Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation

We turn natural language descriptions of behaviors into machine-executable code

Behavioral segmentation of open field in DeepLabCut, or B-SOID ("B-side"), is a pipeline that pairs unsupervised pattern recognition with supervised classification to achieve fast predictions of behaviors that are not predefined by users.

SDK for running DeepLabCut on a live video stream

Various scripts to support deeplabcut and what to do afterwards!

Workshop material for using DeepLabCut

a module for kinematic analysis of deeplabcut outputs

[ICCV 2023] "Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity"

GUI to run DeepLabCut on live video feed

a napari plugin for labeling and refining keypoint data within DeepLabCut projects

Closed-loop behavioral experiment toolkit using pose estimation of body parts.

replicAnt - generating annotated images of animals in complex environments with Unreal Engine

Docker container for running DeepLabCut 2.0, 2.1 (linux support only). Now, DLC main supports 2.2+

Toolbox for using multiple cameras from intrinsic calculations to reconstructing kinematics

Headless DeepLabCut (no GUI support)

Deep learning-driven multi animal tracking and pose estimation add-on for Blender

DLC2Action is an action segmentation package that makes running and tracking of machine learning experiments easy.

A Primer on Motion Capture with Deep Learning:Principles, Pitfalls and Perspectives

Trained deep neural-net models for estimating articulatory keypoints from midsagittal ultrasound tongue videos and front-view lip camera videos using DeepLabCut. This research is by Wrench, A. and Balch-Tomes, J. (2022) (https://www.mdpi.com/1424-8220/22/3/1133) (https://doi.org/10.3390/s22031133).