하이브리드 분류기법을 이용한 위성영상의 분류에 관한 연구 = A Study on the Classification for Satellite Images using Hybrid Method

국문 초록 (Abstract)

본 논문에서는 위성영상의 분류에 대한 성능 개선을 위하여 ISODATA 클러스터링, 퍼지 C-Means 알고리즘, 베이시안 최대우도 분류기법을 통합한 하이브리드 분류기법을 제안하였다. 본 연구에서는 분석자에 의하여 분류항목별 학습 데이터를 선정한 후 이를 ISODATA 클러스터링을 이용하여 각각의 분류항목별로 분광특징에 따라 학습 데이터를 세분화하여 새로운 학습 데이터를 선정하였다. 새롭게 선정된 학습 데이터를 이용하여 퍼지 C-Means 알고리즘을 이용하여 분류를 수행하고 그 결과를 베이시안 최대우도 분류기의 사전확률로 적용하여 분류를 수행하였다. 그 결과 분석자가 선정한 분류항목별 훈련데이터의 분광적인 특징에 관계없이 분류를 수행할 수 있었으며 위성영상의 분류의 성능을 개선할 수 있었다. 제안된 기법은 Landsat TM 위성영상을 이용하여 그 적용성을 시험하였다.

다국어 초록 (Multilingual Abstract)

This paper presents hybrid classification method to improve the performance of satellite images classification by combining Bayesian maximum likelihood classifier, ISODATA clustering and fuzzy C-Means algorithm. In this paper, the training data of each class were generated by separating the spectral signature using ISODATA clustering. We can classify according to pixel's membership grade followed by cluster center of fuzzy C-Means algorithm as the mean value of training data for each class. Bayesian maximum likelihood classifier is performed with prior probability by result of fuzzy C-Means classification. The results shows that proposed method could improve performance of classification method and also perform classification with no concern about spectral signature of the training data. The proposed method is applied to a Landsat TM satellite image for the verifying test.

참고문헌 (Reference)

1 F. R. D. Velasco, "Thresholding using the isodata clustering algorithm" smc-10 : 771-774, 1981.

2 Yuyu Zhou, "The research of classification algorithm based on fuzzy clustering and neural network" 4 : 2525-2527, June2002.

3 "The Canada Centre for Remote Sensing" //www.ccrs.nrca (//www.ccrs.nrca):

4 Zhaocong Wu, "Research on remote sensing image classification using neural network based on rough sets" 1 : 279-28429, Nov.,2001.

5 //dynamo.ecn.purdue.edu/, "Purdue/Laboratory for Applications of Remote Sensing http"

6 Amal S. Perera, "Performance Improvement for Bayesian Classification on Spatial Data with P-Trees" 15th International Conference on Computer Applications in Industry and Engineering Nov.2002.

7 N. K. Pal, "On Cluster Validity for the Fuzzy C-Means Model" 3 (3): 370 -379, 1995

8 David Landgrebe, "Information Extraction Principles and Methods for Multispectral and Hyperspectral Image Data" Chapter 1 of Information Processing for Remote Sensing, edited by C. H. Chen, published by the World Scientific Publishing Co., Inc 1-30, Spring1999.

9 Nakashiim T.,, "Improving the performance of fuzzy classification systems by membership function learning and feature selection" 1 : 488-493, 2002.

10 Jan, "Classification of multispectral remote sensing data using a back- propagation neural network IEEE Trans. on Geosci. and Remote Sensing" 30 (30): 81-88, 1992.

11 Mehmet I Saglam, "Classification of Satellite Images by using Self-organizing map and Linear Support Vector Machine Decision tree" GISdevelopment Conference Proceedings of Map Asia 2003.

12 B.Gorte, "Bayesian classification and class area estimation of satellite images using stratification" 36 (36): 303-, 1998.

13 F, "An explicit fuzzy supervised classification method for multispectral remote sensing images" 38 : 287-295, 2000.

14 Sun, "A New Information Fusion Method for Land-Use Classification Using High Resolution Satellite Imagery" 2000.

15 Nishii,, "A Markov random field-based approach to decision-level fusion for remote sensing image classification" 41 : 2316-2319, Oct.2003.

16 R. Schowengerdt, "'Techniques of Image Processing and Classification in Remote Sensing" Academic Press 1-58, 1983.

17 James C. Bezdek, "'Pattern Recognition with Fuzzy Objective Function Algorithms" Plenum 1981.