Webinar: Clinical Gait Analysis using Video-Based Pose Estimation, Part 1 of 2

Ryan Roemmich and Jan Stenum from the Kennedy Krieger Institute and John Hopkins University School of Medicine presents their clinical gait analysis software using video based pose estimation. Dr. Roemmich highlights and discusses the versatile workflow that leverages an open-source human pose estimation algorithm (OpenPose) and the comprehensive validation they conducted to support its use clinically. This includes 1) validation of the workflow in three different groups of participants (adults without gait impairment, persons post-stroke, and persons with Parkinson’s disease) via comparison to ground-truth three-dimensional motion capture, 2) demonstration of the ability to capture clinically relevant, condition-specific gait parameters, and 3) tracking of within-participant changes in gait, as is required to measure progress in rehabilitation and recovery.

This webinar is offered jointly with the Restore Center (https://restore.stanford.edu/), an NIH-funded Medical Rehabilitation Research Resource Network Center at Stanford University.

Watch the tutorial:
Webinar(Tutorial): Clinical Gait Anal...

Learn more:
Read the associated publications:
https://journals.plos.org/ploscompbio...
https://www.medrxiv.org/content/10.11...
Access the analysis code:
https://github.com/janstenum/GaitAnal...

Chapters:
0:00 Intro
2:25 Research talk
33:20 Q&A