Fully Automatic and Robust Approach for Remote Sensing Image Registration

  • Chi-Farn Chen
  • Min-Hsin Chen
  • Hsiang-Tsu Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)


Image registration is an important preprocessing procedure for remote sensing image applications, such as geometric correction, change detection, and image fusion. Since it is a time-consuming and labor-intensive task to correctly register the remote sensing image, this paper proposes a fully automatic and robust approach for the remote sensing image registration. First, the image pyramid of working and reference images are constructed for coarse to fine matching processing. Second, the feature points can be automatically extracted from the reference image, and the matching point can be searched on the working image. Third, in order to improve the accuracy of registration, the robust estimation serves as an important tool in preserving the correctly matched points. Three sets of satellite images, which include multi-sensor, multi-temporal and multi-spectrum images, are used to test the proposed approach. Results show that the approach is capable of automatically registering the working image to the reference image with great precision.


Image Registration Remote Sensing Image Automatic and Robust 


  1. 1.
    Li, W., Leung, H.: A Maximum Likelihood Approach for Image Registration Using Control Point And Intensity. IEEE Transactions on image processing 13(8), 1115–1127 (2004)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Mao, Z., Pan, D., Huang, H., Huang, W.: Automatic registration of SeaWiFS and AVHRR imagery. Int. J. Remote Sensing 22(9), 1725–1735 (2001)CrossRefGoogle Scholar
  3. 3.
    Chen, L.C., Teo, T.A., Rau, J.Y.: Optimized patch back-projection in ortho-rectification for high resolution satellite images. In: IAPRS, pp. 586–591 (2004)Google Scholar
  4. 4.
    Mäkelä, T., Clarysse, P., Sipilä, O., Pauna, N., Pham, Q.C., Katila, T., Magnin, I.E.: A Review of Cardiac Image Registration Methods. IEEE Transactions on medical image 21, 1011–1021 (2002)CrossRefGoogle Scholar
  5. 5.
    Arun, K.S., Huang, T.S., Blostein, S.D.: Least-squares fitting of two 3-D point sets. IEEE Transactions on Pattern Anal. Machine Intell. PAMI-9, 698–700 (1987)CrossRefGoogle Scholar
  6. 6.
    Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE Transactions on Pattern Anal. Machine Intell. 13, 376–380 (1991)CrossRefGoogle Scholar
  7. 7.
    Van Den Elsen, P.A., Pol, E.D., Sumanaweera, T.S., Her, P.F., Napel, S., Adler, J.R.: Grey value correlation techniques used for automatic matching of CT and MR brain and spine images. In: Proc. SPIE Visualization in Biomedical Computing, vol. 2357 pp. 227–237 (1994)Google Scholar
  8. 8.
    Netanyahu, N., Le Moigne, J., Masek, J.: Geo-Registration of Landsat Data by Robust Matching of Wavelet Features. IEEE Transactions on Geoscience and Remote Sensing 42(7), 1586–1600 (2004)CrossRefGoogle Scholar
  9. 9.
    Stone, H.S., Le Moigne, J., McGuire, M.: Image Registration Using Wavelet Techniques. In: Proceedings of SPIE, vol. 3240, pp. 116–125 (1998)Google Scholar
  10. 10.
    Thevenaz, P., Ruttimann, U.E., Unser, M.: A pyramid approach to sub-pixel registration based on intensity. IEEE Transactions on image processing 7, 27–41 (1998)CrossRefGoogle Scholar
  11. 11.
    Chen, L.C., Lee, L.H.: Progressive Generation of Control Frameworks for Image Registration. Photogrammetric Engineering and Remote Sensing 58(9), 1321–1328 (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Chi-Farn Chen
    • 1
  • Min-Hsin Chen
    • 1
  • Hsiang-Tsu Li
    • 1
  1. 1.Center for Space and Remote Sensing Research, National Central University, JhongliTaiwan

Personalised recommendations