DPPR 2011: Advances in Digital Image Processing and Information Technology pp 378-382 | Cite as
Extraction of Urban Road Network by Performing Edge – Aided Classification in Remote Sensing
Conference paper
Abstract
A new approach for object extraction from high-resolution satellite images is presented in this paper. The new approach integrates image fusion, multi-spectral classification, feature extraction and feature segmentation into the object to improve accuracies. This paper mainly concentrates on road extraction from quick bird MS and Pan images using the proposed approach. Experiments of road extraction with Quick Bind MS and Pan images demonstrate that the proposed approach is effective.
Keywords
Digital Urban Object Edge – Aided ExtractionPreview
Unable to display preview. Download preview PDF.
References
- 1.Zhang, Y.: Detection of Urban Housing Development by Fusing Multisensor Satellitic Data and Performing Spatial Feature Post-Classification. Submitted to the International Journal of Remote Sensing 22(17), 3339–3355 (2001)CrossRefGoogle Scholar
- 2.Zhang, Y.: Texture Integrated Classification of Urban Trees in High-Resolution Color Infrared Imagery. Photogrammetric Engineering & Remote Sensing 67(12), 1359–1365 (2001)Google Scholar
- 3.Zhang, Y.: A New Automatic Approach for Effectively Fusing Landsat 7 images and IKONOS Images. In: IEEE / IGARSS 2002, Toronto, Canada, June 24-28 (2002)Google Scholar
- 4.Lec, D.S., Shan, J., Bethel, B.: Classification-guided building detection from IKONOS imagery. In: CD-Proceeding of American Society of Photogrammetry and Remote Sensing, Washington DC (2002)Google Scholar
- 5.Zhang, C., et al.: Road Network Detection by Mathematical Morphology. In: Proceeding of ISPRS. Workshop “3D Geospatial Data Production: Meeting Application Requirement”, Paris, France, April 7-9, pp. 185–200 (1996)Google Scholar
- 6.Gong, Wang: Road Network Extraction from High Resolution Airborne Digital Camera Data. Geographic Information Sciences 3(1-2) (December 1997)Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2011