SDUNet: Road extraction via spatial enhanced and densely connected UNet. (June 2022)

• Record Type: Journal Article
• Authors: Yang, Mengxing; Yuan, Yuan; Liu, Ganchao
• Is Part Of: Pattern recognition. Volume 126(2022)
• Publication Date: 2022-06
• Subjects: Road extraction -- Image segmentation -- Remote sensing imagery -- Spatial topology; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108549
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a network SDUNet, which combines the multi-level features of the road network and global prior information. A structure preserving model is proposed to enhance feature learning about the structure prior of the road surface. Experimental results show that our approach achieves state-of-the-art performance compared with previous methods. Graphical abstract: Abstract: Extracting road maps from high-resolution optical remote sensing images has received much attention recently, especially with the rapid development of deep learning methods. However, most of these CNN based approaches simply focused on multi-scale encoder architectures or multiple branches in neural networks, and ignored some inherent characteristics of the road surface. In this paper, we design a novel network for road extraction based on spatial enhanced and densely connected UNet, called SDUNet. SDUNet aggregates both the multi-level features and global prior information of road networks by combining the strengths of spatial CNN-based segmentation and densely connected blocks. To enhance the feature learning about prior information of road surface, a structure preserving model is designed to explore the continuous clues in the spatial level. Experimental results on two benchmark datasets show that the proposed method achieves the state-of-the-art performance, compared with previous approaches for road extraction. Code will be made available on https://github.com/MrStrangerYang/SDUNet .