Automated Concrete Pavement Slab Joint Detection Using Deep Learning and 3D Pavement Surface Images

The 3D pavement surface images provide a great opportunity for transportation agencies to digitally and effectively assess jointed plain concrete pavement (JPCP) conditions. An automated and accurate JPCP slab joint detection algorithm, which can support slab separation and faulting evaluation, is a critical prerequisite for applying 3D pavement images on JPCP condition assessments. However, there is no existing study on automated slab joint detection except for commercial software, and the detected joints of the software require massive manual revisions due to insufficient accuracy. In this study, a novel slab joint detection algorithm is proposed, which leverages the power of deep learning to achieve accurate slab joint detection on 3D pavement images. The proposed algorithm consists of a convolutional neural network-based joint segmentation model and a joint coordinates extractor. The joint segmentation model is trained to generate pixel-wise joint segmentation masks from the pavement images, which provide preliminary localization information of the slab joints. Then, with the joint segmentation mask, the joint coordinate extractor is designed to eliminate the false positive predictions and accurately extract the joint coordinates. The proposed algorithm is evaluated on large-scale 3D pavement images collected from multiple interstate highways in the state of Georgia with diverse conditions. In the performance evaluation, the proposed algorithm achieved the highest F1 score of 0.956, which largely outperformed the commercial software with a 10% improvement. The evaluation results demonstrate the effectiveness of the proposed algorithm, which can further support effective and efficient assessments of JPCP conditions.