Search In this Thesis
   Search In this Thesis  
العنوان
Feature Extraction from High Resolution Satellite Images for Mapping /
المؤلف
El-Rashidy, Faten Ahmed Mostafa.
هيئة الاعداد
باحث / فاتن أحمد مصطفى
مشرف / محمد عبد العال يوسف
مناقش / محمود النقراشى
مناقش / عبد العال محمد عبد الواحد
الموضوع
Satellites - Mapping.
تاريخ النشر
2015.
عدد الصفحات
121 P. :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
الهندسة (متفرقات)
الناشر
تاريخ الإجازة
28/5/2015
مكان الإجازة
جامعة أسيوط - كلية الهندسة - Mining and Metallurgical
الفهرس
Only 14 pages are availabe for public view

from 16

from 16

Abstract

High and accelerating rate of the urban changes and extensions in developing countries such as Egypt, calls for an efficient and fast technique for mapping. The availability of the new generation commercial one-meter resolution satellite images has opened a new era for producing and updating large-scale digital maps. The main aim of this study is to investigate the most accurate classification technique for feature extraction which can be applied for Egyptian environment. Also, it aims to evaluate the potentials of information content in Very High Resolution (VHR) satellite images for large scale mapping.
For achieving that aim, the work is carried out in two steps. The first step is the pre-processing for the IKONOS images including geometric correction and data fusion to obtain a geo-referenced pan-sharpened image. Then, a comparison between two classification techniques is performed through application on four test areas from that pan-sharpened image with different specifications with respect to its planning degree. The first technique is the traditional pixel-based image analysis and the second one is the object-oriented image analysis. The classification accuracy was evaluated through overall accuracy and kappa coefficient. The second step is the evaluation of pan-sharpened IKONOS image information content. This step is carried out through converting the classified pan-sharpened image into vector format, then comparing it with a map of a scale 1:5000.
Results of this work showed that, for the Egyptian environment, as the more planning degree as the higher resulting accuracy for both classification techniques. Also, it has been seen that, object-based analysis has more advantages than the Pixel-based one. Study of the information content of IKONOS images shows the capability of updating 1:5000 maps for good planned areas, while, that ability will be decreased with decreasing the degree of planning.