Seed point-based road extraction methods are vital for extracting road networks from satellite images. Despite its effectiveness, roads in very high-resolution (VHR) satellite images are complicated, such as road occlusion and material change. To tackle this issue, this paper proposes to use the colour space transformation and geodesic method. First, the test image is converted from Red-Green-Blue colour space to Hue-Saturation-Value colour space to reduce the material change influence. The geodesic method is subsequently applied to extract initial road segments that link road seed points provided by users. At last, the initial result is adjusted by a kernel density estimation method to produce centred roads. The presented method is quantitatively evaluated on three test images. Experiments show that the proposed method yields a substantial improvement over cutting-edge technologies. The findings in this study shine new light on a practical solution for road extraction from satellite images.
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)