Advertisement

Change Detection by Classification of a Multi-temporal Image

  • Ben Gorte
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1737)

Abstract

Keeping track of changes in our environment is an important application of remote sensing. To express those changes in terms or thematic classes can be done by comparing classifications of different dates, which, however, has the disadvantage that classification errors and uncertainties are accumulated. Moreover, spectral properties of classes in a dynamic environment may be different from those in a stable situation. This paper elaborates on the statistical classification of multi-temporal data sets, using a set of thematic classes that includes class-transitions. To handle the increased complexity of the classification, refined probability estimates are presented, which pertain to image regions rather than to the entire image. The required subdivision of the area could be defined by ancillary data in a geographic information system, but can also be obtained by multi-temporal image segmentation. A case study is presented where land-cover is monitored over an 11-years period in an area in Brazil with drastic deforestation.

Keywords

Feature Vector Normalize Difference Vegetation Index Feature Space Change Detection Class Label 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Clevers, 1988.
    J.G.P.W. Clevers, The application of a weigted infrared-red vegetation index for extimating leaf area index by correcting for soil moisture, Remote Sens. Environ. 29, pp. 25–37.Google Scholar
  2. Cross et al, 1988._ A.M. Cross, D.C. Mason and S.J. Dury. Segmentation of remotely-sensed images by a split-and-merge process. IJRS 9(8), pp. 1329–1345.Google Scholar
  3. Disperati et al, 1998._ Disperati L., G. Righini, M. Bocci, P.L. Pantozzi, A.P. Fiori, S. Kozciac and A.C. Paranhos Filho, Land cover changes in the Rio Verdo de Mato Grasso region (Pantanal, Mato Grasso do Sul, Brasil) as detected through remote sensing and GIS analysis. Technical report, Univ. of Siena (I).Google Scholar
  4. Duda and Hart, 1973.
    R.O. Duda and P.E. Hart, Pattern classification and scene analysis. John Wiley and Sons, New York, 465 pp. 1973.MATHGoogle Scholar
  5. Fu and Mui, 1981.
    Fu and Mui, A survey on image segmentation, Pattern Recognition, 13:3–16, 1981.CrossRefMathSciNetGoogle Scholar
  6. Gorte, 1996.
    B.G.H. Gorte. Multi-spectral quadtree based image segmentation. IAPRS vol. XXXI B3, Vienna, pp. 251–256.Google Scholar
  7. Gorte, 1998.
    B.G.H. Gorte (1998). Probabilistic segmentation of remotely sensed images, Ph.D. thesis,Wageningen Agric. Univ., the Netherlands.Google Scholar
  8. Gorte and Stein, 1998.
    B.G.H. Gorte and A. Stein (1998), Bayesian Classification and Class Area Estimation of Satellite Images using Stratification, IEEE Trans. Geosci. Remote Sens., Vol. 36, No. 3, May 1998, pp. 803–812.CrossRefGoogle Scholar
  9. Haralick and Shapiro, 1985.
    R.M. Haralick and L.G. Shapiro. Survey: Image segmentation techniques. Computer, Vision, Graphics and Image Processing, 29, 1985, pp 100–132.CrossRefGoogle Scholar
  10. Hernandez Filho et al, 1995._ Hernandez Filho P., Ponzoni F.J., Pereira M.N., Pott A., Pott V.J. and Silva M.P (1995) Mapeamento da vegetação e de uso da terra de parte a bacia do Alto Taquari (MS) considerando o procedimentode analise visual de imagens TM/LANDSAT e HRV/SPOT. In: Encontro sobre sensoriamento remoto aplicado a estudos no Pantanal-Livro de Resumas. Corumbà-MS, 9-12 de Outobro de 1995, 137–139.Google Scholar
  11. Jensen, 1986.
    J.R. Jensen, Introductory digital image processing: a remote sensing perspective, Prentice-Hall.Google Scholar
  12. Lillesand and Kieffer, 1994.
    T.M. Lillesand and R.W. Kiefer, Remote sensing and image interpretation-3rd edition, Wiley, 745 pp.Google Scholar
  13. Lyon et al, 1998._ J.G. Lyon, Ding Yuan, R.S. Lunetta and C.D. Elvidge, A change detection experiment using vegetation indices. Photogrammetric Engineering & Remote Sensing, Vol. 64, No. 2, February 1998, pp. 143–150.Google Scholar
  14. Middelkoop and Janssen, 1991.
    H. Middelkoop H. and L.L.F. Janssen. Implementation of temporal relationships in knowledge based classification or satellite images. Photogrammetric Engineering & Remote Sensing, Vol. 57, No. 7, pp. 937–945.Google Scholar
  15. Mulder and Middelkoop, 1990.
    N.J. Mulder and H. Middelkoop (1990). Parametric versus nonparametric maximum likelihood classification. Proc. ISPRS Comm. III, Wuhan.Google Scholar
  16. Pavlidis, 1986.
    T. Pavlidis, A critical survey of image analysis methods, IAPR-8, 1986, pp502–511.Google Scholar
  17. Ripley, 1996.
    B.D. Ripley. Pattern recognition and neural networks, Cambridge University Press.Google Scholar
  18. Strahler, 1980.
    A.H. Strahler. The use of prior probabilities in maximum likelihood classification of remotely sensed data. Remote Sensing of Environment, no. 10, pp. 135–163.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Ben Gorte
    • 1
  1. 1.International Institute for Aerial Survey and Earth Sciences (ITC)EnschedeThe Netherlands

Personalised recommendations