A recent R01 award from the National Eye Institute (NEI) and National Institutes of Health (NIH) enables a collaborative, multidisciplinary team of researchers, low vision specialists, engineers, and computer scientists from the University of Wisconsin—Madison to develop artificial intelligence-assisted software to help visually impaired individuals accomplish their day-to-day activities.
The project entitled “AI-Assisted Vision: Scene-Aware Augmented Reality Systems to Support Low Vision People in Activities of Daily Living” aims to further understanding of the challenges and needs of individuals with diverse visual abilities and to design and build intelligent interactive systems to assist them.
“We will engage low vision professionals as well as patients in developing such technologies to ensure practicality and usefulness,” explained Sanbrita Mondal, OD, Chief of Vision Rehabilitation Services in the UW Department of Ophthalmology and Visual Sciences. “To date, most low vision aids have been developed by sighted researchers. We want to ensure we are developing software with the input of low vision users to increase technology usability and acceptance. “
Dr. Mondal plays a key role in the grant by helping develop workshops, providing input to technology development, and recruiting stakeholders and community participants. Yuhang Zhao, PhD, an Assistant Professor in the Department of Computer Sciences, serves as principal investigator on the project.
“Low vision is a complex and pervasive condition that affects millions of people in the world,” said Zhao. “However, it receives little attention in the technology literature. It is important for us to deeply understand the unique experiences and needs of low vision people and create intelligent assistive technologies that are adaptive to their contexts and preferences. “
Researchers will tackle the challenges faced by people with low vision in complex activities of daily living, such as cooking or safely navigating a crowded room or street.
“These activities involve constant motion and object interactions, and current low vision aids such as magnification devices distort a user’s natural vision or diminish important details for these activities, and thus cannot effectively work in these conditions,” said Dr. Zhao.
A portion of the $1.2 million grant will support an annual workshop that brings together low vision rehabilitation professionals and patients. The inaugural AI-Assisted Vision Mini-Workshop: Opportunities and Challenges of Intelligent Assistive Technologies for Blind and Low Vision Individuals event was held in December 2024 at Union South on the UW—Madison campus.
“It was a great day of learning about the technology research going on at the University of Wisconsin-Madison. There was excellent discourse on technology adaptations low vision individuals and specialists desire to see developed,” said Dr. Mondal “We had the opportunity to test and use the technology developed in Dr. Zhao’s lab.”
Researchers from the University of Washington in Seattle, the University of Texas-Dallas, and Purdue University in Indiana collaborated on the event.
“We plan to hold this workshop annually,” Dr. Mondal said, “to update low vision professionals and patients on the work we are doing, as well as obtain their feedback and suggestions to aid us in developing useful and acceptable solutions for individuals with low vision and blindness.”
*****
Photos from AI-Assisted Vision Mini-Workshop: Opportunities and Challenges of Intelligent Assistive Technologies for Blind and Low Vision Individuals
