Smart scanning technology detects early signs of potholes

Smart scanning technology detects early signs of potholesInteresting work by a team led by Nottingham Trent University on making a mobile scanner that can detect early signs of potholes. It uses conventional cameras, 3D scanners and computer vision to detect ‘ravelling’. Moving this around at traffic speed mounted to a vehicle, and combining it with GPS and a suitable logging system, it could be used to improve road conditions.

Researchers are developing smart scanning technology using existing cameras to detect the early signs of potholes and determine their severity.

The technology, developed by a team led by Nottingham Trent University research fellow Dr Senthan Mathavan, scans roads for ravelling – the loss of aggregates from the asphalt which leads to potholes and cracks.

Ravelling - an early indication of potholes
Ravelling – an early indication of potholes – Source

Combined with 2D and 3D scanners on a pavement monitoring vehicle, a computer vision algorithm can examine the road with accuracy at traffic speed during day or night.

The system works by detecting different textures of the road to identify ravelling and distinguishes it from shadows and blemishes such as tire marks, oil spills and recent pothole repairs.

“It’s imperative for authorities across the world to be able to monitor road conditions efficiently and safely,” said Dr Mathavan, a research fellow of the School of Architecture, Design and the Built Environment.

“For the first time, academic research has addressed the issue of detecting ravelling in an automated way, which has led to the development of this novel software which can be used across the industry.”

The research was published today in Transportation Research Record, a leading academic journal for transportation infrastructure research. It also involves Dr Mujib Rahman of Brunel University, Martyn Stonecliffe-Jones of Dynatest UK Ltd, and Dr Khurram Kamal of the National University of Sciences and Technology in Pakistan.

During the research, the team found that the technology detected road surfaces correctly in all 900 images tested. It took approximately 0.65 seconds to 3D process the ravelling measurements, but it is believed that this could be reduced further.

potholeDr Rahman added: “Potholes, in their worst potential form, can create dangerous driving conditions and cause costly damage to vehicles.

“What this technology allows us to do is capture better quality information on road conditions, without disrupting the flow of traffic or incurring unnecessary costs.

“This could be a significant step forward in the way that potholes are managed, helping improve the timeliness and efficiency of repairs.”