XR‑Embedded Marker-less Gait Analysis for Clinical Use

Marker-less motion capture and extended reality (XR) technologies show strong potential to make gait analysis more accessible beyond specialist biomechanics laboratories. However, most existing validation studies are conducted in non‑immersive conditions and do not integrate gold‑standard kinetic and plantar‑pressure measurements. This creates a critical gap in clinical confidence when gait is assessed within AR or VR environments. This PhD will evaluate whether gait data captured using marker-less motion capture within XR can achieve clinically acceptable accuracy and reliability compared with laboratory reference systems. The candidate will conduct systematic validation studies using THEIA3D marker-less capture, Kistler force plates, the Zeno instrumented walkway, and PEDAR in‑shoe pressure sensors, under real‑world, mixed‑reality, and fully immersive conditions. Advanced statistical and calibration models will quantify measurement error, identify sources of XR‑specific bias, and establish correction thresholds for clinical use. Outcomes will include validated accuracy benchmarks, reliability metrics, and practical guidance defining when XR‑embedded gait assessment can be used confidently in research and clinical practice. The project will directly enable scalable, lower‑cost gait analysis for clinics, community services, and tele‑rehabilitation, supporting wider access to objective movement assessment.