MorFormer: Morphology-Aware Transformer for Generalized Pavement Crack Segmentation

Cracks are common on pavements. Accurate crack detection plays a vital role in pavement maintenance. However, cracks have rich and varied morphological features and fine edges, making this task challenging. Additionally, noise factors such as stains, scratches, and complex textures in the pavement background can easily be confused with cracks, increasing the risk of false prediction in the segmentation process. Therefore, we propose Background Morphology Learning (BML) to reconstruct morphological features of the pavement background noise, extract background morphological dissimilarity maps to suppress interference and reduce false alarms. In addition, we propose Crack Morphology-aware Attention (CMA), which adaptively learns the morphological shape of cracks and dynamically adjusts the shape of the attention receptive field to the topological features of the cracks. This significantly improves the completeness of segmentation. Our method mitigates the problems of false alarms and incomplete segmentation results in the crack segmentation task. Therefore, we propose a Morphology-Aware Transformer (MorFormer) that achieves state-of-the-art results on five public datasets. Moreover, we propose a large-scale cross-domain benchmark for crack segmentation, where MorFormer exhibits excellent domain generalization.