• DOI:10.1364/JOSAA.33.001313
• Corpus ID: 212266

Nonrigid registration of remote sensing images via sparse and dense feature matching.

@article{Chen2016NonrigidRO,
  title={Nonrigid registration of remote sensing images via sparse and dense feature matching.},
  author={Jun Chen and Linbo Luo and Chengyin Liu and Jin-Gan Yu and Jiayi Ma},
  journal={Journal of the Optical Society of America. A, Optics, image science, and vision},
  year={2016},
  volume={33 7},
  pages={
          1313-22
        }
}

• Jun Chen, Linbo Luo, +2 authors Jiayi Ma
• Published 1 July 2016
• Computer Science
• Journal of the Optical Society of America. A, Optics, image science, and vision

In this paper, we propose a novel formulation for building pixelwise alignments between remote sensing images under nonrigid transformation based on matching both sparsely and densely sampled features. Our formulation contains two coupling variables: the nonrigid geometric transformation and the discrete dense flow field. To match sparse features, we fit a geometric transformation specified in a reproducing kernel Hilbert space and impose a locally linear constraint to regularize the transformation. To match dense features, we compute a dense flow field by using a formulation analogous to scale invariant feature transform (SIFT) flow which allows nonrigid matching across different scene appearances. An additional term is introduced to ensure the coherence between the two variables, and we alternatively solve for one variable under the assumption that the other is known. Extensive experiments on both synthetic and real remote sensing images demonstrate that our approach greatly outperforms state-of-the-art methods, particularly when the data contain severe degradations.