Pixel-wise crack defect segmentation with dual-encoder fusion network

Abstract

Automatic crack defect detection plays an important role in early road maintenance. However, the crack defect detection accuracy is seriously affected by some challenging factors, such as complex background, class imbalance issue, poor texture, etc. In this paper, a deep crack defect segmentation network with dual-path encoding and hierarchical fusion schemes, named DEHF-Net, is presented to accurately and effectively segment the crack defects generated in crack images. In order to capture rich feature information of crack defects, a dual-path encoder unit is built to extract the spatial information and context information from crack images simultaneously. On the basis, to strengthen the features extracted from two encoding paths, an attention fusion (AF) block and feature enhancement (FE) block are proposed for effective feature learning to achieve information complementarity of dual-branch encoding paths. Meanwhile, to alleviate the problem of semantic gaps arising from large information differences between the encoding path and decoding path, a residual refinement unit (RRU) is also introduced to enable effective refinement of edges and details. Finally, to make the segmentation results more significant on multi-scale cracks, a weighted hierarchical fusion (WHF) block is introduced in the decoding stage to fuse the shallow texture information with the deep semantic information more effectively. Experimental results show the proposed model has obtained an excellent performance comparison with advanced methods.