Automated crack segmentation on 3D asphalt surfaces with richer attention and hybrid pyramid structures

Automated pavement crack detection is crucial to supporting fine pavement maintenance and ensuring safety for road facilities. Due to the complex pavement condition and crack features, it is still a critical challenge in intelligent pavement surveys. This paper proposed a novel pixel-level pavement crack segmentation network, PCSNet, to provide a solution to this challenge. The network has richer attention and hybrid pyramid structures, which implement full-process crack feature fusion and enhancement. The richer attention module consists of cascaded self-attention and attention gate modules. It captures the crack spatial dependence information and prunes the feature response. The hybrid pyramid structures consist of a multistage convolutional pyramid module and a pyramid pooling module. It integrates contextual information at multiple receptive field scales to enhance the potential crack feature representation. The proposed structure enriches the crack details and optimises the scene parsing on the global geometry of the cracks. A sizeable 3D pavement crack dataset is built for training and testing. The proposed network exhibited the best performance, achieving F1-score, mean intersection of union, and mean pixel accuracy of 81.21%, 77.13%, and 87.17%, respectively. The network can reconstruct the complete crack geometry, preserve the crack edges well, and optimises the detection of shallow and complex cracks. The method exhibits superior and robust performance, facilitating accurate pavement technical condition assessment and maintenance decisions.

Automated summary

This study proposes a novel pixel-level pavement crack segmentation network, PCSNet, to address the challenge of crack detection in intelligent pavement surveys. The network integrates richer attention and hybrid pyramid structures, enhancing crack feature representation and scene parsing. By capturing crack spatial dependence information and integrating contextual information at multiple receptive field scales, the network achieves superior performance with F1-score, mean intersection of union, and mean pixel accuracy of 81.21%, 77.13%, and 87.17%, respectively. The method reconstructs complete crack geometry, preserves crack edges well, and optimizes the detection of shallow and complex cracks.