Automatic Extraction of Roads From Multisource Geospatial Data Using Fusion Attention Network and Regularization Algorithm

Abstract

Automatic extraction of roads from remote sensing imagery has numerous applications, such as urban planning and navigation. However, the quality of images is limited, and most existing road extraction methods suffer from discontinuity. Additionally, there remains a gap between pixel-based road segmentation and road vectorization. To address these challenges, we introduce a method that utilizes a multistage feature fusion attention network (MFFANet) and regularization algorithm to extract road surfaces, centerlines, edges, and intersections. MFFANet comprises three components. The complementary feature embedding module (CFEM) adaptively encodes remote sensing images, vehicle trajectories, and OpenStreetMap (OSM) points to capture specific modal features. The multistage feature fusion module (MFFM) is proposed to improve the completeness and connectivity of road extraction by integrating multisource geospatial features. The multilevel mask generation module (MMGM) enhances road segmentation results through a weighting mechanism that can simultaneously predict local road segments, road sections, and road network masks. Additionally, a novel joint loss function is introduced to balance local and global optimization. In the regularization stage, fused hierarchical masks generate road segments, with a skeleton refinement for centerlines and widths, followed by smooth segment reconstruction and extraction of edges and intersections. Experiments on different datasets demonstrate that our designed fusion attention network outperforms the latest road segmentation models; our regularization algorithm shows strong robustness and the comprehensive metrics of vectorized road line extraction exceeds 70%.