvard, Harvard University, Cambridge, MA, USA. mackenzie@post.harvard.edu.
6
Max Planck Institute for Biological Cybernetics, Tübingen, Germany.
7
Bernstein Center for Computational Neuroscience, Tübingen, Germany.
8
Center for Neuroscience and Artificial Intelligence, Baylor College of Medicine, Houston, TX, USA.

Abstract

Quantifying behavior is crucial for many applications in neuroscience. 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. In motor control studies, humans or other animals are often marked with reflective markers to assist with computer-based tracking, but markers are intrusive, and the number and location of the markers must be determined a priori. Here we present an efficient method for markerless pose estimation based on transfer learning with deep neural networks that achieves excellent results with minimal training data. We demonstrate the versatility of this framework by tracking various body parts in multiple species across a broad collection of behaviors. Remarkably, even when only a small number of frames are labeled (~200), the algorithm achieves excellent tracking performance on test frames that is comparable to human accuracy.

Comment in

PMID:
30127430
DOI:
10.1038/s41593-018-0209-y
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center