RMIT scientists use Street View to monitor road signs
A team of RMIT scientists have developed a fully automated system for monitoring street signs in need of replacement or repair using Google Street View images.
The system is trained using AI-based object detection techniques to identify and geolocate street signs by leveraging Google’s Street View API.
The prototype system, developed by a team led by RMIT Geospatial science Honours student Andrew Campbell and geospatial scientists Dr Chayn Sun and Dr Alan Both, was trained to detect ‘stop’ and ‘give way’ signs from the Street View images as a proof of concept.
Campbell said the system could be trained to detect many other signs and types of infrastructure, and can be scalable for use by local governments and traffic authorities.
“Councils have requirements to monitor this infrastructure but currently no cheap or efficient way to do so. 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 many cases, mandatory GPS location data in existing street sign databases was often inaccurate, sometimes by up to 10 metres. The prototype system has the potential to reduce this human error and automate the process of tracking signs.
Sun said local councils are already exploring the value of visual data through projects such as attaching cameras onto rubbish trucks to gather street footage.
“This imagery is critical for local governments in monitoring and managing assets and with the huge amount of geospatial applications flourishing, this information will only become more valuable,” Sun said.
“Ours is one of several early applications for this to meet a specific industry need but a whole lot more will emerge in coming years.”
Sun noted that information captured by council rubbish trucks and any other georeferenced road imagery could be fed into the system. This could provide more up-to-date visual data compared to Street View images, which could take some time to be updated.
The RMIT team is now working with local governments on heat intervention strategies by using Street View images to analyse street tree shade.
At the Australian Government Digital Awards, Geoscience Australia received the 'Outstanding...
The City of Newcastle's new 'Envirosensing' sensor and IoT network will be used to...
Mapillary is giving Logan City Council more up-to-date images of its road assets, enabling it to...