Spatial Information Research

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

Application of the Rule-Based Image Classification Method to Jeju Island

규칙기반 영상분류 방법의 제주도 지역의 적용

  • Lee, Jin-A (Dept. of Geoinformatic Engineering, University of Science & Technology) ;
  • Lee, Sung-Soon (Korea Institute of Geoscience and Mineral Resources)
  • Received : 2012.12.19
  • Accepted : 2013.02.25
  • Published : 2013.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Geographic features are reflected in satellite images, which contain characteristic elements. Information on changes can be obtained through a comparison of images taken at different times. If multi-temporal images can be classified through the use of an unsupervised method, this is likely to improve the accuracy of image classification and contribute to various applications. A rule-based image classification algorithm for automatic processing without human involvement has been developed, but it must be verified that its results are not affected by imperfect elements. In this study, Landsat images of Jeju Island were used to carry out a rule-based image classification. The application results were examined for complex cases, including the presence of clouds in the images, different photographed times, and the type of target area, such as city, mountain, or field. The presence of clouds did not affect calculations, and appropriate classification rules were applied, depending on the different photographed times. The expansion of the urban areas of Jeju and the increase of facilities such as vinyl greenhouses in Seoguipo were identified. Furthermore, space information changes and accurate classifications for Jeju Island were obtained. With the goal of performing high-quality unsupervised classifications, measures to generalize and improve the methods employed were searched for. The findings of this study could be used in time-series analyses of images for various applications, including urban development and environmental change monitoring.

지형지물은 각각의 특징적 요인을 내포하고 있어 촬영된 위성영상에 반영된다. 촬영시기가 다른 영상을 통하여 변화에 대한 정보를 얻을 수 있다. 다중시기 영상을 무감독 방법으로 분류할 수 있다면 영상 분류의 정확도를 높여 주고, 여러 응용분야에 기여할 수 있다. 규칙기반 영상분류 알고리즘은 사람의 직접적인 개입이 없이 자동화된 방법으로 처리 되도록 개발되었으나, 불완전 요소에 결과가 영향 받는지 확인되어야 한다. 이 연구에서는 제주도 지역의 Landsat 영상으로 규칙기반 영상분류를 수행하였다. 영상의 구름의 존재하고 촬영시기의 차이가 있는 경우, 대상지가 도시, 산지, 농지 등 복합적인 경우에 대하여 적용 결과를 확인하였다. 구름이 있는 부분의 경우, 계수에 영향을 주지 않았으며, 촬영시기의 차이에 따라 분류규칙이 적절이 반영되었다. 제주시 도시지역의 확장, 서귀포시의 비닐하우스 등의 시설물 개체 수 증가 등을 파악 할 수 있었다. 제주도 지역의 공간정보 변화 파악과 분류 정확도를 얻을 수 있었다. 양질의 무감독 분류가 수행되는 것을 목표로 하여 방법의 일반화 및 개선방안을 모색하고자 하였다. 향후 도시개발, 환경변화 모니터링 등 영상 시계열 분석에 다양하게 활용될 수 있을 것이다.

Keywords

References

  1. Alphan, H; Doygun, H; Unlukaplan, YI. 2009, Post-classification Comparison of Land Cover using Multitemporal Landsat and ASTER Imagery: the case of Kahramanmaras, Turkey, Environmental Monitoring and Assessment, 151(1-4):327-336. https://doi.org/10.1007/s10661-008-0274-x
  2. Coenen, F; Leng, P. 2007, The effect of Threshold values on Association Rule Based Classification Accuracy, Data & Knowledge Engineering, 60(2):345-360. https://doi.org/10.1016/j.datak.2006.02.005
  3. Guindon, B; Zhang, Y; Dillabaugh, C. 2004, Landsat Urban Mapping Based on a Combined Spectral-spatial Methodology, Remote Sensing of Environment, 92(2):218-232. https://doi.org/10.1016/j.rse.2004.06.015
  4. Jang, D. H. 2005, Change Detection of land - surface Environment in Gongju Areas Using Spatial Relationships between Land - surface Change and Geo - spatial Information, Journal of the Korean Geographical Society, 40(3): 296-309.
  5. Jang, D. H; Kim, C. S; Park, J. H. 2010, The Land-cover Changes and Pattern Analysis in the Tidal Flats Using Post-classification Comparison Method: The Case of Taean Peninsula Region, Journal of the Korean Geographical Society, 45(2):201-317.
  6. Jang, D. H; Kim, M. K. 2003, Improving of land-cover map using IKONOS image data, The Journal of GIS Association of Korea, 11(2):101-117.
  7. Kim, Y. S; Lee, K. J; Ryu, J. W. 2003, Land Use/Cover Classification Nomenclature for Urban Growth Analysis, Paper presented at the spring meeting for GIS Association of Korea :537-543.
  8. Krishnaswamy, J; Kiran, M. C; Ganeshaiah, K. N. 2004, Tree Model based Eco-climatic Vegetation Classification and Fuzzy Mapping in Diverse Tropical Deciduous Ecosystems using Multi-Deason NDVI, International Journal of Remote Sensing, 25(6):1185-1205. https://doi.org/10.1080/0143116031000149989
  9. Lawrence, R. L; Wright, A. 2001, Rule-Based Classification Systems using Classification and Regression Tree (CART) Analysis, Photogrammetric engineering and Remote Sensing, 67(10): 1137-1142.
  10. Lee, J. A; Lee, S. S. 2011, A Rule-Based Image Classification Method for Analysis of Urban Development in the Capital Area, Journal of Korea Spatial Information Society, 19(6):55-66.
  11. Lee, J. Y; Kim, B. S. 2008, Automated Vinyl Green House Identification Method Using Spatial Pattern in High Spatial Resolution Imagery, Korean Journal of Remote Sensing, 24(2):117-124. https://doi.org/10.7780/kjrs.2008.24.2.117
  12. Lee, K. W; Yu, Y. C; Song, M. Y; Sagong H. S. 2002, Comparative Analysis of Land-use thematic GIS layers and Multi-resolution Image Classification Results by using LANDSAT 7 ETM+ and KOMPSAT EOC image, The Journal of GIS Association of Korea, 10(2):331-343.
  13. Liu, B; Ma, Y; Wong, C. K. 2000, Improving an Association Rule Based Classifier, Principles of Data Mining and Knowledge Discovery Lecture Notes in Computer Science, 1910:504-509.
  14. Quan, H. C; Lee, B. G. 2009, Analysis of Relationship Between LST and NDVI using Landsat TM Images on the City Areas of Jeju Island, Journal of the Korean Society for GeoSpatial Information System, 17(4):39-44.
  15. Shin, K. J; Yu, Y. G; Hwang, E. J. 2009, Land Use Analysis of Chung-Ju Road Circumstance Using Remote Sensing, Journal of the Korea Contents Association, 9(6):436-443. https://doi.org/10.5392/JKCA.2009.9.6.436
  16. Warner, T. A; Levandowski, D. W; Bell, R; Cetin, H. 1994, Rule-Based Geobotanical Classification of Topographic, Aeromagnetic, and Remotely Sensed Vegetation Community Data, Remote Sensing of Environment, 50(1):41-51. https://doi.org/10.1016/0034-4257(94)90093-0
  17. Zha, Y; Gao, J; Ni, S. 2003, Use of Normalized Difference Built-up Index in automatically Mapping Urban Areas from TM Imagery, International Journal of Remote Sensing, 24(3):583-594. https://doi.org/10.1080/01431160304987