Abstract
Quantitative behavioral measurements are important for answering questions across scientific disciplines—from neuroscience to ecology. State-of-the-art deep-learning-based 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, robustness, and usability. Here we introduce an open-source software toolkit, DeepPoseKit, that addresses these problems. Using modern desktop hardware, our methods perform real-time measurements at ~30–110-Hz with offline performance >1000-Hz—approximately 2–6× faster than current methods. We achieve these results while only increasing average error <0.5-pixels compared to the most-accurate methods currently available. We demonstrate the versatility of our approach 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.
