Canadian university prof wins grant for machine vision technology research

Graham Taylor, an engineering professor at the University of Guelph will share $550,000 in federal funding for a three-year international research project intended to help make machine vision technology more discerning.

Utilizing a new grant from the Natural Sciences and Engineering Research Council (NSERC), Taylor hopes to help computers “see” better.

The goal of NSERC’s strategic partner grants is to increase research in targeted areas that strongly enhances Canada’s economy within a 10 year time frame. Research and training under these grants are conducted through a partnership between academic researchers and industry or government organizations.

The objective of the grant is to generate new knowledge or technology that has the strong potential to strengthen Canada’s industrial base, generate wealth, and create employment. Machine vision technology has been targeted as area with enhanced potential.

While computer vision systems are getting better at figuring out whether someone is running, jumping, waving or eating, they still have trouble making sense of complex situations and images, including deciphering body language and facial expressions.

With digital cameras recording more footage from building monitoring systems to YouTube videos, Taylor says that we need smarter computers to make sense of massive amounts of image data. “We have to rely on computers to watch videos faster and draw inferences,” said Taylor.

By way of the grant, Taylor will work with an international team to develop deep learning and structured models to help machines build accurate representations of what they see and to make sense of images in a manner similar to how humans learn about their surroundings.

Taylor’s partners on the machine vision technology project include researchers at INSA-Lyon and Pierre and Marie Curie University in France, and Greg Mori, a researcher at Simon Fraser University.

The project’s industrial partners include a company designing better ways to search through massive amounts of video camera footage. Another company makes interactive kiosk displays that detect users’ gestures rather than input on a keyboard or touch screen.

Article Topics

biometrics  |  Canada  |  computer vision  |  facial recognition  |  image recognition  |  machine learning  |  research and development  |  video surveillance