Abstract
ABSTRACTOne of the main problems in automating road network extraction from high-resolution satellite images is the misclassification between roads and other spectrally similar objects. Significant work is already done on the road class refinement direction. But, extraction of the roads that are closely adjacent to parking lots/buildings and identification of major road intersection is still an issue as they are misclassified. In this paper, a new shape descriptor to separate roads from spectrally similar non-road objects and to identify road network intersection is proposed. The proposed approach classified the input image into road and non-road classes using spectral features at first. In the binary image, considering roads continuous and elongated homogeneous regions, a new shape descriptor measuring the continuity of road pixels in a different direction is applied. The experiments on worldview-2, Ikonos, and GeoEye images showed that the proposed method is simple and effective in automating the separation of roads which are connected to parking lots/buildings and it can identify road intersection correctly.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.