Registration of correspondent points in the stereo-pairs of Chang’E-1 lunar mission using SIFT algorithm

Abstract

In this article, an appropriate strategy for registration of correspondent points in the stereo-pairs of Chang’E-1 lunar mission has been introduced. It consists of area-based method and feature-based method as two steps. Firstly, one subimage was extracted from nadir image as reference image. Making use of area-based method, another subimage which is called target image can be obtained from backward or forward image overlapping the same region of lunar surface with reference image. Secondly, feature points of each subimage can be extracted by SIFT (scale invariant feature transform) algorithm. Lastly, for each feature point given in reference image, the position of correspondence in target image can be estimated according to the parameters of Chang’E-1 lunar orbiter. In contrast to standard SIFT matching algorithm, the method proposed in this article can narrow the search space and accelerate the speed of computation while achieving reduction of the percentage of false registration.

Keywords

Chang’E-1 / CCD image / image registration / SIFT algorithm

References

[1] Babaud J, Baudin M, Witkin A, . Uniqueness of the Gaussian Kernel for Scale-Space Filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(1): 26-33.

[2] Brown L G. A Survey of Image Registration Techniques. ACM Computing Surveys, 1992, 24(4): 325-376.

[3] Harris C, Stephens M. A Combined Corner and Edge Detector. Proceedings of the 4th Alvey Vision Conference, Manchester, 1988, 147-151.

[4] Kitchen L, Rosenfeld A. Gray-Level Corner Detection. Pattern Recognition Letters, 1982, 1(2): 95-102.

[5] Koenderink J J. The Structure of Images. Biological Cybernetics, 1984, 50(5): 363-370.

[6] Lindeberg T. Scale-Space Theory: A Basic Tool for Analyzing Structures at Different Scales. Journal of Applied Statistics, 1994, 21(2): 225-270.

[7] Li C L, Liu J J, Ren X, . The Global Image of the Moon Obtained by the Chang’E-1: Data Processing and Lunar Cartography. Sci. China Earth Sci., 2010, 53(8): 1091-1102.

[8] Lowe D G. Object Recognition from Local Scale-Invariant Features. Proceedings of International Conference on Computer Vision, Corfu, 1999, 1150-1157.

[9] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-100.

[10] Moravec H. Rover Visual Obstacle Avoidance. Proceedings of the 7th International Conference on Artificial Intelligence, Vancouver, 1981, 785-790.

[11] Otto G P, Chau T K W. A Region-Growing Algorithm for Matching of Terrain Images. Proceedings of the 4th Alvey Vision Cofference, 1988, 123-128.

[12] Smith S M, Brady J M. SUSAM-A Approach to Low Level Image Processing. Journal of Computer Vision, 1997, 23(1): 45-78.

[13] Witkin A P. Scale-Space Filtering: A New Approach to Multi-Scale Description: Acoustics, Speech, and Signal Processing. Proceedings of IEEE International Conference on ICASSP, IEEE, 1984, 150-153.

[14] Wiedemann C, Tang L, Ohlhof T. A New Matching Approach for Three-Line Scanner Imagery. International Archives of Photogrammetry and Remote Sension, 1996, 31: 940-945.

[15] Ye M J, Li J, Liang Y Y, . Automatic Seamless Stitching Method for CCDImages of Chang’E-1 Lunar Mission. Journal of Earth Science, 2011, 5(22): 610-618.

[16] Zhang L, Gruen A. Multi-Image Matching for DSM Generation from IKONOS Imagery. Journal of Photogrammetry and Remote Sensing, 2006, 3(60): 195-211.

[17] Zitová B, Flusser J. Image Registration Methods: A Survey. Image and Vision Computing, 2003, 21(11): 977-1000.