Satellite Images Classification in Rural Areas Based on Fractal Dimension

Authors

  • Mohammed Sahib Mahdi, Ass. Prof. Dr. College of Engineering – University of Nahrain
  • Aqeel Abboud Abdul Hassan, Ass. Lect. College of Engineering-University of Baghdad

DOI:

https://doi.org/10.31026/j.eng.2016.04.10

Keywords:

nquadtree, box counting, fractal dimension, supervised classification.

Abstract

Fractal geometry is receiving increase attention as a quantitative and qualitative model for natural phenomena description, which can establish an active classification technique when applied on satellite images. In this paper, a satellite image is used which was taken by Quick Bird that contains different visible classes. After pre-processing, this image passes through two stages: segmentation and classification. The segmentation carried out by hybrid two methods used to produce effective results; the two methods are Quadtree method that operated inside Horizontal-Vertical method. The hybrid method is segmented the image into two rectangular blocks, either horizontally or vertically depending on spectral uniformity criterion; otherwise the block is segmented by the quadtree. Then, supervised classification is carried out by means the Fractal Dimension. For each block in the image, the Fractal Dimension was determined and used to classify the target part of image. The supervised classification process delivered five deferent classes were clearly appeared in the target part of image. The supervised classification produced about 97% classification score, which ensures that the adopted fractal feature was able to recognize different classes found in the image with high accuracy level.

 

Downloads

Download data is not yet available.

How to Cite

“Satellite Images Classification in Rural Areas Based on Fractal Dimension” (2016) Journal of Engineering, 22(4), pp. 147–157. doi:10.31026/j.eng.2016.04.10.

Publication Dates

Published

2016-04-01

Similar Articles

1-10 of 128

You may also start an advanced similarity search for this article.