Smart Hallway logo
Smart Hallway3D movement analysis in clinical spaces

Literature and validation

Smart Hallway is an evidence based approach to make 3D movement assessment accessible and efficient. This page summarizes relevant literature and publicaiton related to the Smart Hallway concept.

Featured Smart Hallway study

The first publication on the Smart Hallway outlined the technical approach and application methods to provide useful gait outcome measures.

McGuirk CJC, Baddour N, Lemaire ED. Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway. Computation. 2021;9(12):130.

2 participants 4 synchronized cameras 60 fps OpenPose BODY25 Stride parameters

Key points

  • Smart Hallway was designed as an accessible, markerless gait analysis approach close to the point of patient contact.
  • The system integrates four ceiling-mounted cameras and automated 3D processing.
  • Small stride-parameter differences relative to manual reference measures.
  • The camera placements and workflow are supported by the research.

Related Research

  • Markerless camera-based 3D motion capture systems provide a valid, reliable, and practical alternative to marker-based systems for gait analysis, particularly for spatiotemporal parameters, though ankle kinematic accuracy was lower.
    • Scataglini S, et al. Accuracy, Validity, and Reliability of Markerless Camera-Based 3D Motion Capture Systems versus Marker-Based 3D Motion Capture Systems in Gait Analysis: A Systematic Review and Meta-Analysis. Sensors. 2024.
  • Stride parameters calculated from OpenPose keypoints are similar to results using 3D motion analysis. Joint angles were within 4 deg for hip, 5.6 deg for knee, and 7.5 deg for ankle.
    • Stenum J, Rossi C, Roemmich RT. Two-dimensional video-based analysis of human gait using pose estimation. PLOS Computational Biology. 2021.
  • OpenPose, using videos recorded from frontal or sagittal views, works for adults without gait impairment, persons post-stroke, and persons with Parkinson’s disease via comparison to ground-truth 3D motion capture; clinically relevant, condition-specific gait parameters can be provided; and within-participant changes in gait can be measured.
    • Stenum J, Hsu MM, Pantelyat AY, Roemmich RT. Clinical gait analysis using video-based pose estimation: multiple perspectives, clinical populations, and measuring change. PLOS Digital Health. 2024.

Reference list

McGuirk CJC, Baddour N, Lemaire ED. Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway. Computation. 2021;9(12):130.
Sampel K, Lemaire ED, Baddour N, Cikajlo I, Kuret Z, Burger H. Transtibial Amputee Stride Parameter Analysis using a Smart Hallway.
McGuirk C. A multi-view video based deep learning approach for human movement analysis (Masters dissertation, Université d'Ottawa/University of Ottawa).
Scataglini S, et al. Accuracy, Validity, and Reliability of Markerless Camera-Based 3D Motion Capture Systems versus Marker-Based 3D Motion Capture Systems in Gait Analysis: A Systematic Review and Meta-Analysis. Sensors. 2024.
D’Antonio E, et al. Validation of a 3D Markerless System for Gait Analysis Based on OpenPose and Two RGB Webcams. IEEE Sensors Journal. 2021.
Stenum J, Rossi C, Roemmich RT. Two-dimensional video-based analysis of human gait using pose estimation. PLOS Computational Biology. 2021.
Stenum J, Hsu MM, Pantelyat AY, Roemmich RT. Clinical gait analysis using video-based pose estimation: multiple perspectives, clinical populations, and measuring change. PLOS Digital Health. 2024.