Journal of Korean Society for Geospatial Information Science (대한공간정보학회지)

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Comparative Study on Suitable SVM Kernel Function of Land Cover Classification Using KOMPSAT-2 Imagery

KOMPSAT-2 영상의 토지피복분류에 적합한 SVM 커널 함수 비교 연구

  • Kang, Nam Yi (Department of Civil Engineering, Chonbuk National University) ;
  • Go, Sin Young (Department of Civil Engineering, Chonbuk National University) ;
  • Cho, Gi Sung (Department of Civil Engineering, Chonbuk National University)
  • Received : 2013.01.29
  • Accepted : 2013.04.25
  • Published : 2013.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, the high-resolution satellite images is used the land cover and status data for the natural resources or environment management very helpful. The SVM algorithm of image processing has been used in various field. However, classification accuracy by SVM algorithm can be changed by various kernel functions and parameters. In this paper, the typical kernel function of the SVM algorithm was applied to the KOMPSAT-2 image and than the result of land cover performed the accuracy analysis using the checkpoint. Also, we carried out the analysis for selected the SVM kernel function from the land cover of the target region. As a result, the polynomial kernel function is demonstrated about the highest overall accuracy of classification. And that we know that the polynomial kernel and RBF kernel function is the best kernel function about each classification category accuracy.

최근 고해상도 위성영상은 자연자원이나 환경 관리에 필요로 하는 토지 피복 및 이용 현황자료 분석 등에 유용하게 사용되고 있다. 영상처리 알고리즘 중 SVM 알고리즘은 최근 다양한 분야에서 이용되고 있다. 그러나 SVM 알고리즘은 다양한 커널 함수 및 매개변수에 의해 그 정확도가 달라진다. 따라서 본 논문에서는 SVM 알고리즘의 대표적 커널 함수를 KOMPSAT-2의 영상자료에 적용하고 토지피복결과를 검사점을 이용하여 정확도 분석을 실시하였다. 또한 대상지의 토지피복분류에 적합한 SVM의 커널 함수 선정하기 위해 분석을 실시하였다. 그 결과 전체 분류 정확도에는 Polynomial 커널 함수가 가장 높은 정확도를 보였으며 분류 항목별 정확도에서의 가장 적절한 커널 함수는 Polynomial, RBF 커널 함수임을 알 수 있었다.

Keywords

References

  1. Carl Staelin, 2003, Parameter selection for SVMs, Hewlett-Packard Company.
  2. Chang, Q., Chen, Q., Wang, X., 2005, Scaling gaussian RBF kernel width to improve SVM classification, ICNN&B 05' International Conference, Vol. 1.
  3. Chi, M., Feng, R., Bruzzone, L., 2008, Classification of hyperspectral remote-sensing data with primal SVM for small-sized training dataset problem, Advances in Space Research, Vol. 41, No. 11, pp. 1793-1799. https://doi.org/10.1016/j.asr.2008.02.012
  4. Choi, Jae Wan, Byun, Young Gi, Kim, Yong Il, Yu, Ki Yun, 2006, Support vector machine classification of hyperspectral image using spectral similarity kernel, The Korean Society for Spatial Information system, Vol. 14, No. 4, pp. 71-77.
  5. Foody, G.M., Mathur, A., 2004, A relative evaluation of multi-class image classification by SVMs, IEEE Transactions on Geoscience and Remote Sensing, Vol. 42, No. 6, pp. 1335-1343. https://doi.org/10.1109/TGRS.2004.827257
  6. Han, Seung Hee, 2010, Spatial Information engineering, Goomi Book.
  7. Kang, Nam Yi, Pak, Jung Gi, Cho, Gi Sung, Yeu, Yeon, 2012, An analysis of land cover classification methods using IKONOS satellite image, The Korean Society for Spatial Information system, Vol. 20, No. 3, pp. 65-70.
  8. Kim, Gi Sung, 2003, Classification using support vector machine, Thesis, Inha University.
  9. Kim, Hyo Mi, 2002, Classification of multi-class micro array gene expression data using SVM, Thesis, Yonsei University.
  10. Lee, Chang Seok, 2011, Adult image detection based on the skin region distribution using SVM, Thesis, Hanbat National University.
  11. Lee, Min Hoon, 2006, Study on classification of object and non-object images based on the color and texture significance, Thesis, Kumoh national Institute of Technology.
  12. Muller, K., Mika, S., Ratisch, G., Tsuda, K., Scholkopf, B., 2001, An introduction to kernel-based learning algorithms, IEEE Transactions On Neural Networks, Vol. 12, NO. 2.
  13. Prasad, S.V.S., Satya Savitri, T., Murali Krishna, I.V., 2011, Classification of multispectral satellite images using clustering with SVM classifier, International Journal of Computer Applications, Vol.35, No. 5, pp. 32-44. https://doi.org/10.5120/4399-6107
  14. Richards, John A., 1994, Remote sensing digital image analysis : An introduction, second, Revised and Enlarged Edition, pp.229-262, Springer-Verlag.
  15. Scholkopf, Bernhard., Smola, Alexander J., 2002, Leaning with kernels, The MIT Press, London.
  16. Schowengerdt, R., 1983, Techniques of image processing and classification in remote sensing, 1st Ed, pp. 1-58, Academic Press.
  17. Vapnik, Vladimir N., 1995, The nature of statical learning theory, Springer-Verlag, NewYork.

Cited by

  1. Development of a Classification Method for Forest Vegetation on the Stand Level, Using KOMPSAT-3A Imagery and Land Coverage Map vol.32, pp.6, 2018, https://doi.org/10.13047/KJEE.2018.32.6.686
  2. 산사태 취약성 분석: ASTER 위성영상을 이용한 점토광물인자 추출 및 공간데이터베이스의 SVM 통계기법 적용 vol.26, pp.1, 2016, https://doi.org/10.9720/kseg.2016.1.23
  3. 기계학습 기법에 따른 KOMPSAT-3A 시가화 영상 분류 - 서울시 양재 지역을 중심으로 - vol.36, pp.6, 2020, https://doi.org/10.7780/kjrs.2020.36.6.2.7