Knowledge-based road network extraction on SPOT satellite images
Automated delineation of linear cultural structures can help to improve the classification of remotely-sensed images. This topic also provides an excellent testbed for knowledge-based computer vision research. In this paper, a road network extraction system, useful on SPOT satellite images, is described. By applying semantic model-fitting operators, an initial spatial segmentation is obtained. To analyse the resulting primal road network, declaratively stated knowledge about generic appearances of roads and crossroads on SPOT images is used. As a result a more detailed description of the network can be obtained. Advantages and drawbacks of the use of existing knowledge base tools for this computer vision task are reported.
Unable to display preview. Download preview PDF.
- [DESTIVAL]Destival, I. Le Men, H. Detection of linear networks on satelitte images Proc. 8th. Int. Conf. Pat. Rec. 86 (1986) 856–858Google Scholar
- [FISCHLER 81]Fischler, M. Tenenbaum, J. Wolf, H. Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integrating technique Com. Gr. Im. Pr. 15 (1981) 201–223Google Scholar
- [FISCHLER 87]Fischler, M. Firschein, O. The eye, the brain and the computer Addison Wesley 1987Google Scholar
- [PARIKH]Parikh, J. A. Automatic Techniques for Extraction of Geological Fracture Patterns Pattern Recognition in Practice II (1986) 373–383Google Scholar
- [VAN CLEYN]Van Cleynenbreugel, J. et al. Knowledge-based improvement of automatic image interpretation for restricted scenes: two case studies submitted for publication to Image and Vision Comp. (april 1987)Google Scholar
- [WANG]Wang, F. Newkirk, R. A Knowledge-based System for Highway Network Extraction Proc. IGARSS 87 (1987) 343–347Google Scholar
- [YEE]Yee, B. An Expert System for Planimetric Feature Extraction Proc. IGARSS 87 (1987) 321–325Google Scholar
- [ZHU]Zhu, M. Yeh, P. Automatic Road Network Detection on Aerial Photographs Proc. IEEE CVPR 86 (1986) 34–40Google Scholar