Korean Journal of Remote Sensing (대한원격탐사학회지)

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

DOI QR Code

Hyperspectral Target Detection by Iterative Error Analysis based Spectral Unmixing

Iterative Error Analysis 기반 분광혼합분석에 의한 초분광 영상의 표적물질 탐지 기법

  • Received : 2017.10.11
  • Accepted : 2017.10.16
  • Published : 2017.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a new spectral unmixing based target detection algorithm is proposed which adopted Iterative Error Analysis as a tool for extraction of background endmembers by using the target spectrum to be detected as initial endmember. In the presented method, the number of background endmembers is automatically decided during the IEA by stopping the iteration when the maximum change in abundance of the target is less than a given threshold value. The proposed algorithm does not have the dependence on the selection of image endmembers in the model-based approaches such as Orthogonal Subspace Projection and the target influence on the background statistics in the stochastic approaches such as Matched Filter. The experimental result with hyperspectral image data where various real and simulated targets are implanted shows that the proposed method is very effective for the detection of both rare and non-rare targets. It is expected that the proposed method can be effectively used for mineral detection and mapping as well as target object detection.

본 연구에서는 탐지하고자 하는 표적신호를 초기 엔드멤버로 하여 Iterative Error Analysis를 통해 배경물질들의 반사 스펙트럼을 순차적으로 엔드멤버로 추출하고, 추출된 엔드멤버들을 이용하여 분광 혼합분석함으로써 표적물질의 분포를 탐지하는 새로운 초분광 표적탐지 기법을 제안한다. 제안된 기법에서는 표적물질에 대한 점유율의 변화가 주어진 문턱값보다 작아질 때 엔드멤버 추출을 위한 반복을 멈추게 된다. 이 기법은 Orthogonal Subspace Projection과 같은 모델 기반 표적 탐지기법들과 달리 사전에 엔드멤버들을 확보해야 할 필요가 없으며, Matched Filter와 같은 확률론적 표적 탐지 기법들과 달리 배경 전체를 하나의 신호로 특징화하지 않기 때문에 표적의 희소성 여부에 의한 영향을 받지 않는다는 장점을 가지고 있다. 실제 항공 초분광 영상자료 및 다양한 인공 표적물질들이 삽입된 모의 초분광 영상자료를 이용한 실험 결과, 제안된 방법이 희소 및 비 희소 표적의 탐지에 매우 효과적임이 확인되었다. 제안된 방법은 표적 물체 탐지뿐만 아니라 광물, 오염물질 등 자원 및 환경 분야에서 다양한 피복 물질을 탐지하는데 효과적으로 사용될 수 있을 것으로 기대된다.

Keywords

References

  1. Akhter, M. A., R. Heylen, and P. Scheunders, 2015. A Geometric Matched Filter for Hyperspectral Target Detection and Partial Unmixing, IEEE Geoscience Remote Sensing Letters, 12(3): 661-665. https://doi.org/10.1109/LGRS.2014.2355915
  2. Bedini, E., 2011. Mineral Mapping in the Kap Simpson, Central EAST Greenland, Using HyMap and ASTER Remote Sensing Data, Advance in Space Research, 47(1): 60-73. https://doi.org/10.1016/j.asr.2010.08.021
  3. Boardman, J. W., F. A. Kruse, and R. O. Green, 1995. Mapping target signatures via partial unmixing of AVIRIS data, Proc. of Summaries 5th Annual JPL Airborne Geoscience Workshop, Pasadena, CA, Jan. 23-26, vol. 1, pp. 11-14.
  4. Chang, A., Y. Kim, S. Choi, D. Han, J. Choi, Y. Kim, Y. Han, H. Park, B. Wang, and H. Lim, 2013. Construction and Data Analysis of Test-bed by Hyperspectral Airborne Remote Sensing, Korean Journal of Remote Sensing, 29(2): 161-172 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2013.29.2.1
  5. Choi, J., D. Kim, B Lee, Y. Kim, and Y. Yun, 2006. Hyperspectral Image Fusion Algorithm Based on Two-Stage Spectral Unmixing Method, Korean Journal of Remote Sensing, 22(4): 295-304 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2006.22.4.295
  6. Funk, C. C., J. Theiler, D. A. Roberts, and C. C. Borel, 2000. Clustering to improve matched filter detection of weak gas plumes in hyperspectral thermal imagery, IEEE Transactions on Geoscience and Remote Sensing, 39(7): 1410-1420.
  7. Harsanyi, J. C. and C. I. Chang, 1994. Hyperspectral image classification and dimensionality reduction: An orthogonal subspace projection, IEEE Transactions on Geoscience and Remote Sensing, 32(4): 779-785. https://doi.org/10.1109/36.298007
  8. Daniel C. Heinz and C. I. Chang, 2001. Fully Constrained Least Squares Linear Spectral Mixture Analysis Method for Material Quantification in Hyperspectral Imagery, IEEE Transactions on Geoscience and Remote Sensing, 39(3): 529-545. https://doi.org/10.1109/36.911111
  9. Kim, K., 2015. Study on Improving Hyperspectral Target Detection by Target Signal Exclusion in Matched Filtering, Korean Journal of Remote Sensing, 31(5): 433-440 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2015.31.5.7
  10. Manolakis, D., D. Marden, and G. Shaw, 2003. Detection algorithms for hyperspectral imaging applications, Lincoln Laboratory Journal, 14(1): 79-116.
  11. Matteoli, Y. S., N. Acito, M. Diana, and G. Corsini, 2010. An automatic approach to adaptive local background estimation and suppression in hyperspectral target detection, IEEE Transactions on Geoscience and Remote Sensing, 49(2): 790-800. https://doi.org/10.1109/TGRS.2010.2065235
  12. Neville, R. A., K. Staennz, T. Szeredi, J. Lefebvre, and P. Hauff, 1999. Automatic endmember extraction from hyperspectral data for mineral exploration, Proc. of 21st Canada Symposium on Remote Sensing, Ottawa, ON, Canada, Jun. 21-24, pp. 21-24.
  13. Shin, J. and K. Lee, 2012. Comparative Analysis of Target Detection Algorithms in Hyperspectral Image, Korean Journal of Remote Sensing, 28(4): 369-392 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2012.28.4.3
  14. Son, Y., K. Kim, and W. Yoon, 2015. A Review of Remote Sensing Techniques and Applications for Geoscience and Mineral Resources, Journal of The Korean Society of Mineral and Energy Resources Engineers, 52(4): 429-457 (in Korean with English abstract). https://doi.org/10.12972/ksmer.2015.52.4.429
  15. Song, A., J. Choi, A. Chang, and Y. Kim, 2015. Change Detection Using Spectral Unmixing and IEA(Iterative Error Analysis) for Hyperspectral Images, Korean Journal of Remote Sensing, 31(5): 361-370 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2015.31.5.1
  16. Song, A., Y. Han, Y. Kim, and Y. Kim, 2014. Spectral Mixture Analysis Using Modified IEA Algorithm for Forest Classification, Korean Journal of Remote Sensing, 30(2): 219-226 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2014.30.2.5