Anipose: a toolkit for robust markerless 3D pose estimation
| Autor: | Evyn S. Dickinson, Pierre Karashchuk, Sarah Walling-Bell, Katie L. Rupp, John C. Tuthill, Elischa Sanders, Eiman Azim, Bingni W. Brunton |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
QH301-705.5
Computer science Movement Walking pose estimation Tracking (particle physics) 3D pose estimation General Biochemistry Genetics and Molecular Biology Article Mice Deep Learning Imaging Three-Dimensional Software 3d tracking Animals Humans Animal behavior Computer vision Biology (General) Pose computer.programming_language Behavior Animal behavior business.industry Deep learning robust tracking Triangulation (computer vision) Python (programming language) Pipeline (software) Visualization Biomechanical Phenomena markerless tracking Artificial intelligence business computer 3D Camera resectioning |
| Zdroj: | Cell reports Cell Reports, Vol 36, Iss 13, Pp 109730-(2021) |
| DOI: | 10.1101/2020.05.26.117325 |
| Popis: | SUMMARY Quantifying movement is critical for understanding animal behavior. Advances in computer vision now enable markerless tracking from 2D video, but most animals move in 3D. Here, we introduce Anipose, an open-source toolkit for robust markerless 3D pose estimation. Anipose is built on the 2D tracking method Deep-LabCut, so users can expand their existing experimental setups to obtain accurate 3D tracking. It consists of four components: (1) a 3D calibration module, (2) filters to resolve 2D tracking errors, (3) a triangulation module that integrates temporal and spatial regularization, and (4) a pipeline to structure processing of large numbers of videos. We evaluate Anipose on a calibration board as well as mice, flies, and humans. By analyzing 3D leg kinematics tracked with Anipose, we identify a key role for joint rotation in motor control of fly walking. To help users get started with 3D tracking, we provide tutorials and documentation at http://anipose.org/. Graphical Abstract In brief Karashchuk et al. introduce Anipose, a Python toolkit that enables researchers to track animal poses in 3D. Anipose performs 3D calibration, filters tracked keypoints, and visualizes resulting pose data. This open-source software and accompanying tutorials facilitate the analysis of 3D animal behavior and the biology that underlies it. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|