bioRxivNeurosciencePreprint
Validation of DeepLabCut as a tool for markerless 3D pose estimation
Veronika KosourikhinaiD, Diarmuid KavanaghiD, Michael J. RichardsoniD, David Michael KaplaniD
- Citations
- 3
Abstract
Deep learning-based approaches to markerless 3D pose estimation have taken neuroscience by storm. Yet many of these tools remain unvalidated. Here, we report on the validation of one increasingly popular tool (DeepLabCut) against simultaneous measurements obtained from a reference measurement system (Fastrak) with well-known performance characteristics. Our results confirm close (mm range) agreement between the two, indicating that deep learning-based approaches can be used by the research community with confidence.
Reproducibility ledger
Nobody has reported trying to reproduce this paper yet. Did you replicate an experiment or run the code? Your report saves the next lab a week.
Sign in to file a reproducibility report.
Related papers
- Validating marker-less pose estimation with 3D x-ray radiography
D. D. Moore, J. D. Walker, … N. G. Hatsopoulos·bioRxiv·Jun 15, 2021
- Using DeepLabCut for 3D markerless pose estimation across species and behaviors
Tanmay Nath, Alexander Mathis, … Mackenzie Weygandt Mathis·Nature ProtocolsPeer-reviewed·Jun 21, 2019
- LiftPose3D, a deep learning-based approach for transforming 2D to 3D pose in laboratory animals
A. Gosztolai, S. Gunel, … P. Ramdya·bioRxiv·Sep 18, 2020
- Validation of marker-less pose estimation for 3D kinematics during upper limb reaching
I. Avni, L. Landau, … L. Shmuelof·bioRxiv·Mar 16, 2023
- Human Movement Science in The Wild: Can Current Deep-Learning Based Pose Estimation Free Us from The Lab?
L. Needham, M. Evans, … S. L. Colyer·bioRxiv·Apr 22, 2021
- Anipose: a toolkit for robust markerless 3D pose estimation
Pierre Karashchuk, Katie L. Rupp, … John C Tuthill·Cell ReportsPeer-reviewed·Sep 1, 2021