Applied Intelligence

, Volume 18, Issue 2, pp 215–234

Change Detection in Overhead Imagery Using Neural Networks

  • Chris Clifton
Article
  • 128 Downloads

Abstract

Identifying interesting changes from a sequence of overhead imagery—as opposed to clutter, lighting/seasonal changes, etc.—has been a problem for some time. Recent advances in data mining have greatly increased the size of datasets that can be attacked with pattern discovery methods. This paper presents a technique for using predictive modeling to identify unusual changes in images. Neural networks are trained to predict “before” and “after” pixel values for a sequence of images. These networks are then used to predict expected values for the same images used in training. Substantial differences between the expected and actual values represent an unusual change. Results are presented on both multispectral and panchromatic imagery.

change detection overhead imagery neural networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    R.L. Lillestrand, “Techniques for change detection,” IEEE Transactions on Computers, vol. 21, no.7, pp. 654–659, 1972.Google Scholar
  2. 2.
    I. Niemeyer, M. Canty, and D. Klaus, “Unsupervised change detection techniques using multispectral satellite images,” in Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’99), 1999, pp. 327–329.Google Scholar
  3. 3.
    S. Gopal and C. Woodcock, “Remote sensing of forest change using artificial neural networks,” IEEE Transactions on Geoscience and Remote Sensing, vol. 34, no.2, pp. 398–404, 1996.Google Scholar
  4. 4.
    P.J. Deer, “Digital change detection techniques: Civilian and military applications,” in ISSSR-95, 1995.Google Scholar
  5. 5.
    O. Firschein and T.M. Strat (eds.), RADIUS: Image Understanding for Imagery Intelligence, San Francisco: Morgan Kaufmann, 1997.Google Scholar
  6. 6.
    X. Dai and S. Khorram, “Requirements and techniques for an automated change detection system,” in Proceedings of the 1998 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’98), vol. 5, 1998, pp. 2752–2754.Google Scholar
  7. 7.
    A. Huertas and R. Nevatia, “Detecting changes in aerial views of man-made structures,” in Proceedings of the Sixth International Conference on Computer Vision (ICCV98), 1998, pp. 73–79.Google Scholar
  8. 8.
    R. Chellappa, Q. Zheng, L.S. Davis, D. DeMenthon, and A. Rosenfeld, “Site-model-based change detection and image registration,” in DARPA93, 1993, pp. 205–216.Google Scholar
  9. 9.
    S. Kuttikkad, R. Chellappa, and L. Novak, “Building 2-D wide area site models from single-and multi-pass single polarization SAR data,” in SPIE Aerosense’ 96, Orlando, FL, 1996.Google Scholar
  10. 10.
    L. Bruzzone and D.F. Prieto, “A Bayesian approach to automatic change detection,” in Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’99), 1999, pp. 1816–1818.Google Scholar
  11. 11.
    H. Hanaizumi and S. Fujimura, “Change detection from remotely sensed multi-temporal images using multiple regression,” in Proceedings of the 1992 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’92), 1992, pp. 564–566.Google Scholar
  12. 12.
    T. Yamamoto, H. Hanaizumi, and S. Chino, “A change detection method for remotely sensed multi-spectral and multi-temporal images using 3-D segmentation,” in Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’99), 1999, pp. 77–79.Google Scholar
  13. 13.
    M.J. Carlotto, “Detection and analysis of change in remotelysensed imagery with application to wide area surveillance,” IEEE Transactions on Image Processing, vol. 6, no.1, 1997.Google Scholar
  14. 14.
    V.K. Shettigara, “A generalized procedure for change detection and semi-automatic extraction of man-made objects from multispectral images,” in ISSSR-95, 1995.Google Scholar
  15. 15.
    X. Dai and S. Khorram, “Development of a new automated land cover change detection system from remotely sensed imagery based on artificial neural networks,” in Proceedings of the 1997 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’97), vol. 2, Singapore, 1997, pp. 1029–1031.Google Scholar
  16. 16.
    J.T. Morisette and S. Khorram, “An introduction to using generalized linear models to enhance satellite-based change detection,” in Proceedings of the 1997 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’97), vol. 4, Singapore, 1997, pp. 1769–1771.Google Scholar
  17. 17.
    L. Bruzzone and D.F. Prieto, “Automatic analysis of the difference image for unsupervised change detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 38, no.3, pp. 1171–1182, 2000.Google Scholar
  18. 18.
    A. Schaum and A. Stocker, “Spectral/temporal detection of military targets in clutter,” in 44th National IRIS, 1997.Google Scholar
  19. 19.
    U.M. Fayyad, S.G. Djorgovski, and N. Weir, “Automating the analysis and cataloging of sky surveys,” in Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press, 1996, pp. 471–493.Google Scholar
  20. 20.
    M. Burl, U. Fayyad, P. Perona, P. Smyth, and M. Burl, “Automating the hunt for volcanoes on venus,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, 1994.Google Scholar
  21. 21.
    T. Zhang, R. Ramakrishnan, and M. Livny, “BIRCH: A new data clustering algorithm and its applications,” Data Mining and Knowledge Discovery, vol. 1, no.2, pp. 141–182, 1997.Google Scholar
  22. 22.
    P.E. Stolorz and C. Dean, “Quakefinder: A scalable data mining system for detecting earthquakes from space,” in Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96), Portland, OR, 1996, pp. 208–213.Google Scholar
  23. 23.
    D.P. Roy, “The impact of misregistration upon composited wide field of viewsatellite data and implications for change detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 38, (no. 4 part 2), pp. 2017–2032, 2000.Google Scholar
  24. 24.
    L. Fonseca and B.S. Manjunath, “Registration techniques for multisensor remotely sensed imagery,” Photogrammetric Engineering and Remote Sensing, vol. 62, no.9, 1996.Google Scholar
  25. 25.
    X. Dai, S. Khorram, and H. Cheshire, “Automated image registration for change detection from landsat thematic mapper imagery,” in Proceedings of the 1996 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’96), vol. 3, 1996, pp. 1609–1611.Google Scholar
  26. 26.
    A. Can, C. Stewart, and B. Roysam, “Robust hierarchical algorithm for constructing a mosaic from images of the curved human retina,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1999, pp. 286–292.Google Scholar
  27. 27.
    X. Dai and S. Khorram, “Effects of image misregistration on the accuracy of remotely sensed change detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 36, no.5, pp. 1566–1577, 1998.Google Scholar
  28. 28.
    J.R.G. Townshend, C.O. Justice, C. Gurney, and J. McManus, “Impact of misregistration on change detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 30, no.5, pp. 1054–1060, 1992.Google Scholar
  29. 29.
    ERDAS, “ERDAS IMAGINE,” http://www.erdas.com, 2001.Google Scholar
  30. 30.
    S. Fahlman, “Fast-learning variations on back-propagation: An empirical study,” in Proceedings of the 1988 Connectionist Models Summer School, 1988, pp. 38–51.Google Scholar
  31. 31.
    P. Goodman, D. Rosen, L. McKnight, A. Purankar, and F. Sha, “NevProp4: Artificial neural network software for statistical prediction,” http://www.scs.unr.edu/nevprop/, 1994.Google Scholar
  32. 32.
    C. Canus and J.L. Vehel, “Change detection in sequences of images by multifractal analysis,” in Proceedings of the 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-96), vol. 4, 1996, pp. 2172–2175.Google Scholar
  33. 33.
    landsat, “Multi-resolution land characteristics (MRLC),” Earth Resources Observation Systems (EPOS), Data Center, U.S. Geological Survey (USGS). Available at http://edcwww.cr.usgs.gov/Webglis/glisbin/guide.pl/glis/hyper/guide/mrl, 2001.Google Scholar
  34. 34.
    fthood, “Ft. Hood Datasets,” Model Based Vision Laboratory (MBVL), Air Force Research Laboratory (AFRL), United States Air Force. Available at https://www.mbvlab.wpafb.af.mil/ public/sdms/datasets/fthood/index.htm, 2001.Google Scholar
  35. 35.
    ATR, “Special issue—automatic target recognition,” Neural Networks, vol. 8, nos.7/8, pp. 1005–1358, 1995.Google Scholar
  36. 36.
    Nassar M. Nasrabadi and Aggelos K. Katsaggelos (eds.), “Session 1: Use of Neural Networks for Automatic Target Recognition, Classification, and Characterization,” in Applications of Artificial Neural Networks in Image Processing IV, vol. 3647, SPIE, 1999, pp. 2–57.Google Scholar
  37. 37.
    R.G. White, and C.J. Oliver, “Change detection in SAR imagery,” in Proceedings of the 1990 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’90), 1990, pp. 217–222.Google Scholar
  38. 38.
    D.J. Wehdahl, “Change detection in SAR images,” in Proceedings of the 1991 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’91), 1991, pp. 1421–1424.Google Scholar
  39. 39.
    M. Bao, “Backscattering change detection in SAR images using wavelet techniques,” in Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’99), 1999, pp. 1561–1563.Google Scholar
  40. 40.
    Darwin, “Oracle Darwin Data Mining Software,” http:// www.oracle.com/ip/analyze/warehouse/datamining/, 2001.Google Scholar

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  • Chris Clifton
    • 1
  1. 1.Department of Computer SciencesPurdue UniversityWest Lafeyette

Personalised recommendations