Road Extraction from High-resolution Remotely Sensed Image Based on Morphological Segmentation

Based on grey level mathematical morphology, this paper presents a newly developed approach to extract road network from high-resolution remotely sensed image. First, the image is segmented based on grey level morphological characteristics, and basic road network can be obtained. Then final road network is extracted from the basic road network by line match method. The proposed approach in the paper can be adapted for road extraction from the remotely sensed image where road cannot be differentiated with background clearly. And the experiments also indicate that the proposed approach is efficient for extracting road network from remotely sensed image.