December 1, 2010
Title: Computer Vision Technologies to Promote Independent Living for the Elderly
Abstract: Improved medical care and the aging of the baby boomer generation have resulted in the increasing size and proportion of the world's elderly population. With the greying population, the prevalence of health issues associated with old age is also growing. The resulting cognitive or physical impairments often lead to the loss of independence among the elderly. Given a choice, many older adults prefer to live independently as long as possible. Such aging-in-place reduces healthcare costs in providing infrastructure and care while keeping the elderly happy, independent, and socially connected. This talk will be on intelligent assistive technologies that aim at enabling the elderly to live safely in their place of choice for as long as possible. In particular, the talk will focus on employing computer vision and machine learning techniques in two fronts: the first is the automatic detection of dangerous situations such as falls and emergency response. The second is video analysis methods to automate the process of product design usability assessment and to facilitate improved environmental design.
Biography: Babak Taati is a research associate in the Intelligent Assistive Technology and Systems Lab at the University of Toronto and the Toronto Rehabilitation Institute, where he develops and applies computer vision and machine learning algorithms in assistive and rehabilitation technology applications. Prior to joining UofT/TRI, he worked on 3D urban reconstruction from aerial images as lead computer vision scientist at Feeling Software. He completed his Ph.D. on object recognition and pose acquisition in range data at Queen's University and in collaboration with MDA Space Missions and the Canadian Space Agency. Results from his PhD research were used in a real-time pose acquisition and satellite tracking prototype developed at MDA Space Missions.