More than 1.25 million lives are lost on roads around the world each year – a statistic a University of Queensland-led research team is aiming to tackle using engineering technology.

UQ civil engineer and researcher Professor Simon Washington said the Engineering and Technology project relied on video technology, deep learning, artificial intelligence and advanced econometrics to improve road safety.

“Using advanced video analytics technologies, we’re able to measure and detect interactions among road users that are reliable predictors of future crashes,” Professor Simon Washington said.

“This data can then help determine how roads can be improved, in order to prevent crashes.

“We estimate this technology has the potential to eliminate approximately 540 crashes in South East Queensland each year — equating to about $40 million in reduced crash-related costs.”

Professor Washington worked with Professor Tarek Sayed from The University of British Columbia and Associate Professor M.D. Haque from the Queensland University of Technology, bringing together more than 70 years of research experience.

The team developed a complex set of algorithms that can relate information about interactions among vehicles, pedestrians and cyclists, to crash risks.

These algorithms allow researchers to predict where and when crash risks are greatest.

“We’ve already implemented this technology in 20 cities in eight countries around the world, resulting in improvements to a number of intersections,” Professor Washington said

"We've also partnered with the Department of Transport and Main Roads to roll out a pilot of the technology locally."

Professor Washington said the project was part of a significant partnership between UQ and the state government in supporting innovation.

“This pilot project with Transport and Main Roads will help us to build on the knowledge gained from implementation of the technology in other cities,” he said.

Transport and Main Roads’ Director (Safer Roads) Simon Harrison said previously blackspots were mainly identified through reported crashes, but now there is a greater focus on proactive methods.

"This research into video analytics has the potential to improve the way we identify safety issues before a crash trend develops," Mr Harrison said.

"As we work towards Vision Zero — zero road deaths and serious injuries — this intervention could take us one step closer to implementing engineering solutions before anybody gets seriously hurt."

Media: Professor Simon Washington, s.washington@uq.edu.au, +61 451 951 300; EAIT Communications, Genevieve Worrell, g.worrell@uq.edu.au, +61 408 432 213.