Hierarchical Feature Matching via Structure-Semantic Separation for Road Extraction

Road information derived from remote sensing images is extensively utilized across various fields. Traditionally, road extraction methods relied predominantly on manually designed features, and yet these have progressively evolved toward deep learning-based approaches. Despite robust performances by existing methodologies, extracting road regions from high-resolution remote sensing images still presents significant challenges: 1) the narrow and continuous morphological characteristics of roads require comprehensive contextual understanding from a global perspective and 2) roads are often obscured by vegetation, shadows, and buildings, causing visual discontinuities and a lack of local correlation. To address these issues, this article proposes a hierarchical feature matching network for separated features of structure-semantic. It is mainly composed of the structure-semantic features enhancement pipeline (SFEP) with two parallel modules combined with a fusion module [separated features matching fusion (SFMF)]. This separated architecture allows each pattern of features to maintain distinct representations without mutual interference, improving interregional correlation. Meanwhile, the SFMF is used to match and fuse the diverse patterns of features for the corresponding regions. In addition, a novel connected region (CR) loss is proposed to leverage the inherent topological connectivity of roads to direct the attention of the model to truncated regions. Experiments are conducted on the DeepGlobe, CITY-OSM, and CHN6-CUG datasets, and the results show that our method significantly outperforms existing networks on most evaluation metrics, highlighting its effectiveness in addressing complex road extraction challenges.