@article {Graving620245, author = {Jacob M. Graving and Daniel Chae and Hemal Naik and Liang Li and Benjamin Koger and Blair R. Costelloe and Iain D. Couzin}, title = {DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning}, elocation-id = {620245}, year = {2019}, doi = {10.1101/620245}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Quantitative behavioral measurements are important for answering questions across scientific disciplines{\textemdash}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{\textquoteright}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 eZcient 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{\texttimes} 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{\textemdash}including groups of interacting individuals. Our work reduces barriers to using advanced tools for measuring behavior and has broad applicability across the behavioral sciences.}, URL = {https://www.biorxiv.org/content/early/2019/09/04/620245}, eprint = {https://www.biorxiv.org/content/early/2019/09/04/620245.full.pdf}, journal = {bioRxiv} }