DUCTNet: An Effective Road Crack Segmentation Method in UAV Remote Sensing Images Under Complex Scenes

Road crack detection in complex scenarios is challenged by vehicles, traffic facilities, road printed signs and fine cracks. In order to better solve these problems, a novel dense nested depth U-shaped structure for crack image segmentation network named DUCTNet is proposed. Firstly, a depth dense nested structure is designed by combining the superior performance of the Unet $++$ dense nested structure and the deep nested structure of U2Net. This structure improves the ability of the model to extract crack features in depth. Second, a novel deep competitive fusion feature extraction block is proposed. It improves the feature dissimilarity between the cracks and the background by competitive fusion. Then, a novel high-density feature fusion attention mechanism is proposed. This method enhances the contextual and sensitive information of cracks both horizontally and vertically by increasing the feature density. Finally, DUCTNet achieves the best results in comparison tests with eight state-of-the-art specialized crack segmentation networks in both self-built datasets and four public datasets. In addition, DUCTNet achieves excellent results in real road tests, which proves that DUCTNet can provide engineers and technicians with a better means of detecting road cracks.