Metadata-Version: 2.1
Name: anipose
Version: 1.0.0
Summary: Framework for scalable DeepLabCut based analysis including 3D tracking
Home-page: https://github.com/lambdaloop/anipose
Author: Pierre Karashchuk
Author-email: krchtchk@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: BSD License
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: deeplabcut (>=2.0.4.1)
Requires-Dist: aniposelib (>=0.4.0)
Requires-Dist: opencv-contrib-python
Requires-Dist: toml
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: pandas
Requires-Dist: tqdm
Requires-Dist: click
Requires-Dist: scikit-video
Requires-Dist: flask
Requires-Dist: flask-compress
Requires-Dist: flask-ipban
Provides-Extra: viz
Requires-Dist: mayavi ; extra == 'viz'

# Anipose

[![PyPI version](https://badge.fury.io/py/anipose.svg)](https://badge.fury.io/py/anipose)

Anipose is an open-source toolkit for robust, markerless 3D pose estimation of animal behavior from multiple camera views. It leverages the machine learning toolbox [DeepLabCut](https://github.com/AlexEMG/DeepLabCut) to track keypoints in 2D, then triangulates across camera views to estimate 3D pose.

Check out the [Anipose preprint](https://www.biorxiv.org/content/10.1101/2020.05.26.117325v1) for more information.

The name Anipose comes from **Ani**mal **Pose**, but it also sounds like "any pose".

## Documentation

Up to date documentation may be found at [anipose.org](http://anipose.org) .

## Demos

<p align="center">
<img src="https://raw.githubusercontent.com/lambdaloop/anipose-docs/master/tracking_3cams_full_slower5.gif" width="70%" >
</p>
<p align="center">
Videos of flies by Evyn Dickinson (slowed 5x), <a href=http://faculty.washington.edu/tuthill/>Tuthill Lab</a>
</p>

<p align="center">
<img src="https://raw.githubusercontent.com/lambdaloop/anipose-docs/master/hand-demo.gif" width="70%" >
</p>
<p align="center">
Videos of hand by Katie Rupp
</p>



## References

Here are some references for DeepLabCut and other things this project relies upon:
- Mathis et al, 2018, "DeepLabCut: markerless pose estimation of user-defined body parts with deep learning"
- Romero-Ramirez et al, 2018, "Speeded up detection of squared fiducial markers"


