James Coughlan

James Coughlan received his B.A. in physics at Harvard University in 1990 and completed his Ph.D. in physics there in 1998. He is currently a Senior Scientist at The Smith-Kettlewell Eye Research Institute in San Francisco, California. His main research focus is the application of computer vision to assistive technology for blind and visually impaired persons, including systems to provide guidance at traffic intersections, find and read signs and other textual information, and detect terrain hazards for persons with combined vision and mobility impairments. He is also interested in probabilistic methods in computer and human vision, particularly the use of graphical models and belief propagation for visual search, segmentation and 3D stereo.

Computer vision is an emerging technology that seems ideally suited to complement the vision loss experienced by the rising number of persons with blindness or visual impairment, whose vision limitations create many barriers to full participation in many activities of daily life. Indeed, as computer vision algorithms are able to solve an increasingly wide range of visual tasks, and the amount of computing power available in portable devices such as smartphones grows, it is becoming possible to create a variety of practical computer vision-based aids for blindness and visual impairment. Despite the promise of computer vision, however, it is a relatively “brittle” technology that functions reliably only in proscribed domains. I will discuss the limitations of computer vision and the need for researchers to carefully match its capabilities to the specific needs of blind and visually impaired persons by focusing on solving suitable problems with appropriate hardware and software. Finally, I will discuss other technologies such as crowdsourcing and sensors that can complement and augment computer vision, which promise to enable truly robust assistive technology for blind and visually impaired persons.