2008 IEEE: Road network extraction with new vectorization and pruning from...
Hang Jin, Yanming Feng, Bofeng Li
With the increasing resolution of remote sensing images, road network can be displayed as continuous and homogeneity regions with a certain width rather than traditional thin lines. Therefore, road network extraction from large scale images refers to reliable road surface detection instead of road line extraction. In this paper, a novel automatic road network detection approach based on the combination of homogram segmentation and mathematical morphology is proposed, which includes three main steps: (i) the image is classified based on homogram segmentation to roughly identify the road network regions; (ii) the morphological opening and closing is employed to fill tiny holes and filter out small road branches; and (iii) the extracted road surface is further thinned by a thinning approach, pruned by a proposed method and finally simplified with Douglas- Peucker algorithm. Lastly, the results from some QuickBird images and aerial photos demonstrate the correctness and efficiency of the proposed process.
