Abstract
High-resolution satellite remote sensing image are mostly used for accurate updating of GIS data. As the primary GIS data, urban roads on the image show the rich geometric features and radiation characteristics, that edge detection and grouping becoming an important way to solve the road extraction. However, edge elements obtained from images are always discontinuous for interference of noise and weak contrast between road and background. What more, vehicles, plant, buildings and shadow blocking results in weak grouping relation of elements. In processing, insignificant candidate road may be weeded out as noise and lead to failure road extraction. This paper presents a semi-automated extraction method for low contrast road basing on statistical grouping of orientation texture feature. Multi-direction and multi-scale Gabor filters are employed to detect directions of road texture. Then same direction pixels are grouped under constraining of rectangle template and generate road base elements. Finally, simulated annealing algorithm is used to optimize elements connection. Experiment results show that proposed method was effective in accurate extraction of low contrast road.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
