Anipose: A toolkit for robust markerless 3D pose estimation.

Anipose: A toolkit for robust markerless 3D pose estimation.
复制标题

DOI:
10.1016/j.celrep.2021.109730
复制
发表时间:
2021-09-28
期刊:
影响因子:
8.8
通讯作者:
Tuthill JC
Tuthill JC
中科院分区:
生物学1区
文献类型:
--
作者:
Karashchuk P;Rupp KL;Dickinson ES;Walling-Bell S;Sanders E;Azim E;Brunton BW;Tuthill JC

文献摘要

参考文献

被引文献

相似文献

量化运动是理解动物行为的关键。计算机视觉的进步现在可以从2D视频中进行无标记跟踪,但大多数动物的运动都是3D的。在这里,我们介绍Anipose,一个用于鲁棒无标记3D姿态估计的开源工具包。Anipose是建立在二维跟踪方法Deep-LabCut,所以用户可以扩展他们现有的实验设置,以获得准确的三维跟踪。它由四个部分组成:(1)三维标定模块;(2)用于解决二维跟踪误差的滤波器;(3)集成时空正则化的三角测量模块;(4)用于对大量视频进行结构化处理的管道。我们在校准板以及小鼠,苍蝇和人类上评估Anipose。通过分析Anipose跟踪的三维腿部运动学,我们确定了关节旋转在苍蝇行走的电机控制中的关键作用。为了帮助用户开始使用3D跟踪,我们在http://anipose.org/提供教程和文档。Karashchuk等人介绍了Anipose,一个Python工具包,使研究人员能够在3D中跟踪动物的姿势。Anipose执行3D校准,过滤跟踪的关键点,并可视化产生的姿态数据。这个开源软件和附带的教程促进了3D动物行为和生物学的分析。
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/. 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.
DOI: 10.1038/s41598-018-27101-0
发表时间: 2018-06-07
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Balbinot, Gustavo;Schuch, Clarissa Pedrini;Corbett, Dale
通讯作者: Corbett, Dale
DOI: 10.1016/j.neuron.2019.05.007
发表时间: 2019-07-17
期刊: NEURON
影响因子: 16.2
作者:
Becker, Matthew, I;Person, Abigail L.
通讯作者: Person, Abigail L.
DOI: 10.1016/j.conb.2011.10.023
发表时间: 2012-02
影响因子: 5.7
作者:
Bernstein JG;Garrity PA;Boyden ES
通讯作者: Boyden ES
DOI: 10.1126/science.aav6416
发表时间: 2019-08-16
期刊: SCIENCE
影响因子: 56.9
作者:
Abdelfattah, Ahmed S.;Kawashima, Takashi;Schreiter, Eric R.
通讯作者: Schreiter, Eric R.
DOI: 10.1038/nature13021
发表时间: 2014-04-17
期刊: NATURE
影响因子: 64.8
作者:
Azim, Eiman;Jiang, Juan;Jessell, Thomas M.
通讯作者: Jessell, Thomas M.