Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Change Detection Using Spectral Unmixing and IEA(Iterative Error Analysis) for Hyperspectral Images

IEA(Iterative Error Analysis)와 분광혼합분석기법을 이용한 초분광영상의 변화탐지

  • Song, Ahram (Department of Civil and Environmental Engineering, Seoul National University) ;
  • Choi, Jaewan (School of Civil Engineering, Chungbuk National University) ;
  • Chang, Anjin (Civil Engineering, Texas A&M University-Corpus Christi) ;
  • Kim, Yongil (Department of Civil and Environmental Engineering, Seoul National University)
  • 송아람 (서울대학교 건설환경공학부) ;
  • 최재완 (충북대학교 토목공학과) ;
  • 장안진 (텍사스 A&M - 코퍼스 크리스티 토목공학과) ;
  • 김용일 (서울대학교 건설환경공학부)
  • Received : 2015.06.09
  • Accepted : 2015.09.30
  • Published : 2015.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Various algorithms such as Chronochrome(CC), Principle Component Analysis(PCA), and spectral unmixing have been studied for hyperspectral change detection. Change detection by spectral unmixing offers useful information on the nature of the change compared to the other change detection methods which provide only the locations of changes in the scene. However, hyperspectral change detection by spectral unmixing is still in an early stage. This research proposed a new approach to extract endmembers, which have identical properties in temporally different images, by Iterative Error Analysis (IEA) and Spectral Angle Mapper(SAM). The change map obtained from the difference of abundance efficiently showed the changed pixels. Simulated images generated from Compact Airborne Spectrographic Imager (CASI) and Hyperion were used for change detection, and the experimental results showed that the proposed method performed better than CC, PCA, and spectral unmixing using N-FINDR. The proposed method has the advantage of automatically extracting endmembers without prior information, and it could be applicable for the real images composed of many materials.

초분광영상을 이용한 변화탐지 기법으로는 Chronochrome(CC), Principal Component Analysis(PCA), 분광혼합분석(spectral unmixing) 등이 있다. 특히, 분광혼합분석을 이용한 변화탐지는 변화객체의 위치 정보뿐만 아니라 변화의 속성까지 분석할 수 있다는 점에서 매우 효과적이나, 분광혼합분석을 활용한 초분광영상의 변화탐지 연구는 여전히 초기단계에 머물러 있다. 본 연구에서는 분광혼합분석을 이용한 효과적인 변화탐지를 위하여 Iterative Error Analysis(IEA)와 Spectral Angle Mapper(SAM) 등을 활용하여 두 영상에서 변화지역을 설명할 수 있는 동일한 endmember를 결정하였으며, 점유비율의 차영상을 통하여 변화지역을 추출하였다. 제안기법의 적용성을 평가하기 위하여 임의의 변화지역을 포함한 Compact Airborne Spectrographic Imager(CASI) 및 Hyperion 모의영상에 대한 변화탐지를 수행하였다. 실험결과, 제안기법이 기존의 CC, PCA, N-FINDR를 이용한 분광혼합분석보다 효과적으로 변화지역을 추출할 수 있는 것으로 나타났다. 본 연구의 제안기법은 사전정보 없이 자동으로 동일한 endmember를 추출할 수 있는 장점을 갖기 때문에 다양한 피복물질로 구성된 영상의 변화탐지에 효과적으로 활용될 것이다.

Keywords

References

  1. Alp, E. and A. Plaza, 2015. Informative change detection by unmixing for hyperspectral images, IEEE Geoscience Remote Sensing Letters, 12(6): 1252-1256. https://doi.org/10.1109/LGRS.2015.2390973
  2. Han, D., D. Kim, and Y. Kim, 2006. The removal of noisy bands for hyperion data using extrema, Korean Journal of Remote Sensing, 22(4): 275-284 (In Korean with English abstact). https://doi.org/10.7780/kjrs.2006.22.4.275
  3. Hsieh, C.C., P.F. Hsieh, and C.W. Lin, 2006. Subpixel change detection based on abundance and slope features, Geoscience and Remote Sensing Symposium, IGARSS 2006, Denver, CO, 775-778.
  4. Kim, D. and M. Pyen, 2011. Extraction of changed pixels for Hyperion hyperspectral images using range average based buffer zone concept, Journal of the Korean Society of Subveying Geodecy, Photogrammetry and Carteography, 29(5): 487-496 (In Korean with English abstact). https://doi.org/10.7848/ksgpc.2011.29.5.487
  5. Kim, S. and C. Yang, 2015. Current status of hyperpsectral data processing techniques for monitoring coastal water, Korean Association of Geographic Information Studies, 18(1): 48-63. https://doi.org/10.11108/kagis.2015.18.1.048
  6. Kim, S., K. Lee, J. Ma, and M. Kook, 2005. Current status of hyperspectral remote sensing: principle, data processing techniques, and applications, Korean Journal of Remote Sensing, 21(4): 341-369. https://doi.org/10.7780/kjrs.2005.21.4.341
  7. Lee, J. and K. Lee, 2003. Analysis of forest cover information extracted by spectral mixture analysis, Korean Journal of Remote sensing, 19(6): 411-419 (In Korean with English abstact). https://doi.org/10.7780/kjrs.2003.19.6.411
  8. Molina, I., E. Martinez, A. Arquero, G. Pajares, and J. Sanchez, 2012. Evaluation of a change detection methodology by means of binary thresholding algorithms and informational fusion processes, Sensors, 12(3): 3528-3561. https://doi.org/10.3390/s120303528
  9. Neville, R.A., K. Staennz, T. Szeredi, J. Lefebvre, and P. Hauff, 1999. Automatic endmember extraction from hyperspectral data for mineral exploration, Proc. of 21 st Canada Symposium on Remote Sensing, Ottawa, ON, Canada, pp. 21-24.
  10. Roberts, D.A., M. Gardner, R. Church, S. Ustin, G. Scheer, and R.O. Green, 1998. Mapping Chaparral in the Santa Monica Mountains Using Multiple Endmember Spectral Mixture Models, Remote Sensing of Environment, 44: 255-269.
  11. Snchez, S., A. Paz, and A. Plaza, 2011. A real time spectral unmixing using iterative error analysis on commodity graphics processing units. Proc. of IEEE International Geoscience and Remote Sensing Symposyium (IGARSS 2011), Vancouver, BC, Canada, 24-29 July 2011, pp. 1767-1770.
  12. Schaum, A. and A. Stocker, 1998. Long-interval chronochrome target detection, Proc. of International Symposium on Spectral Sensing Research, San Diego, CA, USA, 1998.
  13. Schaum, A. and A. Stocker, 2004. Hyperspectral change detection and supervised matched filtering based on covariance equalization, Proceedings SPIE 2004, 5425: 77-90.
  14. Song, A., A. Chang, J. Choi, S. Choi, and Y. Kim, 2015. Automatic extraction of optimal endmembers from airborne hyperspectral imagery using iterative error analysis (IEA) and spectral discrimination measurements, Sensors, 15(2): 2593-2613. https://doi.org/10.3390/s150202593
  15. Vikrant, G. and A.P. Pushp, 2014. Survey on various change detection techniques for hyperspectral images, International Journal of Advanced Research in Computer Science and Software Engineering, 4(8): 851-855.
  16. Vongsy, K.M., 2007. Change detection methods for hyperspectral imagery, Master of Science in Engineering, Wright State University, Electrical Engineering.
  17. Wu, C., B. Du, and L. Zhang, 2013. A subspace-based change detection method for hyperspectral images, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2): 815-830. https://doi.org/10.1109/JSTARS.2013.2241396

Cited by

  1. An Unsupervised Algorithm for Change Detection in Hyperspectral Remote Sensing Data Using Synthetically Fused Images and Derivative Spectral Profiles vol.2017, pp.1687-7268, 2017, https://doi.org/10.1155/2017/9702612
  2. Iterative Error Analysis 기반 분광혼합분석에 의한 초분광 영상의 표적물질 탐지 기법 vol.33, pp.5, 2015, https://doi.org/10.7780/kjrs.2017.33.5.1.8