Pavement crack detection based on transformer network

Accurate pavement surface crack detection is essential for pavement assessment and maintenance. This study aims to improve pavement crack detection under noisy conditions. A novel model named Crack Transformer (CT), which unifies Swin Transformer as the encoder and the decoder with all multi-layer perception (MLP) layers, is proposed for the automatic detection of long and complicated pavement cracks. Based on a comprehensive investigation of training performance metrics and visualization results on three public datasets, the proposed CT model indicates enhanced performance. Experimental results prove the effectiveness and robustness of the Transformer-based network on accurate pavement crack detection. This study shows the feasibility of using a Transformer-based network for automatic robust pavement crack detection under noisy conditions. • A novel approach for automatic pavement crack inspection based on transformer network is proposed. • The proposed CT model can model the long-range pavement crack pixels with high accuracy and efficiency. • A new pavement crack image dataset named CrackSC is established and released to public.