Research on Methods of Pavement Distress Detection using Convolutional Neural Network based on Highway Rapid Inspection Images

Aiming at the problem of intelligent detection of pavement distress based on highway rapid inspection images, this paper studies the intelligent detection technology of pavement distress based on Convolutional Neural Networks (CNN). Firstly, the methods of pavement distress detection based on Faster R-CNN, SSD and RetinaNet are compared and analyzed. Secondly, three variants of CNN models are investigated for pavement distress detection of highway rapid inspection images, including Faster R-CNN-PDD-HRII, SSD-PDD-HRII and RetinaNet-PDD-HRII. Finally, the comparative experiments were conducted using SEU-BH dataset, and the results showed that the average of Faster R-CNN-RSDD-HRII is superior to the other two methods, with an average accuracy of 94.88% and F1-Score of 90.29%.