Monocular video enables gait analysis for spinal cord injury patients
Monocular markerless biomechanics for clinically interpretable gait assessment in spinal cord injury
Computer Vision and Pattern Recognition
Summary
Gait analysis helps doctors understand how people with spinal cord injuries walk, but it usually needs special cameras and sensors that not many clinics have. The authors created a dataset from videos and sensors capturing 239 patients walking and developed a way to use just one simple video to measure walking movements and forces accurately. Their method matches traditional measurements closely and helps identify different walking patterns related to how independent a person is. This approach could make gait analysis easier and more available in clinics without expensive equipment.
What this means in practice
- •For rehabilitation clinics: Use monocular video-based gait assessment to evaluate walking mechanics in spinal cord injury patients without needing motion capture systems or force plates.
- •For physical therapy software developers: Integrate monocular video analysis into rehabilitation software for scalable and low-cost biomechanical assessment tools tailored to neurological patients.$Commercial implications: Enables development of affordable gait analysis products for clinics lacking specialized motion capture hardware.
Authors
Shreyasvi Natraj, Mathieu Ruepp, Yanke Li, Robert Riener, Inge Eriks-Hoogland, Diego Paez-Granados
Abstract
Three-dimensional gait analysis guides rehabilitation after spinal cord injury but depends on marker-based motion capture and force plates, which few clinics have. Monocular markerless pipelines have been established in fewer healthy adult cohorts but not in neurological cohorts. We present the SCAI SCI Gait dataset, comprising 239 adult individuals with spinal cord injury with synchronized video, motion capture, and force-plate measurements, we fitted a parametric body mesh to a single sagittal-view video, driving an anthropometrically scaled OpenSim model via virtual markers. Markerless lower-body kinematics showed state-of-the-art agreement with motion-capture measurements (r = 0.68-0.90, p < 0.001, and RMSE = 4.18-6.49 degrees), and accurate kinematics-based predicted ground-reaction forces closely matched those measured by force plates (r = 0.85-0.87, p < 0.001, and RMSE = 2.13-2.19 Newton per kg). Furthermore, conditional-dependence graph analysis with Markov blankets revealed that waveform components were conditionally associated with functional independence, and speed-stratified clustering revealed distinct mechanical strategies among individuals walking at similar speeds. These findings establish the use of monocular video as a scalable approach for clinically meaningful biomechanical assessment and data-driven phenotyping in patients with spinal cord injury. Github: https://github.com/SCAI-Lab/SCAI-SCI-Gait