Keeping Their Eyes on the Prize in AI

In the next decade, the capacity of computer vision systems is projected to massively broaden, opening up a new realm of possibilities.

 |  Transcript [PDF]
Share

Artificial intelligence (AI) has tremendous potential, and we may soon unlock pathways for technologies with more human-like versatility by learning about what makes us tick. Vision scientist James Elder works at the interface of human and computer intelligence, and this interdisciplinary work is exactly the type of research fostered by the Vision: Science to Applications (VISTA) program at York University.

“We really are living through an extraordinary time, where we’re learning from the brain how to design truly intelligent machine systems,” says Elder.

“The big idea that kind of keeps me dreaming is how we go from our current state in AI, which is one where we can build applications for very specific purposes, to a more general kind of intelligence that we see with humans, and achieving that goal is going to involve a much better understanding of ourselves.”

Currently, computer vision systems have very narrow and defined limits, says Elder. For instance, a program might excel at recognizing faces or objects, but programs that can replicate general human visual reasoning aren’t possible yet. It’s a boundary that Elder and other researchers continue to push, and he believes that in the next 5-10 years that broader applications will become possible.

One example use case is intelligent systems to assist with road safety.

“We’re not going to really see autonomous driving for many years, but what I do hope we’ll see are computer vision systems that are embedded in our streets that keep people safer by recognizing hazards,” says Elder.

Take, for example, an elderly pedestrian crossing the street. If a car was on a potential collision course, cameras on the road or in the vehicle could be paired with computer vision to sense that hazard as it emerges. Layers of signalling could then be relayed to give an early alert to the pedestrian and the driver in hopes of preventing an accident. This is the type of technology that is achievable in the next decade.

Every day, researchers are learning more about how the human brain works, and that knowledge is helping them build smarter technologies. It’s an exciting time to see what will be possible in a few short years.

‹ Previous post
Next post ›

James Elder is a Professor and York Research Chair in Human and Computer Vision at York University. He is jointly appointed to the Department of Psychology and the Department of Electrical Engineering & Computer Science at York and is a member of York’s Centre for Vision Research (CVR) and Vision: Science to Applications (VISTA) program. Elder is also Director of the NSERC CREATE Training Program in Data Analytics & Visualization (NSERC CREATE DAV) and Principal Investigator of the Intelligent Systems for Sustainable Urban Mobility (ISSUM) project. His research seeks to improve machine vision systems through a better understanding of visual processing in biological systems. Elder’s current research is focused on natural scene statistics, perceptual organization, contour processing, shape perception, single-view 3D reconstruction, attentive vision systems and machine vision systems for dynamic 3D urban awareness.


Research2Reality is a groundbreaking initiative that shines a spotlight on world-class scientists engaged in innovative and leading edge research in Canada. Our video series is continually updated to celebrate the success of researchers who are establishing the new frontiers of science and to share the impact of their discoveries with the public.