Researchers develop an AI-based automatic pothole detection system that can be installed on the windshield of a vehicle to detect potholes on the road surface in real-time.
Potholes, in the rainy season, can cause many problems for drivers and vehicles. They can damage cars and may even lead to life-threatening accidents. If a vehicle passes over a pothole at high speed without noticing it, the vehicle may break away from the driving lane, and can threaten the driver’s life.
Researchers from the Korea Institute of Civil Engineering and Building Technology (KICT) have developed an Artificial Intelligence (AI) based automatic pothole detection system that can be installed on the windshield of a vehicle to detect potholes on the road surface in real-time.
Real-time data by cars about potholes can help the road surface management team to take action. The detection can involve vibration-, laser scanning-, and image recognition-based technologies. A research team at KICT led by Dr. Seungki Ryu developed a system that detects potholes in real-time by photographing the road surface while driving with a vision sensor installed on the windshield of a vehicle. The damaged surface on the road is segment using an encoder-decoder network based on the FCN (fully convolutional neural network) architecture.
The problem with image-based detection is that the pixels that contain information change in the external environment. It may be challenging to identify the defect on the surface as the brightness of the road surface changes over time. To overcome this challenge, the researchers developed a new CNN (convolutional neural network) model for image preprocessing for increased robustness.
Dr. Ryu said, “It is essential to maintain road facilities in good condition in the coming era of autonomous vehicles. This AI-based technology will make effective road surface management much easier.”
The work has been described in the journal Electronics.
