Scientists at the Royal Melbourne Institute of Technology (RMIT) have developed a proof-of-concept program that can monitor the condition of street signs using Google Street View images.
The program uses artificial intelligence (AI) to identify street signs from the Google images to determine whether they need to be replaced. It has been trained to see "stop" and "give way" signs, with RMIT saying the program could be trained to identify other inputs for use by local governments and traffic authorities as well.
According to RMIT, authorities spend large amounts of time and money monitoring and recording the geo-location of traffic infrastructure manually, a task which also exposes workers to unnecessary traffic risks.
See also: RMIT creates bird-like drone with flappable wings
"Councils have requirements to monitor this infrastructure but currently no cheap or efficient way to do so," study lead author and RMIT University Geospatial Science honours student, Andrew Campbell, said.
"By using free and open source tools, we've now developed a fully automated system for doing that job, and doing it more accurately."
In the results of the program's trial, the program detected signs at around 96% accuracy, identified their type at near 98% accuracy, and could record their precise geo-location from the 2D images.
In comparison to the proof of concept, the team of scientists found that mandatory GPS location data in existing street sign databases were often inaccurate by around 10 metres.
"Tracking these signs manually by people who may not be trained geoscientists introduces human error into the database. Our system, once set up, can be used by any spatial analyst -- you just tell the system which area you want to monitor and it looks after it for you," Campbell added.
The team is currently working with local governments on heat intervention strategies using Google Street View images to analyse street tree shade.
The Commonwealth Scientific and Industrial Research Organisation's (CSIRO) Data61 has also been working on improving the management of Australia's road infrastructure, having partnered with Transport for New South Wales (TfNSW) in February to create a program to improve the efficiency and effectiveness of the state's transport systems.
Dr Chen Cai, leader of the Advanced Data Analytics in Transport (ADAIT) group at Data61 touted the program as being able to analyse "automated end-to-end, multi-modal journey planning for operators and passengers".
Cai also said at the time that the University of New South Wales has been exploring trials of connected devices on heavy vehicles, passing messages between traffic signals to trucks to tell them when the signal is going to turn green, so they can prepare for incoming traffic without stopping too early.
"In the future, we should see a larger and greater scale application and adoption of these technologies," he added.