Study on Ejina Oasis Land Cover Using Decision Tree Classification

Author

An, Huijun ; Wang, Bing ; Zhang, Qiuliang ; Zhang, Tao ; Jin, Yu

Author_Institution

Forestry Coll., Inner Mongolia Agric. Univ., Hohhot, China

fYear

2010

fDate

29-31 Oct. 2010

Firstpage

1

Lastpage

4

Abstract

The automatic recognition of images has been always one of preceding issues in the filed of remote sensing. From traditional algorithm of K-Means, maximum likelihood to new decision tree, neural networks, wavelet transform and fuzzy recognition system, the classification accuracy has been improved. In this work, based on Decision Tree Classification (DTC) and Landsat ETM+ data, Ejina Oasis land cover is classified. And the applications of NDVI, K-T transformation and Principal Component Analysis (PCA) into the decision tree classification are mainly studied. Finally, the accuracy of the classification results is analyzed. The results indicate that the built decision tree model is reasonable; the overall accuracy is up to 93.28%. It can provide scientific basis for the ecological health dynamic monitoring and regional sustainable development of Ejina Oasis.

Keywords

decision trees; image classification; image recognition; maximum likelihood estimation; neural nets; principal component analysis; remote sensing; wavelet transforms; Ejina Oasis land cover; K-T transformation; Landsat ETM+ data; automatic image recognition; decision tree classification; ecological health dynamic monitoring; fuzzy recognition system; maximum likelihood; neural networks; principal component analysis; regional sustainable development; remote sensing; wavelet transform; Accuracy; Brightness; Classification algorithms; Classification tree analysis; Principal component analysis; Remote sensing;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Technology (ICMT), 2010 International Conference on

Conference_Location

Ningbo

Print_ISBN

978-1-4244-7871-2

Type

conf

DOI

10.1109/ICMULT.2010.5631031

Filename

5631031