Semi-automatic Extraction of Rural Roads From High-Resolution Remote Sensing Images Based on a Multifeature Combination

Abstract

Roads play a vital role in rural economic development. However, rural roads feature irregular curvature changes, are narrow, and are built using diverse construction materials, which renders the analysis of road geometric and spectral characteristics less certain and reduces the automation ability of existing methods. Thus, this letter proposes a semiautomatic extraction of rural roads from high-resolution remote sensing images based on a multifeature combination. First, to address irregular curvature change characteristics of rural roads, we modify multiscale line segment orientation histogram (MLSOH) descriptors to reduce the impact of local curvature change on tracking. Second, we design a multicircle template to analyze the contrast between roads and nonroads and solve the problem of narrow roads. Last, we propose a panchromatic and hue, saturation, value (HSV) space interactive matching model to solve the problem of matching diverse road construction materials. This letter employs Pleiades satellite and GF-2 imagery. Compared with other methods, the proposed method improves automated road extraction by ensuring the extraction accuracy.