The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Classification for Satellite Images using Hybrid Method

하이브리드 분류기법을 이용한 위성영상의 분류에 관한 연구

  • 전영준 (동의대학교 컴퓨터공학과) ;
  • 김진일 (동의대학교 대학원 컴퓨터공학과)
  • Published : 2004.04.01
Download PDF
⟨ Previous Next ⟩

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.

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.

Keywords

References

  1. John A. Richards, 'Remote Sensing Digital Image Analysis : An Introduction,' Second, Revised and Enlarged Edition, Springer-Verlag, pp.229-262, 1994
  2. The Canada Centre for Reomote Sensing, http://www.ccrs.nrcan.gc.ca
  3. R. Schowengerdt, 'Techniques of Image Processing and Classification in Remote Sensing,' 1st Ed., Academic Press, pp.1-58, 1983
  4. 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., pp.1-30, Spring, 1999
  5. B.Gorte and A. Stein, 'Bayesian classification and class area esimation of satellite images using stratification,' IEEE Trans, On Geoscience and Remote Sensing, 36(3), p.303, 1998 https://doi.org/10.1109/36.673673
  6. Amal S. Perera, Masum H. Serazi, William Perrizo, 'Performance Improvement for Bayesian Classification on Spatial Data with P-Trees,' 15th International Conference on Computer Applications in Industry and Engineering(CAINE 2002), Nov., 2002
  7. Melgani, F., Hashemy, B. A. R. and Taha, S. M. R., 'An explicit fuzzy supervised classification method for multispectral remote sensing images,' Geoscience and Remote Sensing, IEEE Transactions on, Vol.38, Issue 1 Part 1, pp.287-295, 2000 https://doi.org/10.1109/36.823921
  8. Nakashiim, T., Nakai, G. and Ishibuchi, H., 'Improving the performance of fuzzy classification systems by membership function learning and feature selection,' Fuzzy Systems, FUZZ-IEEE '02. Proceedings of the 2002 IEEE International Conference on, Vol.1, pp.488-493, 2002 https://doi.org/10.1109/FUZZ.2002.1005039
  9. Mehmet I Saglam, Bingul Yazgan, Okan K Ersoy, 'Classification of Satellite Images by using Self-organizing map and Linear Support Vector Machine Decision tree,' GISdevelopment Conference Proceedings of Map Asia 2003
  10. Zhaocong Wu, 'Research on remote sensing image classification using neural networks based on rough sets,' Info-tech and Info-net, 2001, Proceedings. ICII 2002-Beijing, 2001 International Conference on, Vo.1, pp.279-28429, Nov., 2001 https://doi.org/10.1109/ICII.2001.982759
  11. Heermann, P. D. and Khazenie, N., 'Classification of multispectral remote sensing data using a back-pro-pagation neural network,' IEEE Trans. on Geosci. and Remote Sensing, Vol.30, No.1, pp.81-88, Jan., 1992 https://doi.org/10.1109/36.124218
  12. Nishii, R., 'A Markov random field-based approach to decision-level fusion for remote sensing image classification,' IEEE Transactions on, Vol.41, Issue 10 pp.2316-2319, Oct., 2003 https://doi.org/10.1109/TGRS.2003.816648
  13. Yuyu Zhou, Hong Chen, Qijang Zhu, 'The research of classification algorithm based on fuzzy clustering and neural network,' Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International, Vol.4, pp.2525-2527, June, 2002 https://doi.org/10.1109/IGARSS.2002.1026599
  14. F. R. D. Belasco, 'Thresholding using the isodata clustering algorithm,' IEEE Trans. Syst. Man, Cybern., Vol.SMC-10, pp.771-774, 1981
  15. ISOCLUS, Isodata Clustering Program, http://www. pcigeomatics.com/cgi-bin/pcihlp/m_isoclus/
  16. James C. Bezdek, 'Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum, NY, 1981
  17. N. K. Pal and J. C. Bezdek, 'On Cluster Validity for the Fuzzy C-Means Model,' IEEE Trans. Fuzzy Syst., Vol.3, No.3, pp.370-379, 1995 https://doi.org/10.1109/91.413225
  18. Sun, W., 'A New Information Fusion Method for Land-Use Classification Using High Resolution Satellite Imagery,' Ph.D Dissertation, http://archimed.uni-mainz.de/pub/2000/0004, 2000
  19. Purdue/Laboratory for Applications of Remote Sensing http://dynamo.ecn.purdue.edu/~biehl/MultiSpec/.