Tuesday 20th of February 2018

Application of the Gradient Vector Flow Method for Treating Satellite Image

Mohammed Ait Oussous, Noureddine Alaa and Youssef Ait Khouya

In this work we propose a new approach to delineate regions in Satellite Image. This method is particularly applicable to the limitation of insoluble habitats. We are interested in detecting the boundaries of the villages near Marrakech from their satellite images, as a study case: Ouahat Sidi Brahim. Our approach has three stages: The first, using k nearest neighbour method for classification of the satellite image. The second, using a mean filter to regularize this classification. In the last we use the Gradient Vector Flow to detect the edge of the village. Our method gives satisfactory and encouraging results to detect the edge of the village and can be used as a tool to control the spread of slums.

Keywords: Classification, Satellite Image, k-Nearest Neighbour ( k-NN), median filter, active contour, Gradient Vector Flow.

Download Full-Text


Mohammed Ait Oussous
Faculty of Science and Technology of Marrakech

Noureddine Alaa
Faculty of Science and Technology of Marrakech

Youssef Ait Khouya
Faculty of Science and Technology of Marrakech

IJCSI Published Papers Indexed By:





IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »