Researchers aim to adapt ‘image pattern recognition’ software to enable automated systems for the analysis of road safety and road conditions.
CQUniversity Professor Brijesh Verma’s research project will be supported by a fresh Australian Research Council LINKAGE grant worth around $390 000 ($240 519 from ARC and $150 000 from the Queensland Department of Transport and Main Roads).
Professor Verma says the current manual systems used for road safety, not only in Australia but around the world, are inefficient and prone to many errors.
“The major challenges are to accurately detect, segment and classify all road objects and also calculate the distance between objects.” he says.
“A recent software breakthrough involving ‘deep learning’ has the ability to address such major challenges.”
Professor Verma says digital video road data is collected over every state road in Queensland through vehicle-mounted video and mobile laser scanning, and has the potential to provide a range of value-added products for safer roads.
“This project will develop deep learning-based neural network techniques which can learn and classify roadside objects so that video data can be automatically analysed, allowing the estimation of proximity of objects for road safety and rating.
“The final outcome will be new identification techniques and software which can be incorporated with road data collection systems.”
Professor Verma says the automatic analysis of digital video road data for road safety and conditions will reduce accidents, improve road asset management and make Australian roads much safer, with fewer fatalities.
“Automatic assessment of road safety and conditions is essential for improving road infrastructure and reducing fatalities on the roads,” he says.
Successful outcomes could find automated solutions for road safety rating required by national and international safety and risk assessment models, such as the Australian Road Assessment Program (AusRAP).
