DOI QR코드

DOI QR Code

Automatic Estimation of Threshold Values for Change Detection of Multi-temporal Remote Sensing Images

다중시기 원격탐사 화상의 변화탐지를 위한 임계치 자동 추정

  • 박노욱 (한국지질자원연구원 지질자원정보센터) ;
  • 지광훈 (한국지질자원연구원 지질자원정보센터) ;
  • 이광재 (한국항공우주연구원 위성 정보처리그룹) ;
  • 권병두 (서울대학교 지구과학교육과)
  • Published : 2003.12.01

Abstract

This paper presents two methods for automatic estimation of threshold values in unsupervised change detection of multi-temporal remote sensing images. The proposed methods consist of two analytical steps. The first step is to compute the parameters of a 3-component Gaussian mixture model from difference or ratio images. The second step is to determine a threshold value using Bayesian rule for minimum error. The first method which is an extended version of Bruzzone and Prieto' method (2000) is to apply an Expectation-Maximization algorithm for estimation of the parameters of the Gaussian mixture model. The second method is based on an iterative thresholding algorithm that successively employs thresholding and estimation of the model parameters. The effectiveness and applicability of the methods proposed here were illustrated by two experiments and one case study including the synthetic data sets and KOMPSAT-1 EOC images. The experiments demonstrate that the proposed methods can effectively estimate the model parameters and the threshold value determined shows the minimum overall error.

이 논문은 다중시기 원격탐사 화상의 무감독 변화탐지를 위해 자동으로 임계치를 결정하는 두가지 방법을 제안하였다. 두 방법 모두 3성분 가우시안 혼합 확률 모델의 파라미터 추정과 베이지안 최소 오차 이론을 이용한 임계치 결정의 두 단계로 이루어져 있다. 첫 번째 방법은 Bruzzone and Prieto (2000)의 방법을 확장 적용한 것으로, 혼합 확률 모델의 파라미터 추정에 기대최대화 기법을 적용한다. 두 번째 제안 방법은 연속적으로 임계치 결정과 혼합 확률 모델의 파라미터 추정을 수행한다. 모의 화상과 KOMPSAT-1 EOC 화상에 적용한 결과, 제안한 두 기법 모두 효율적으로 모델 파라미터를 추정할 수 있었으며, 최소 오차를 보이는 임계치에 근사한 값을 추출할 수 있었다.

Keywords

References

  1. IEEE Transactions on Geoscience and Remote Sensing v.35 no.4 An iterative technique for the detection of land-cover transitions in multitemporal remote-sensing images Bruzzone,L.;S.B.Serpico
  2. IEEE Transactions on Geoscience and Remote Sensing v.38 no.3 Automatic analysis of the difference image for unsupervised change detection Bruzzone,L.;D.F.Prieto
  3. Photogrammetric Engineering and Remote Sensing v.67 no.2 Detecting the nature of change of machine learning algorithms Chan,J.C.W.;K.P.Chan;A.G.O.Yeh
  4. IEEE Transactions on Geoscience and Remote Sensing v.32 no.4 Processing of multitemporal Landsat TM imagery to optimize extraction of forest cover change features Coppin,P.R.;M.E.Bauer
  5. Journal of the Royal Statistical Society Series(B) v.39 no.1 Maximum likelihood from incomplete data via the EM algorithm Dempster,A.P.;N.M.Laird;D.B.Rubin
  6. Pattern Classification Duba,R.O.;P.E.Hart;D.G.Stork
  7. Introduction to Statistical Pattern Recognition Fukunaga,K.
  8. IEEE Transactions on Geoscience and Remote Sensing v.28 no.12 An assessment of YM imagery for land-cover change detection Fung,T.
  9. Photogrammetric Engineering and Remote Sensing v.54 no.10 The determination of optimal threshold levels for change detection using various accuracy indices Fung,T.;E.LeDrew
  10. Introductory Digital Image Processing: a Remote Sensing Perspective Jensen,J.R.
  11. International Journal of Remote Sensing v.19 no.6 Change vector analysis: a technique for the multispectral monitoring of land cover condition Johnson,R.D.;E.S.Kasischke
  12. Korean Journal of Remote Sensing v.12 no.3 Applications of principal component analysis and fuzzy set operation to change detection of urban environment using Landset data Lee,K.;S.M.Park;K.H.Chi
  13. Signal Processing Magazine v.13 no.6 The expectation-maxmization algorithm Moon,T.K.
  14. Photogrammetric Engineering and Remote Sensing v.66 no.7 Accuracy assessment curves for satellite-based change detection Morisette,J.T.;S.Khorram
  15. International Journal of Remote Sensing v.10 no.6 Digital change detection techniques using remotely-sensed data Singh,A.
  16. IEEE Transactions on Geoscience and Remote Sensing v.39 no.5 A change detection method for remotely sensed multispectral and multitemporal images using 3-D segmentation Yamamoto,T.;H.Hanaizumi;S.Chino