대한지리학회지 (Journal of the Korean Geographical Society)

대한지리학회 (The Korean Geographical Society)
권호 표지

지식 기반 시스템에서 GIS 자료를 활용하기 위한 기계 학습 기법에 관한 연구 - Landsat ETM+ 영상의 토지 피복 분류를 사례로

A Machine learning Approach for Knowledge Base Construction Incorporating GIS Data for land Cover Classification of Landsat ETM+ Image

  • 발행 : 2008.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

원격탐사에서 위성 영상의 디지털 처리 기술이 발달하면서 GIS 자료와 지식 기반 전문가 시스템과의 통합에 대한 관심이 증가하고 있다. 본 연구에서는 위성영상을 토지피복 분류하는 과정에서 GIS 자료를 통합하기 위하여 기계 학습 기법과 규칙 기반 분류 기법을 적용하였다. 사례 지역을 대상으로 Landsat ETM+ 영상과 고도, 경사, 향, 수역과의 거리, 도로와의 거리, 인구밀도 등의 GIS 자료를 함께 활용하였다. C5.0 추론 기계 학습 알고리듬을 이용하여 350개의 표본점으로부터 결정 트리와 분류 규칙을 생성하였다. 본 연구에서 도출된 규칙을 이용하여 분류한 결과, 고독 수역과의 거리, 인구밀도 등의 GIS 자료가 규칙 기반 분류에 효과적인 것으로 나타났다. 본 연구에서 제안한 기계 학습과 지식 기반 분류 기법을 이용하면 다양한 GIS 자료들을 통합하여 위성영상을 보다 효과적으로 분류할 수 있다.

Integration of GIS data and human expert knowledge into digital image processing has long been acknowledged as a necessity to improve remote sensing image analysis. We propose inductive machine learning algorithm for GIS data integration and rule-based classification method for land cover classification. Proposed method is tested with a land cover classification of a Landsat ETM+ multispectral image and GIS data layers including elevation, aspect, slope, distance to water bodies, distance to road network, and population density. Decision trees and production rules for land cover classification are generated by C5.0 inductive machine learning algorithm with 350 stratified random point samples. Production rules are used for land cover classification integrated with unsupervised ISODATA classification. Result shows that GIS data layers such as elevation, distance to water bodies and population density can be effectively integrated for rule-based image classification. Intuitive production rules generated by inductive machine learning are easy to understand. Proposed method demonstrates how various GIS data layers can be integrated with remotely sensed imagery in a framework of knowledge base construction to improve land cover classification.

키워드

참고문헌

  1. Ball, G. H. and Hall, D. J., 1965, A Novel Method of Data Analysis and Pattern Classification, Menlo Park, Stanford Research Institute
  2. Eklund, P. W., Kirkby, S. D., and Salim, A., 1998, Data mining and soil salinity analysis, International Journal of Geographical Information Science, 12(3), 247-268 https://doi.org/10.1080/136588198241888
  3. Enslin, W. R., Tonand, J., and Jain, A., 1987, Land cover change detection using a GIS-guided featurebased classification of Landsat Thematic Mapper data, Proc. ASPRS, 6, 108-120
  4. Fayyad, U. M., Piatetsky-Shapiro, G., Smyth, P., and Uthurusamy, R., 1996, Advances in knowledge Discovery and Data Mining, AAAI/MIT Press, Menlo Park
  5. Gahegan, M., 2000, On the application of inductive machine learning tools to geographical analysis, Geographical Analysis, 32, 113-139 https://doi.org/10.1111/j.1538-4632.2000.tb00420.x
  6. Gahegan, M., 2003, Is inductive machine learning just another wild goose (or might it lay the golden egg)?, International Journal of Geographic Information Science, 17(1), 69-92 https://doi.org/10.1080/713811742
  7. Huang, X. and Jensen, J. R., 1997, A Machine Learning approach to automated knowledge-base building for remote sensing image analysis with GIS data, Photogrammetric Engineering and Remote Sensing, 63(10), 1185-1194
  8. Jensen, J. R., 2005, Introductory digital image processing:A Remote Sensing Perspective, Upper Saddle River, Prentice Hall, New Jersey
  9. Kontoes, C., Wilkingson, G., Burrill, A., Goffredo, S., and Megier, J., 1993, An experimental system form the integration of GIS data in knowledge-based image analysis for remote sensing of agriculture, International Journal of Geographical Information Science, 7(3), 247-262 https://doi.org/10.1080/02693799308901955
  10. Li, D., Di, K., and Li, D., 2000, Land use classification of remote sensing image with GIS data based on spatial data mining techniques, International Archives of Photogrammetry and Remote Sensing, 33, Part B3
  11. Malebra, D., Esposito, F., Lanza, A., and Lisi, F. A., 2001, Machine learning for information extraction from topographic maps. In Miller, H. J. and Han, J. (Eds.), Geographic Data Mining and Knowledge Discovery (pp. 291-314). Taylor and Francis, New York
  12. Michalski, R. S. and Chilausky, R. L., 1980, Learning by being told and learning from examples: an experimental comparison of the two methods of knowledge acquisition in the context of developing and expert system for soybean disease diagnosis, Policy Analysis and Information Systems, 4(2), 1980
  13. Mitchell, T. M., 1997, Machine Learning, McGraw-Hill, New York
  14. Qi, F. and Zhu, A. 2003, Knowledge discovery from soil maps using inductive learning, International Journal of Geographical Information Science, 17(8), 771-795 https://doi.org/10.1080/13658810310001596049
  15. Quinlan, J. R., 1986, Induction of decision trees, Machine Learning, 1, 81-106
  16. Quinlan, J. R., 1993, C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers, San Mateo, California
  17. Quinlan, J. R., 2001, See5: An Informal Tutorial, Accessed at URL: http://www.rulequest.com
  18. Westmoreland, S. and Stow, D. A. 1992, Category identification of changed land-use polygons in an integrated image processing geographic information system, Photogrammetric Engineering and Remote Sensing, 58(11), 1593- 1599