The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Voi. XXXVII. Part B3b. Beijing 2008 
4. CONCLUSIONS 
In this article, a road extraction methodology from high 
resolution satellite images is proposed. 
The first step called road detection was performed based on NN 
classifiers. It was discovered that using texture parameters of a 
binerized pre-determined road raster map integrated with 
spectral information of individual pixels can improve both road 
and background detection ability of neural networks. 
In the second step of road vectorization, genetic algorithms did 
not show enough attractiveness as they are quite time 
consuming for image clustering. 
A novel clustering algorithm was proposed for road key point 
identification wich is based on shape interpretation of road 
patches. Then the obtained road key points were connected 
considering the adjacency information obtained form a fuzzy 
clustering. 
The designed methodology was performed on different pan- 
sharpened IKONOS and Quick Bird sample images and the 
road extraction ability the proposed method was approved. 
REFERENCES 
Doucette, P., Agouris, p., Stefanidis, A., and Musavi, M., 2001. 
Self-organised clustering for road extraction in classified 
imagery, ISPRS Journal of Photogrammetry and Remote 
Sensing. 55( 5/6), pp. 347-358. 
Malay K. Pakhira, Sanghamitra Bandyopadhyay, Ujjwal 
Maulik, 2005. A study of some fuzzy cluster validity indices, 
genetic clustering and application to pixel classification, Fuzzy 
Sets and Systems. 155 (2), pp. 191-214. 
Mena, J.B., 2003. State of the art on automatic road extraction 
for GIS update: a novel classification. Pattern Recognition 
Letters, 24(16), pp. 3037-3058. 
Mena, J.B., and Malpica J.A., 2005. An automatic method for 
road extraction in rural and semi-urban areas starting from high 
resolution satellite imagery. Pattern Recognition Letters. 26(9), 
pp. 1201-1220. 
Mena, J.B., 2006. Automatic vectorization of segmented road 
networks by geometrical and topological analysis of high 
resolution binary images. Knowledge based systems. 19(8), pp. 
704-718. 
Mohammadzadeh, A., Tavakoli, A., and Valadan Zoej, M.J., 
2006. Road extraction based on fuzzy logic and mathematical 
morphology from pan-sharpened IKONOS images. The 
Photogrammetric Record, 21(113), pp. 44-60. 
Mokhtarzade, M., Ebadi, H., and Valadan Zoej, M.J., 2007. 
Optimization of Road Detection from High-Resolution Satellite 
Images Using Texture Parameters in Neural Network 
Classifiers. Canadian Journal of Remote Sensing. 33(6), pp. 
481-491. 
Mokhtarzdae, M., and Valadan Zoej, M.J., 2007. Road 
detection from high resolution satellite images using artificial 
neural networks. International journal of applied earth 
observation and geoinformation, 9(1), pp. 32-40. 
Zhang, Q., and Couloigner, I., 2006. Benefit of the angular 
texture signature for the separation of parking lots and roads on 
high resolution multi-spectral imagery. Pattern Recognition 
Letters. 27(9), pp. 937-946. 
555