Enhanced pixel-level crack detection using Att-SegCrack: an improved CNN with feature fusion and large receptive field

Deep convolutional neural networks have demonstrated significant advancements in pavement crack detection. Nevertheless, challenges persist in achieving satisfactory performance due to discontinuous crack edges and low background contrast. This paper presents Att-SegCrack, an enhanced encoder-decoder network that addresses these limitations through three key components. First, a simple yet effective feature fusion scheme restores crack details by bilinearly up-sampling encoder features and integrating them with outputs from the penultimate decoder layer, which subsequently serves as input to the final decoding layer. Second, dilated convolutions expand the receptive field to capture comprehensive contextual information for complete crack profiles. Third, the convolutional block attention module enhances crack-background differentiation in low-level features. Evaluations on two benchmark datasets (Crack500 and DeepCrack) demonstrate that our method outperforms other state-of-the-art methods in crack detection performance.