IMC Newsdesk

Cubic tackles Covid-19 transport problems in Melbourne

  • July 21, 2020
  • Steve Rogerson

California-based Cubic Transportation Systems is working with the University of Melbourne to tackle transport problems arising from Covid-19.
 
As a result of the global pandemic, many cities around the world are seeing increased levels of walking and cycling, creating challenges for urban centres that usually move people on public transport or in cars.
 
Melbourne, Sydney and Brisbane are now building cycle ways to accommodate increasing numbers of cyclists and pedestrians in the urban environment. Some of Melbourne’s bike routes have reported over 300 per cent more use, which is set to increase as more people return to work.
 
“With the huge additional influx of bikes, pedestrians and cars, there is a significant risk of more congestion and accidents at intersections,” said Chris Bax, vice president at Cubic Transportation Systems. “To protect cyclists and reduce congestion, cities must embrace technologies that integrate multiple sources of data to optimise efficiencies.”
 
Under Australia’s iMove cooperative research centre, Cubic is working with the University of Melbourne and several local government agencies to bring the improved detection needed at intersections to tackle current and future challenges, using the firm’s’ Gridsmart technology.
 
“The advanced detection system made possible through Gridsmart allows machine learning control strategies to consider all modes of transport, in particular vulnerable road users such as cyclists and pedestrians,” said Majid Sarvi from the University of Melbourne.
 
Gridsmart is a complete omnidirectional-imaging, real-time computer vision product, comprising hardware and software, that works with the traffic controller to actuate intersections for cars and bikes to provide intersection performance data. Its Smartmount Bell camera is being installed at strategic locations in the Australian Integrated Multimodal EcoSystem (Aimes) in the heart of Melbourne.
 
Gridsmart uses its fisheye Bell camera, along with real-time computer vision tracking and deep neural net classification, to track and discriminate bicyclists from other road users as they pass into and through intersections. The system provides improved safety for bicyclists while simultaneously improving intersection efficiency for multimodal traffic.
 
“The Gridsmart technology provides a 360-degree live view of all traffic at the intersection,” said Bax. “The system tracks cyclists as they travel through the intersection, providing the correct amount of green time for individuals based on their chosen path and speed. It also aims to produce improved road safety by detecting wrong way driving and increase situational awareness by providing live video from the intersection.”
 
To meet the hurdles resulting from changes in transport patterns, drivers will need to be better informed, buses will need to be expedited with signal prioritisation and crowded walkways must be dispersed safely. By using big data and artificial intelligence, Gridsmart technology can help address these needs.
 
“The Gridsmart camera is constantly learning, so it knows not to give priority to a turning vehicle when there’s just one car waiting, but instead considers how many cars are waiting before it decides to actually start to give right turns,” said Bax. “It also categorises vehicles, so we can distinguish between cyclists, cars, and trucks.”
 
The cameras are expected to be fully installed and go live in September this year.
 
“Our partnership with Cubic and the cutting-edge technologies they have developed and deployed in Aimes are helping to achieve our vision of delivering safer, cleaner and more sustainable transport outcomes,” said Sarvi.