Sallie Lamb

[Fees plus a stipend of £21,805 per annum for 2026/7.] PhD Studentship at the University of Exeter: Computer vision to predict falls from everyday movement in older adults . This project addresses an important clinical problem: falls are a major cause of injury-related hospital admission and death among older adults, yet current risk assessment methods are limited because they usually rely on brief one-off clinical tests. The project will use real-world-inspired movement data collected in the STEPPING OUT Home Scene, a simulated home environment at the University’s VSimulators facility, where older adults perform everyday actions such as standing up, sitting down, turning, moving around furniture, opening doors, changing surfaces, and responding to slips and trips. Multi-camera video, motion capture, and wearable sensors are used to capture movement, while participants’ falls and clinical histories are known. The PhD will investigate whether a simple camera can detect stability and movement-quality markers that are visible to experienced clinicians. The research aims are to: derive measures from markerless pose estimation and validate them against motion capture; identify movement patterns that distinguish people who fall from those who do not, including near-falls and moments before loss of balance; test how well these measures predict falls and how early change can be detected; and adapt the methods for low-cost devices in homes, care homes, and hospitals, including on-device processing. The student will work with computer vision, deep learning for movement sequences, self-supervised learning, and interpretable machine learning, with an emphasis on methods that clinicians can understand and act upon. Expected outputs include a validated analysis pipeline, open benchmarks for stability assessment from video, evidence on the predictive value of ordinary video for falls risk, and a tested low-cost prototype. The studentship provides funding of fees plus a stipend of £21,805 per annum for 2026/7. The advertised deadline is 08 Dec 2026. The project offers training across computer vision, data science, biomechanics, and clinical falls research within a supportive supervisory environment.