Road network extraction using multi-layered filtering and tensor voting from aerial images

Abstract

Road network extraction from high-resolution aerial images is a predominant research area in remote sensing due to road network applications in various applications like transportation and industrialization disaster management. In this work, an integrated method is proposed to delineate a smooth and accurate road centerline from very high resolution (VHR) aerial images. The proposed approach incorporates Gabor filtering, hysteresis thresholding, road filtering using shape features, and tensor voting (TV). The initial road map is generated by detecting the road features that lie on the edges in the starting phase, using Gabor filter and hysteresis thresholding. In the next phase, the initial road map's exactitude is enhanced by removing non-road components from the initial road network using filtering based on shape features and morphological operations. Further, the Euclidean distance transform is applied for the extraction of the road centerline. The centerlines extracted by the method are broken at some places due to occlusions caused by different factors. Finally, the fractured road network is reconstructed by the TV technique. The experimental results tested on VHR aerial images demonstrate the accurate centerline extraction of high quality and higher assessable results as compared with contemporary methods.