Format

Send to

Choose Destination
Elife. 2019 Oct 1;8. pii: e47994. doi: 10.7554/eLife.47994. [Epub ahead of print]

DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning.

Author information

1
Department of Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany.
2
Department of Computer Science, Princeton University, Princeton, United States.
3
Department for Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany.

Abstract

Quantitative behavioral measurements are important for answering questions across scientific disciplines-from neuroscience to ecology. State-of-the-art deep-learning methods offer major advances in data quality and detail by allowing researchers to automatically estimate locations of an animal's body parts directly from images or videos. However, currently-available animal pose estimation methods have limitations in speed and robustness. Here we introduce a new easy-to-use software toolkit, DeepPoseKit, that addresses these problems using an efficient multi-scale deep-learning model, called Stacked DenseNet, and a fast GPU-based peak-detection algorithm for estimating keypoint locations with subpixel precision. These advances improve processing speed >2× with no loss in accuracy compared to currently-available methods. We demonstrate the versatility of our methods with multiple challenging animal pose estimation tasks in laboratory and field settings-including groups of interacting individuals. Our work reduces barriers to using advanced tools for measuring behavior and has broad applicability across the behavioral sciences.

KEYWORDS:

neuroscience

PMID:
31570119
DOI:
10.7554/eLife.47994
Free full text

Supplemental Content

Full text links

Icon for eLife Sciences Publications, Ltd
Loading ...
Support Center