Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회지)

Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회)
권호 표지

A Study on Automatic Coregistration and Band Selection of Hyperion Hyperspectral Images for Change Detection

변화탐지를 위한 Hyperion 초분광 영상의 자동 기하보정과 밴드선택에 관한 연구

  • 김대성 (서울대학교 건설환경공학부) ;
  • 김용일 (서울대학교 건설환경공학부) ;
  • 어양담 (국방과학연구소 기술연구본부)
  • Published : 2007.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study focuses on co-registration and band selection, which are one of the pre-processing steps to apply the change detection technique using hyperspectral images. We carried out automatic co-registration by using the SIFT algorithm which performance was already established in the computer vision fields, and selected the bands fur change detection by estimating the noise of image through the PIFs reflecting the radiometric consistency. The EM algorithm was also applied to select the band objectively. Hyperion images were used for the proposed techniques, and non-calibrated bands and striping noises contained in Hyperion image were removed. Throughout the results, we could develop the reliable co-registration procedure which coincided with accuracy within 0.2 pixels (RMSE) for change detection, and verified that band selection depending on the visual inspection could be objective by extracting the PIFs.

본 연구는 초분광 영상을 이용한 변화탐지 기법의 전처리 과정 중 하나인 영상간 기하보정과 밴드선택에 초점을 맞추고 있다. 최근 그 성능이 입증된 SIFT(Scale-Invariant Feature Transform) 기법을 이용하여 자동화된 기하보정을 수행하였으며, 분광정보의 불변 특성을 반영하는 PIF(Pseudo-Invariant Feature)를 추출하여 영상의 잡음을 추정함으로써, 변화탐지를 위한 유효 밴드를 선택하였다. 또한, 기대최대화(Expectation-Maximization) 기법을 이용한 객관적인 밴드선택 방법을 구현하였다. 제안된 기법들을 실제 적용하기 위해 Hyperion 영상을 사용하였으며, 영상에 나타나는 보정되지 않은 밴드 및 Striping 잡음의 특성을 부가적으로 제거하였다. 결과를 통해, 변화탐지를 위한 최소한의 요구조건인 0.2화소 이내의 정확도(RMSE)를 만족하는 신뢰도 높은 기하보정을 수행할 수 있었으며, 시각적인 판단에 의존하던 밴드선택을 PIF를 통해 객관화할 수 있음을 확인하였다.

Keywords

References

  1. 김대성, 김용일 (2006), 화소간 유사도 측정 기법을 이용한 하이퍼스펙트럴 데이터의 무감독 변화탐지에 관한 연구, 춘계학술대회 발표회 논문집, 한국측량학회, pp. 243-248
  2. 김선화, 이규성, 마정림, 국민정 (2005), 초분광 원격탐사의 특성, 처리기법 및 활용 현황, 대한원격탐사학회지, 대한원격탐사학회, Vol. 21, No.4, pp. 341-369 https://doi.org/10.7780/kjrs.2005.21.4.341
  3. 한동엽, 김대성, 김용일 (2006), 극단화소를 이용한 Hyperion 데이터의 노이즈 밴드제거, 원격탐사학회지, 대한원격탐사학회, Vol. 22, No.4, pp. 275-284 https://doi.org/10.7780/kjrs.2006.22.4.275
  4. 한동엽, 김대성, 이재빈, 오재홍, 김용일 (2006), SIFT 기법을 이용한 중저해상도 위성영상간의 자동 기하보정, 한국측량학회지, 한국측량학회, Vol. 24, No.5, pp. 409-416
  5. Bajcsy, P., and Groves, P. (2004), Methodology for Hyper-spectral Band Selection, Photogrammetric Engineering & Remote Sensing, ASPRS, Vol. 70, No.7, pp. 793-802 https://doi.org/10.14358/PERS.70.7.793
  6. Barry, P. (2001), EO-1/Hyperion Science Data User's Guide. TRW Space, Defense and Information Systems
  7. Bentoutou, Y., Taleb, N., Kpalma, K., and Ronsin, J. (2005), An Automatic Image Registration for Applications in Remote Sensing, IEEE Transactions on Geoscience and Remote Sensing, IEEE, Vol. 43, No.9, pp. 2127-2137 https://doi.org/10.1109/TGRS.2005.853187
  8. Bisun, D., Tim R. M., Tom, G. V., Tom, G. V. N., David, L. B. J., and Jay, S. P. (2003), Preprocessing EO-1 Hyperion Hyperspectra1 Data to Support the Application of Agricultural Indexes, IEEE Transactions on Geoscience and Remote Sensing, IEEE, Vol. 41, No.6, pp. 1246-1259
  9. Bruzzone, L. and Cossu, R. (2003), An Adaptive Approach to Reducing Registration Noise Effects in Unsupervised Change Detection, IEEE Transactions on Geocience and Remote Sensing, IEEE, Vol. 41, No. 11, pp. 2455-2465 https://doi.org/10.1109/TGRS.2003.817268
  10. Bruzzone, L. and Priato, D. F. (2000), Automatic Analysis of the Difference Image for Unsupervised Change Detection, IEEE Transactions on Geocience and Remote Sensing, IEEE, Vol. 38, No.2, pp. 1171-1182 https://doi.org/10.1109/36.843009
  11. Dai, X., and Khorram, S. (1998), The Effects of Image Misregistration on the Accuracy of Remotely Sensed Change Detection, IEEE Transactions on Geoscience and Remote Sensing, IEEE, Vol. 36, No.5, pp. 1566-1577 https://doi.org/10.1109/36.718860
  12. Dart, B., McVicar, T. R., Niel, T. G. V., Jupp, D. L. B., and Pearlman, J. S. (2003), Preprocessing EO-1 Hyperion Hyperspectral Data to Support the Application of Agricultural Indexes, IEEE Transactions on Geoscience and Remote Sensing, IEEE, Vol. 41, No.6, pp. 1246-1259 https://doi.org/10.1109/TGRS.2003.813206
  13. Du, Y., Teillet, P. M., and Cihlar, J. (2002), Radiometric Normalization of Multitemporal High-resolution Satellite Images with Quality Control for Land Cover Change Detection, Remote Sensing of Environment, ISRSE, Vol. 82, pp. 123-134 https://doi.org/10.1016/S0034-4257(02)00029-9
  14. EO-1 Homepage, http://eol.usgs.gov/imagePreviews.php
  15. Frank, M., and Canty, M. (2003), Unsupervised Change Detection for Hyperspectral Images, JPL Publication, 8th publication
  16. Goodenough, D. G., Dyk, A., Niemann, K. O., Pearlman, J. S., Chen, H., Han, T., Murdoch, M., and West, C. (2003), Processing Hyperion and ALI for Forest Classification, IEEE Transactions on Geoscience and Remote Sensing, IEEE, Vol. 41, No.6, pp. 1321-1331 https://doi.org/10.1109/TGRS.2003.813214
  17. Han, T., Goodenough, D. G., Dyk, A., and Love, J. (2002), Detection and Correction of Abnormal Pixels in Hyperion Images, in Proc. IGARSS, Vol. 3, Toronto, Canada, pp. 1327-1330
  18. Janzen, D. T., Fredeen, A. L., and Wheate, R. D. (2006), Radiometric Correction Techniques and Accuracy Assessment for Landsat TM Data in Remote Forested Regions, Canadian Journal of Remote Sensing, Vol. 32, No.5, pp. 330-340 https://doi.org/10.5589/m06-028
  19. Jensen, J. R. (2005), Introductory Digital Image Processing A Remote Sensing Perspective, 3rd Edition, Prentice Hall, NY, USA, pp. 467-494
  20. Landgrebe, D. A. (2003), Signal Theory Methods in Multispectral Remote Sensing, Wiley-Interscience, NJ, USA, pp. 273-321
  21. Lowe, D. G. (2004), Distinctive Image Features from Scaleinvariant Keypoints, International Journal on Computer Vision, IJCV, Vol. 60, No.2, pp. 91-110 https://doi.org/10.1023/B:VISI.0000029664.99615.94
  22. Lu, D., Mausel, P., Brondizio, E and Moran, E. (2004), Change Detection techniques, International Journal of Remote Sensing, IJRS, Vol. 25, No. 12, pp. 2365-2407 https://doi.org/10.1080/0143116031000139863
  23. Moon, T. K. (1996), The Expectration- Maximization Algorithm, IEEE Signal Processing Magazine, IEEE, Vol. 13, No.6, pp. 47-60 https://doi.org/10.1109/79.543975
  24. Nielsen, A. A., and Canty, M. J. (2005), Multi- and Hyperspectral Remote Sensing Change Detection with Generalized Difference Images by the IR-MAD Method, International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, IEEE, Mississippi, USA, pp. 169-173
  25. Singh, A. (1989), Digital Change Detection Techniques Using Remotely Sensed Data, International Journal of Remote Sensing, IJRS, Vol. 10, pp. 989-1003 https://doi.org/10.1080/01431168908903939
  26. Yoon, Y., and Kim, Y. (2007), Application of Hyperion Hyperspectral Remote Sensing Data for Wildfire Fuel Mapping, Korean Journal of Remote Sensing, KSRS, Vol. 23, No.1, pp. 21-32 https://doi.org/10.7780/kjrs.2007.23.1.21
  27. Zitova, B., and Flusser, J. (2003), Image Registration Methods: a Survey, Image and Vision Computing, Vol. 21, No. 11, pp. 977-1,000 https://doi.org/10.1016/S0262-8856(03)00137-9