Vision-based gait analysis data for the Timed Up and Go (TUG) test, likely containing 2D and 3D human pose keypoints. The dataset includes JH-FRAT labels, which are used for fall risk assessment. It is hosted on Kaggle and is intended for applications in healthcare and computer vision.
Use Cases
- Train pose estimation models for clinical movement analysis based on 2D/3D keypoints.
- Develop regression models to predict fall risk scores based on gait features.
- Build classification models to categorize patient mobility levels using JH-FRAT labels.
- Validate vision-based systems for automating the Timed Up and Go (TUG) test.
Strengths
- Includes JH-FRAT labels for clinical fall risk assessment.
- Provides both 2D and 3D pose keypoints for multi-view analysis.
Limitations
- Row count is unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.
- Last update date is unknown; freshness unverified.
Provenance
- Collection Method
- Vision-based capture of the Timed Up and Go (TUG) test.