My research focuses on the application of computer vision and machine learning techniques to real-world rehabilitation and assistive technology challenges and to health and safety monitoring. Examples include:
- ambient monitoring of gait in long-term care facilities to automatically identify residents at a high risk of falling;
- ambient monitoring of facial expressions to automatically identify expressions of pain in older adults with dementia who might not be able to communicate their pain;
- automated vision-based assessment of orofacial function in individuals with neurological a movement disorder;
- non-contact monitoring of sleep to diagnose breathing disorders during sleep;
- real-time upper-limb motion assessment during post-stroke rehabilitation therapy; and
- analysis of gait and joint movements to asses joint hypermobility or to monitor the rehabilitation process in the home.
A major focus of my research is to move away from the laboratory and contrived situations towards the development and validation of computer vision algorithms and systems that work reliably in natural settings, such as in the home or in long-term care facilities. My research is at the intersection of technical and clinical areas. I receive funding from a variety of agencies and foundations (e.g. NSERC, CIHR, AGE-WELL, Alzheimer’s Association) as well as through partnership with companies.
Dr. Taati is a Senior Scientist at KITE and also serves as the Lead of the KITE Aging Team. He holds an Associate Professor (status only) appointment in the Department of Computer Science and the Institute of Biomedical Engineering at the University of Toronto.
- Associate Professor (status only), Department of Computer Science, University of Toronto
- Faculty Affiliate, Institute of Biomedical Engineering, University of Toronto
- Faculty Affiliate, Vector Institute, University of Toronto
- Faculty Member, Rehabilitation Sciences Institute, University of Toronto