Using Deep Learning-Based Defect Detection and 3D Quantitative Assessment for Steel Deck Pavement Maintenance

Abstract

Efficient distress detection and identification analysis are of great significances for long-span steel bridge deck pavement maintenance. This paper proposes a pavement distress recognition method based on road quality detection equipment and deep learning. Firstly, the sub-block image is used as the processing unit, and the three-dimensional image is divided into fracture surface element and background surface element. A pavement crack recognition network (PDRNet) based on convolutional neural network is proposed, which is used for automatic recognition of pavement background element and pavement crack element. Then, considering the pixel-level neighborhood characteristics of cracks in 3D pavement images, the PDRNet model is used to detect and quantitatively evaluate pavement cracks, which combines the crack elevation detection method to extract the complete contour of cracks in the crack surface element. Finally, the distress database containing three-dimensional markers is integrated into the pavement maintenance management platform. Results show that the PDRNet proposed in this paper has high prediction accuracy on the verification set and shows good robustness to various distress, and the average accuracy is above 88%. The established spatial-temporal integration platform overcomes the communication bottleneck between different types of data, and is important to improve the maintenance management level and predict the long-term development of distress.