Improved SIFT Algorithm for Remote Sensing Image Matching

Image matching is the process of finding correspondences between two or more images of the same scene taken at different times, from different viewpoints, and/or by different sensors. Extracting welldistributed, reliable and precisely aligned point pairs for accurate image registration is a difficult task, especially for multi-source remote sensing images that have significant illumination, rotation and scene differences. SIFT approach, as a well-known feature based image matching algorithm, has been successfully applied in a number of automatic registration of remote sensing images. Regardless of its distinctiveness and robustness, SIFT algorithm suffers from several problems in the fields of quality, quantity and distribution of extracted features especially in multi-source remote sensing imageries. In this paper, an improved SIFT algorithm is introduced that is fully automated and applicable to various kinds of optical remote sensing images. The main key of the proposed approach is a selection strategy of SIFT features in the full distribution of location and scale where the feature qualities are quarantined based on the stability and distinctiveness constraints. Then the extracted features are introduced to an initial cross-matching process followed by a consistency check in the projective transformation model. Comprehensive evaluations of efficiency, distribution quality and positional accuracy of the extracted point pairs prove the capabilities of the proposed matching algorithm on a variety of optical remote sensing images.