Korean researchers develop AI-based pothole inspection tool

The system is designed to review primary pothole information detected by the pothole detection program operated by the Land Management Office. This is a mobile-based application used for detecting potholes.

However, due to limitations in device performance, high-specification programmes cannot run on mobile devices. This means that what is flagged as a pothole by the systems is often not so, and instead correlates with shadows, lane markings and tires – a mistake that the new system aims to address.

The solution developed by the KICT team aims to counter this tendency. Using AI tools, the researchers designed a system that can exclude objects other than potholes from the primary pothole information transmitted to the server, effectively selecting the real ones.

Once the training of the pothole filtering program is complete, the algorithm proceeds to inspect the primary pothole information, and then sends the verified pothole information to the road maintenance personnel of the Land Management Office every three hours.

“We anticipate that the newly developed system will reduce the processing time of emergency pothole restoration on roads,” said Dr Moon-Sup Lee, the lead researcher of the team. 

Potholes are a road damage phenomenon in which parts of the asphalt sink into bowl-like depressions. They occur when a significant amount of rainwater infiltrates the road surface, weakening the ground below and causing the asphalt pavement to collapse under the weight of passing vehicles.

In recent times, climate change has caused extreme weather events such as heavy rain and snow to occur more frequently. This, in turn, has increased the number of potholes present on roads, as well as the likelihood of road accidents. 

Apart from Korea, other countries are noticing an increase in the amount of potholes on their roads. In the UK, the RAC recently reported a 39 per cent surge in the number of drivers falling foul of potholes on British roads. The organisation estimated that drivers are now 1.6 times more likely to break down due to the repeated wear caused by potholes than they were 17 years ago, which is when it started collecting detailed breakdown data.

According to a report in March, more than £14bn in central government funding would be needed to fix the backlog of repairs needed on British roads. While half (51 per cent) of local roads are reported to be in good structural condition, the remaining 100,000 miles could continue to deteriorate to the point of needing to be rebuilt within the next 15 years, the report warned.