Research of methods for man-made change detection on earth surface using high resolution satellite image series
V.A. Fedoseev, N.V. Chupshev

Full text of article: Russian language.

Abstract:
In this paper, we perform the analysis and functionality research of several algorithms designed for detection of anthropogenic changes on the Earth's surface by analyzing a series of satellite images of the same area taken at different times. The greatest attention is paid to the algorithm based on the principal component analysis, the “Wallflower” algorithm based on Wiener filter, and the Li algorithm based on the extraction of straight line segments. The results of research of these algorithms on real series of high resolution satellite images, as well as conclusions about their usefulness are given in the paper. Also, some modifications of the algorithms designed to reduce errors and improve the quality of their work are proposed..

Key words:
change detection, remote sensing, satellite imagery analysis, principal component analysis, Wiener filter, Burns algorithm, shadow mask.

References:

  1. Radke, R.J. Image change detection algorithms: a systematic survey / R.J. Radke, S. Andra, O. Al-Kofahi, B. Roysam // IEEE Trans. on Image Processing. – 2005. – Vol. 14(3). – P. 294-307.
  2. Bruzzone, L. An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images / L. Bruzzone, D.F. Prieto // IEEE Trans. on Image Processing. – 2002. – Vol. 11(4). – P. 452-466.
  3. Aach, T. Statistical model-based change detection in moving video / T. Aach, A. Kaup // Signal Process. – 1993. – Vol. 31. – P. 165-180.
  4. Hsu, Y.Z. New likelihood test methods for change detection in image sequences / Y.Z. Hsu, H.-H. Nagel, G. Rec­kers // Comput. Vis., Graph. Image Process. – 1984. – Vol. 26. – P. 73-106.
  5. Jain, Z. Optimum multisensor data fusion for image change detection / Z. Jain, Y. Chau // IEEE Trans. Syst., Man, Cybern. – 1995. – Vol. 25(9). – P. 1340-1347.
  6. Niemeyer, I. Unsupervised change detection techniques using multispectral satellite images / I. Niemeyer, M. Canty, D. Klaus // Proc. IEEE Int. Geoscience and Remote Sensing Symp. – 1999. – P. 327-329.
  7. Qiu, B. Multi-block PCA method for image change detection / B. Qiu, V. Prinet, E. Perrier, O. Monga // 12th International Conference on Image Analysis and Processing. – 2003. – P. 385-390
  8. Toyama, K. Wallflower: Principles and practice of background maintenance / K. Toyama, J. Krumm, B. Brumitt, B. Meyers // Proc. ICCV. – 1999. – P. 255-261.
  9. Li, W. A novel framework for urban change detection using VHR satellite images / W. Li, Y. Wu, Z. Hu // Proc. of ICPR. – 2006. – P. 312-315.
  10. Zhang, Sh. Urban change detection based on edge line segments and texture / Sh. Zhang, W. Li, Q. Liu, Zh. Zhou, H. Lu // Conference in Research and Practice in Information Technology, 2006.
  11. Burns, J.B. Extracting straight lines / J.B. Burns, A.R. Han­son, E.M. Riseman // IEEE Trans. PAMI. – 1986. – Vol. 8(4). – P. 425-455.
  12. Arévalo, V. Detecting shadows in QuickBird satellite images / V. Arévalo, J. González, J. Valdes, G. Ambrosio // ISPRS Commission VII Mid-term Symposium "Remote Sensing: From Pixels to Processes", Enschede, the Netherlands, 2006.
  13. Shapiro, L. Computer Vision / L. Shapiro, G. Stockman. – Prentice-Hall, Inc, 2001.
    Lowe, D.G. Object recognition from local scale-invariant features / D.G. Lowe // Proceedings of the International Conference on Computer Vision. – 1999. – P. 1150-1157.
  14. Jensen, J. Introductory Digital Image Processing, a Remote Sensing Perspective / J. Jenson. – Prentice-Hall, Inc., 1996.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: ko@smr.ru; Phones: +7 (846 2) 332-56-22, Fax: +7 (846 2) 332-56-20