Real-Time Monitoring of Road Networks for Pavement Damage Detection Based on Preprocessing and Neural Networks

Abstract

This paper presents a novel multi-initialization model for recognizing road surface damage, e.g. potholes and cracks, on video using convolutional neural networks (CNNs) in real-time for fast damage recognition. The model is trained by the latest Road Damage Detection dataset, which includes four types of road damage. In addition, the CNN model is updated using pseudo-labeled images from semi-learned methods to improve the performance of the pavement damage detection technique. This study describes the use of the YOLO architecture and optimizes it according to the selected parameters, demonstrating high efficiency and accuracy. The results obtained can enhance the safety and efficiency of road pavement and, hence, its traffic quality and contribute to decision-making for the maintenance and restoration of road infrastructure.

Keywords

• pavement
• damage detection
• convolutional neural network
• YOLO architecture
• machine learning
• classification