In pixel-based remote sensing image classification, the long processing time limits application of classification. Image segmentation is adopted to accelerate the classification speed. Image segmentation is a procedure of dividing an image into separated homogenous regions. These regions are considered as objects to be classified. A refined quadtree-based segmentation algorithm is proposed in the paper. The windowed aggregation method is designed to solve the problem of over-segmentation, which occurs in quadtree-based segmentation. A spot 5 remote sensing image in Qingdao was selected as the test image. Three experiments were implemented on the test image: the first is pixel-based classification; the second is quadtree-based classification; the third is refined quadtree-based classification. The pixel-based classification obtains the highest accuracy while takes more time. The refined quadtree-based classification is superior to quadtree-based classification in time consumed and accuracy.
[1]
Guaraci J. Erthal,et al.
Satellite Imagery Segmentation: a region growing approach
,
1996
.
[2]
Xia Jun,et al.
The Classification of Land Cover Derived from High Resolution Remote Sensing Imagery
,
2011,
2011 Fourth International Conference on Intelligent Computation Technology and Automation.
[3]
Humberto Bustince,et al.
Image Threshold Computation by Modelizing Knowledge/Unknowledge by Means of Atanassov's Intuitionistic Fuzzy Sets
,
2008,
Fuzzy Sets and Their Extensions: Representation, Aggregation and Models.
[4]
Jaroslaw Stepaniuk,et al.
Fuzzy Rough Entropy Clustering Algorithm Parametrization
,
2009,
ICMMI.
[5]
N. Otsu.
A threshold selection method from gray level histograms
,
1979
.
[6]
Kong Jie.
Remote Sensing Image Segmentation Approach Based on Quarter-tree and Graph Cut
,
2010
.