대한원격탐사학회지 (Korean Journal of Remote Sensing)

  • 제29권5호
  • /
  • Pages.569-579
  • /
  • 2013
  • /
  • 1225-6161(pISSN)
  • /
  • 2287-9307(eISSN)
대한원격탐사학회 (Korean Society of Remote Sensing)
권호 표지
DOI QR코드

DOI QR Code

3차원 웨이블렛 변환을 이용한 다중시기 SAR 영상의 특징 추출 및 분류

Feature Extraction and Classification of Multi-temporal SAR Data Using 3D Wavelet Transform

  • 유희영 (인하대학교 지리정보공학연구소) ;
  • 박노욱 (인하대학교 지리정보공학과) ;
  • 홍석영 (농촌진흥청 국립농업과학원 토양비료과) ;
  • 이경도 (농촌진흥청 국립농업과학원 토양비료과) ;
  • 김이현 (농촌진흥청 국립농업과학원 토양비료과)
  • Yoo, Hee Young (Geoinformatic Engineering Research Institute, Inha University) ;
  • Park, No-Wook (Department of Geoinformatic Engineering, Inha University) ;
  • Hong, Sukyoung (Soil and Fertilizer Management Division, National Academy of Agricultural Science, Rural Development Administration) ;
  • Lee, Kyungdo (Soil and Fertilizer Management Division, National Academy of Agricultural Science, Rural Development Administration) ;
  • Kim, Yihyun (Soil and Fertilizer Management Division, National Academy of Agricultural Science, Rural Development Administration)
  • 투고 : 2013.10.08
  • 심사 : 2013.10.25
  • 발행 : 2013.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이 연구에서는 다중시기 SAR 영상으로부터 3D 웨이블렛 변환을 통해 추출된 특징 정보를 이용하여 토지피복 분류를 수행하였고 그 적용가능성을 평가하였다. 분류를 하기 전 단계로 3차원 웨이블렛 변환기반 특징을 추출하였고, 이후 토지 피복 분류에 사용하였다. 비교를 목적으로 특징추출 단계가 들어가지 않는 원본 영상과 주성분분석 기반 특징들의 분류를 함께 수행하였다. 성능 검증을 위해 당진에서 촬영된 다중시기 Radarsat-1호 영상을 사용하였고 토지피복은 논, 밭, 산림, 수계, 도심지가 포함된 5개의 클래스로 구분하였다. 토지피복 식별 능력 분석에 따르면 밭과 산림은 매우 유사한 특성을 보이기 때문에 두 클래스를 구분하는 것은 매우 어렵다. 3차원 웨이블렛 기반 특징을 사용하는 경우, 도심지를 제외하고 모든 클래스의 분류 정확도가 향상되었다. 특히 밭과 산림의 정확도가 향상된 것을 확인할 수 있었다. 이러한 향상은 다중시기자료를 시간과 공간적으로 동시에 분석하는 3차원 웨이블렛 변환 과정에 기인한 것으로 판단된다. 이 결과로부터 3차원 웨이블렛 변환이 영상으로부터 특징을 추출하는데 이용 가능하다는 것을 확인할 수 있었고, 추후에 다른 센서나 다른 연구지역으로 추가 실험을 수행할 예정이다.

In this study, land-cover classification was implemented using features extracted from multi-temporal SAR data through 3D wavelet transform and the applicability of the 3D wavelet transform as a feature extraction approach was evaluated. The feature extraction stage based on 3D wavelet transform was first carried out before the classification and the extracted features were used as input for land-cover classification. For a comparison purpose, original image data without the feature extraction stage and Principal Component Analysis (PCA) based features were also classified. Multi-temporal Radarsat-1 data acquired at Dangjin, Korea was used for this experiment and five land-cover classes including paddy fields, dry fields, forest, water, and built up areas were considered for classification. According to the discrimination capability analysis, the characteristics of dry field and forest were similar, so it was very difficult to distinguish these two classes. When using wavelet-based features, classification accuracy was generally improved except built-up class. Especially the improvement of accuracy for dry field and forest classes was achieved. This improvement may be attributed to the wavelet transform procedure decomposing multi-temporal data not only temporally but also spatially. This experiment result shows that 3D wavelet transform would be an effective tool for feature extraction from multi-temporal data although this procedure should be tested to other sensors or other areas through extensive experiments.

키워드

참고문헌

  1. Angiulli, G., V. Barrile, and M. Cacciola, 2005. SAR imagery classification using multi-class support vector machines, Journal of Electromagnetic Waves and Applications, 19(14): 1865-1872. https://doi.org/10.1163/156939305775570558
  2. Burges, C.J.C., 1998. A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, 2 :121-167. https://doi.org/10.1023/A:1009715923555
  3. Bouvet, A., T.L. Toan, and N. Lam-Dao, 2009. Monitoring of the rice cropping system in the Mekong Delta using ENVISAT/ASAR dual polarization data, IEEE Transactions on Geoscience and Remote Sensing, 47(2): 517-526. https://doi.org/10.1109/TGRS.2008.2007963
  4. Chang, T. and C. Kuo, 1993. Texture analysis and classification with tree-structured wavelet transform, IEEE Transaction on Image Processing, 2(4): 429-441. https://doi.org/10.1109/83.242353
  5. Daubechies, I., 1988. Orthonormal bases of compactly supported wavelet, Communications on Pure and Applied Mathematics, 41(7): 906-966.
  6. Fukuda, S. and H. Hirosawa, 1999. A wavelet-based texture feature set applied to classification of multifrequency polarimetric SAR images, IEEE Transactions on Geoscience and Remote Sensing, 37(5): 2282-2286. https://doi.org/10.1109/36.789624
  7. Fukada, S. and H. Hirosawa, 2001. Support vector machine classification of land cover: Application to polarimetric SAR data, Proc. of 2001 International Geoscience and Remote Sensing Symposium, Sydney, Australia, Jul. 9- 13, pp.187-189.
  8. Galford, G., J.F. Mustard, J. Melillo, A. Gendrin, C.C. Cerri, and C.E.P. Cerri, 2008. Wavelet analysis of MODIS time series to detect expansion and intensification of row-crop agriculture in Brazil, Remote sensing and Environment, 112: 576-587. https://doi.org/10.1016/j.rse.2007.05.017
  9. Henebry, G.M., 1997. Advantages of principal components analysis for land cover segmentation from SAR image series, Proc. of the third ERS symposium, Florence, Italy, Mar. 21-26, sp-414, pp. 175-178.
  10. Hirosawa, Y., S.E. Marsh and D.H. Kliman, 1996. Application of standardized principal component analysis to land-cover characterization using multitemporal AVHRR Data, Remote Sensing of Environment, 58: 267-281. https://doi.org/10.1016/S0034-4257(96)00068-5
  11. Hochschild, V., M. Klenke, A. Bartsch and W.A. Flügel, 1999. Land cover classification in Hilly watersheds using SAR backscatter intensity and interferometric coherence information, Proc. of 1999 International Symposium on Operationalization of Remote Sensing, Enschede, Netherlands, Aug. 16-20.
  12. Huang, S. and L. Zhang, 2012. A multiscale urban complexity index based on 3D wavelet transform for spectral spatial feature extraction and classification: an evaluation on the 8- channel WorldView-2 imagery, International Journal of Remote Sensing, 33(8): 2641-2656. https://doi.org/10.1080/01431161.2011.614287
  13. Jang, M.-W., Y.-H. Kim, N.-W. Park and S.-Y. Hong, 2012. Mapping paddy rice varieties using multi-temporal RADARSAT SAR images, Korean Journal of Remote Sensing, 28(6): 653-660. https://doi.org/10.7780/kjrs.2012.28.6.5
  14. Lee, J.-S., M.R. Grunes, T.L. Ainsworth, L.J. Du, D.L. Schuler and S.R. Cloude, 1999. Unsupervised classification using polarimetric decompositions and the complex wishart classifier, IEEE Transactions on Geoscience and Remote Sensing, 37(5): 2249-2258. https://doi.org/10.1109/36.789621
  15. Martínez, B. and M.A. Gilabert, 2009. Vegetation dynamics from NDVI time series analysis using the wavelet transform, Remote Sensing of Environment, 113(9): 1823-1842. https://doi.org/10.1016/j.rse.2009.04.016
  16. Muraki, S., 1993. Volume data and wavelet transforms, IEEE Computer Graphics and Applications, 13(4): 50-56. https://doi.org/10.1109/38.219451
  17. Park, N.W. and K.H. Chi, 2008. Integration of multitemporal/polarization C-band SAR data sets for land-cover classification, International Journal of Remote Sensing, 29(16): 4667-4688. https://doi.org/10.1080/01431160801947341
  18. Skriver, H., J. Schou, and W. Dierking, 2000. Landcover mapping using multitemporal, dualfrequency polarimetric SAR data, Proc. of 2000 International Geoscience and Remote Sensing Symposium, Honolulu, HI, Jul. 24-28, vol.1, pp. 331-333.
  19. Tan, C.-P., J.-Y. Koay, K.-S. Lim, H.-T. Ewe and H.-T. Chuah, 2007. Classification of multi-temporal SAR images for rice crops using combined entropy decomposition and support vector machine technique, Progress In Electromagnetics Research, 71: 19-39. https://doi.org/10.2528/PIER07012903
  20. Yoo, H.Y., K. Lee and B.D. Kwon, 2007. Application of the 3D discrete wavelet transformation scheme to remotely sensed image classification, Korean Journal of Remote Sensing, 23(5): 355-363. https://doi.org/10.7780/kjrs.2007.23.5.355
  21. Yoo, H.Y., K. Lee and B.D. Kwon, 2008. A comparative study of 3D DWT based spaceborne image classification for different types of basis function, Korean Journal of Remote Sensing, 24(1): 57-64. https://doi.org/10.7780/kjrs.2008.24.1.57
  22. Yoo, H.Y., K. Lee and B.D. Kwon, 2009. Quantitative indices based on 3D discrete wavelet transform for urban complexity estimation using remotely sensed imagery, International Journal of Remote Sensing, 30(23): 6219-6239. https://doi.org/10.1080/01431160902842359

피인용 문헌

  1. Classification of Multi-temporal SAR Data by Using Data Transform Based Features and Multiple Classifiers vol.31, pp.3, 2015, https://doi.org/10.7780/kjrs.2015.31.3.1