Abstract—This paper proposes an optimized mathematical model for linear feature extraction from satellite images. The model first uses the Ant Colony Optimization (ACO) to detect the edges from the satellite image. Next the line plausibility map is used as the external energy in a snake model to identify and extract the linear features like roads edges in image. Our approach is validated by a series of tests on satellite images.

Index Terms—Ant colony optimization, image edge detection, road, satellite image, snake, line plausibility map.

L. Mohammadnia is with Science and Research Branch, Islamic Azad University .Tehran, Iran (e-mail: lmohamadnia@gmail.com). J. Amini is with Department of geomantic engineering, collage of Engineering, University of Tehran, and Tehran, Iran (e-mail: lmohamadnia@gmail.com).

Cite: Leila Mohammadnia and Jalal Amini, "An Optimized Model for Linear Feature Extraction from Satellite Image," International Journal of Applied Physics and Mathematics  vol. 2, no. 5, pp. 316-318, 2012.