Artificial Intelligence Review

, Volume 25, Issue 1–2, pp 161–178

Using Dempster–Shafer to incorporate knowledge into satellite image classification

Article

Abstract

Remote sensing imaging techniques make use of data derived from high resolution satellite sensors. Image classification identifies and organises pixels of similar spatial distribution or similar statistical characteristics into the same spectral class (theme). Contextual data can be incorporated, or ‘fused’, with spectral data to improve the accuracy of classification algorithms. In this paper we use Dempster–Shafer’s theory of evidence to achieve this data fusion. Incorporating a Knowledge Base of evidence within the classification process represents a new direction for the development of reliable systems for image classification and the interpretation of remotely sensed data.

Keywords

Classification Evidential theory Remote sensing Maximum likelihood 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Anand S, Scotney B, Tan M, McClean S, Bell D, Hughes J and Magill I (1997). Designing a kernel for data mining. IEEE Expert 12: 65–74 CrossRefGoogle Scholar
  2. 2.
    Benediktsson J, Swain P and Ersoy O (1990). Neural network approaches versus statistical methods in classification of multisource remote sensing data. IEEE Trans Geosci Remote Sens 28(4): 540–552 CrossRefGoogle Scholar
  3. 3.
    Bourman C and Shapiro M (1994). A multiscale random field model for bayesian image segmentation. IEEE Trans Image Process 3(2): 162–177 CrossRefGoogle Scholar
  4. 4.
    Cheeseman P and Stutz J (1996). Bayesian classification: theory and results. In: Fayyad, U, Piatetsky, S, Smyth, P and Uthurusamy, R (eds) Advances in knowledge Discovery and Data Mining, pp 153–189. AAAI/MIT Press, Cambridge, MA Google Scholar
  5. 5.
    Congalton R (2001). Accuracy assessment and validation of remotely sensed and other spatial information. Int J Wildland Fire 10: 321–328 CrossRefGoogle Scholar
  6. 6.
    Debeir O, Latinne P and Van Den Steen I (2001). Remotes sensing classification of spectral, spatial and contextual data using multiple classifier systems. Image Anal Stereo 1(20): 584–589 Google Scholar
  7. 7.
    Dempster A (1968). A generalisation of Bayesian inference. J R Stat Soc B 30: 205–247 MathSciNetGoogle Scholar
  8. 8.
    Dengsheng L and Qihao W (2005). Urban classification using full spectral information of Landsat ETM + Imagery in Marion county, Indiana. P E & RS 71(11): 1275–1284 Google Scholar
  9. 9.
    Deren LI, Kaichang DI, Deyi LI (2000) Land use classification of remote sensing image with GIS data based on spatial data mining techniques. Int Arch Photogrametric Remote Sens XXXIII (Part B3)Google Scholar
  10. 10.
    Dhodhi M, Saghri J, Ahmed I and Ul-Mustafa R (1999). D-ISODATA: a distributed algorithms for unsupervised classification of remotely sensed data on network of workstations. J Parallel Distrib Comput 59: 280–301 CrossRefGoogle Scholar
  11. 11.
    Duda T and Canty M (2002). Unsupervised classification of satellite imagery: choosing a good algorithm. Int J Remote Sens 23(11): 2193–2212 CrossRefGoogle Scholar
  12. 12.
    Egmont-Peterson M, De Ridder D and Handles H (2002). Image processing with neural networks—a review. Pattern Recognit 35: 2279–2301 CrossRefGoogle Scholar
  13. 13.
    Fangju W (1999). Fuzzy supervised classification of remotely sensing images. IEEE Trans Geosci Remote Sens 28(2): 194–201 Google Scholar
  14. 14.
    Gibson P and Power C (2000). Introductory remote sensing, digital image processing applications. Taylor and Francis Group, Routledge Google Scholar
  15. 15.
    Gorte B and Stein A (1998). Bayesian classification and class area estimation of satellite images using stratification. IEEE Trans Geosci Remote Sens 36(3): 803–812 CrossRefGoogle Scholar
  16. 16.
    Guan J and Bell D (1991). Evidence theory and its applications. Elsevier Science Inc., New York MATHGoogle Scholar
  17. 17.
    Guan J and Bell D (1992). Evidence theory and its applications. Elsevier Science Inc., New York MATHGoogle Scholar
  18. 18.
    H’egarat-Mascle S, Richard D Le and Ottl’e C (2003). Multi-scale data fusion using Dempster–Shafer evidence theory. Integr Comput Aided Eng 10: 9–22 Google Scholar
  19. 19.
    Huadong W, Siegel M, Stiefelhagen R and Jie Y (2002). Sensor fusion using Dempster–Shafer theory. Proc 19th IEEE Instrum Meas Technol Conf 1: 7–12 Google Scholar
  20. 20.
    Jackson Q and Landgrebe D (2002). Adaptive Bayesian contextual classification based on Markov random fields. IEEE Trans Geosci Remote Sens 40(11): 2454–2463 CrossRefGoogle Scholar
  21. 21.
    Jensen J (1996). Introductory digital image Processing, a remote sensing prospective. Prentice Hall, Englewood cliffs Google Scholar
  22. 22.
    Jia X and Richards J (1994). Efficient maximum likelihood classification for image imaging spectrometer data sets. IEEE Trans Geosci Remote Sens 3(2): 274–281 Google Scholar
  23. 23.
    Lillesand TM and Kiefer RW (2000). Remote sensing and image interpretation. John Wiley & Sons, New York Google Scholar
  24. 24.
    Mascle S, Bloch I and Vidal-Madjar D (1997). Application of Dempster–Shafer evidence theory to unsupervised classification in multisource remote sensing. IEEE Trans Geosci Remote Sens 35(4): 1018–1031 CrossRefGoogle Scholar
  25. 25.
    Mather P (1999). Computer processing of remotely-sensed images analysis, An Introduction,. John Wiley & Sons, Chichester Google Scholar
  26. 26.
    McClean S and Scotney B (1997). Using evidence theory for the integration of distributed databases. Int J Intell Syst 12: 763–776 CrossRefGoogle Scholar
  27. 27.
    Murai H and Omatsu S (1997). Remote sensing image analysis using neural and knowledge-based processing. Int J Remote Sens 18(4): 811–828 CrossRefGoogle Scholar
  28. 28.
    Richards J and Jia X (1999). Remote sensing digital image analysis an Introduction. Springer, New York Google Scholar
  29. 29.
    Shafer G (1982). Belief functions and parametric models. J R Stat Soc B 44: 322–352 MATHMathSciNetGoogle Scholar
  30. 30.
    Torsun I (1995). Foundation of intelligent Knowledge-based systems. Academic Press, San Diego Google Scholar
  31. 31.
    U.S. Geological Survey Web Site (2006) http://seamless.usgs.gov/. Cited 30 Nov 2006
  32. 32.
    Warrender C and Augusteijn M (1999). Fusion of image classification using Bayesian techniques with Markov random fields. Int J Remote Sens 20(10): 1987–2002 CrossRefGoogle Scholar
  33. 33.
    Engemann K, Filev D and Yager (1995). On the concept of immediate probabilities. Int J Intell Syst 10: 373–397 MATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2007

Authors and Affiliations

  1. 1.School of Computing and Information Engineering, Faculty of EngineeringUniversity of UlsterColeraineNorthern Ireland, UK

Personalised recommendations