Design and Implementation of Real-time Pothole Detection using Convolutional Neural Network for IoT Smart Environment

Road is a transportation infrastructure that has a very important role in supporting the economic, social and culture as well as various other aspects of community life. Various community activities are affected by road conditions. Roads that are in good condition will provide comfort and facilitate economic activity in an area. However, in reality there are still many roads that are not in good condition, such as potholes. Various attempts have been made to detect potholes automatically, especially with the two-dimensional imaging method. In this paper, we propose real-time potholes detection using the Convolutional Neural Network (CNN) method based on the Edge Tensor Processing Unit (TPU) with the MobileNet SSD v2. Our system was implemented on Jetson Nano with several additional sensors such as a camera and GPS. The accuracy of the system is verified through experiments using the testbed.