Putting the eye in advertising

A device that measures eye movements could provide an affordable way to track the effectiveness of advertisements by measuring how many people look at advertising hoardings and screens.

Called eyebox2, the portable device was developed at Queen’s University, Canada. It uses a camera that monitors eye movements in real time and automatically detects when a person is looking at it from up to 10m away, without calibration. Until now, such eye-trackers have been ineffective beyond 60cm as they required people to remain stationary, needed personalised calibration to function, and cost more than $25,000. The new walk-up-and-use eye is available at a fraction of that cost.

‘This camera mimics eye contact perception in humans, allowing us to pinpoint quite accurately what plasma screen or product shelf people are looking at,’ said Dr Roel Vertegaal, director of the Human Media Laboratory at Queen’s and inventor of the technology.

While the impact of internet ads can be measured by the number of hits on a web site, it is much harder to assess the effectiveness of plasma screens that target people in shopping centres, restaurants and other public places. The Queen’s invention gives advertisers a tool to accurately measure how much attention something receives, whether on a plasma panel, a billboard, or as the result of its placement on a supermarket shelf.

’We’ve been striving for the last 15 years to make eye tracking a mass input device as useful and convenient as a mouse,’ Vertegaal said. ‘Now we have a growth market in advertising, and a product that’s small enough, cheap enough, and able to work at a much longer distance, and in walk-up-and-use scenarios. I think it represents a real breakthrough that will later on help people work better with computers in ways currently that are unthinkable.’

Developed from their research into Attentive User Interfaces, the technologies reflect a novel approach to human-computer interactions. The focus of the research is on making everyday devices more attentive to their users by ‘sensing’ when it is appropriate to interact with them. Future potential uses include attentive computers, cellphones and household appliances.