Registration of Correspondent Points in the Stereo-Pairs of Chang’E-1 Lunar Mission Using SIFT Algorithm

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.