Four Charles Darwin University (CDU) Master of Data Science students have developed an Artificial Intelligence (AI) model capable of detecting and classifying road signs with more than 90 per cent accuracy, demonstrating the potential for AI to improve road safety and infrastructure monitoring.
Students Cong Do Le, Khai Quang Thang, Van Phuc Vinh Ho and Buu Dang Phan built the model over a single semester as part of a collaborative project between CDU and national civil engineering provider Civiltech Solutions.
The team’s work involved training the model to accurately identify road signs under a range of challenging conditions including low light, poor weather and complex urban environments.
To achieve this, Civiltech Solutions provided videos of Darwin streets captured from a camera mounted on a bicycle, the university said in a news release.
From these, the students extracted around 60,000 images, later refining the dataset to approximately 8,000 high-quality frames to feed into the model for training and testing.
CDU Lecturer in Information Technology Dr Thuseethan Selvarajah, who supervised the project, said the collaboration demonstrated the university’s commitment to integrating real-world industry challenges into academic learning.
“Normally students are used to theoretical studies,” Dr Selvarajah said. “But they don’t know where and how to apply their knowledge and skills, so it’s important for us to have partners like Civiltech. These opportunities are directly linked with graduate outcomes.”
The students said the hands-on project was both a technical and personal learning experience. Ho, who has a background in IT, said the project opened his eyes to the practical applications of data science.
“At first, we had a lot of trouble, we had little knowledge about sign recognition,” he said. “We improved the model step by step to make it more accurate and faster, and we got expert advice from our lecturers and Civiltech which improved our approach to monitoring and better understanding the real-world applications.”
Thang, whose background is in business, said working closely with CDU professors, teammates and professionals from Civiltech was a key takeaway.
“We had to submit our project to the CDU IT Code Fair Research Competition, and this gave me a chance to speak in public. This is important to become a data analyst, because you must work with technology but also communicate with clients,” he said.
Civiltech Solutions has a history of working with CDU across multiple disciplines, and Founder and Chief Executive Leigh Carnall said the recent collaboration underscored the benefits of cross-sector knowledge sharing.
“This experience gave civil engineering exposure to AI, what it can do and to different ways of solving data problems,” Carnall said.
“With the data science students, it gives them a way of engaging with professionals to find out exactly what the problem is they’re wanting to solve, go through the process of what’s possible, what the outcomes are and the roadmap of how we could get there.”
He said such partnerships not only enhance student capability but also support local workforce development.
“This is a great story for the NT because it encourages CDU students to stay after studies are finished. To enable that, there needs to be an industry that offers careers for graduates to apply their skills in fulfilling, rewarding and interesting work within Northern Territory,” he said.
The AI model created during the semester is expected to serve as a foundation for future CDU student cohorts to further adapt and expand the technology’s applications.
Ho said the potential uses could include self-driving systems and real-time road sign recognition to assist in civil mapping and maintenance.
“Projects like this are a foundation for other students in the university to adapt and develop this technology,” he said.
