Fusion of remote sensing images based on pyramid decomposition with Baldwinian Clonal Selection Optimization |
| |
Affiliation: | 1. Institut für Festkörperphysik, Universität Bremen, Otto-Hahn-Allee 1, 28359 Bremen, Germany;2. Institut für Halbleitertechnik, Technische Universität Braunschweig, Hans-Sommer-Str. 66, 38106 Braunschweig, Germany;3. EMAT, University of Antwerp, Groenenborgerlaan 171, 2020 Antwerp, Belgium;1. Department of Biology, University of Turku, Turku 20014, Finland;2. Department of Ecology and Evolutionary Biology, University of Michigan, Ann Arbor, MI 48109-1048, USA;3. Faculty of Biology, Belarusian State University, Minsk, Belarus |
| |
Abstract: | In this paper, we put forward a novel fusion method for remote sensing images based on the contrast pyramid (CP) using the Baldwinian Clonal Selection Algorithm (BCSA), referred to as CPBCSA. Compared with classical methods based on the transform domain, the method proposed in this paper adopts an improved heuristic evolutionary algorithm, wherein the clonal selection algorithm includes Baldwinian learning. In the process of image fusion, BCSA automatically adjusts the fusion coefficients of different sub-bands decomposed by CP according to the value of the fitness function. BCSA also adaptively controls the optimal search direction of the coefficients and accelerates the convergence rate of the algorithm. Finally, the fusion images are obtained via weighted integration of the optimal fusion coefficients and CP reconstruction. Our experiments show that the proposed method outperforms existing methods in terms of both visual effect and objective evaluation criteria, and the fused images are more suitable for human visual or machine perception. |
| |
Keywords: | Image fusion Remote sensing images Baldwinian Clonal Selection Algorithm Optimization |
本文献已被 ScienceDirect 等数据库收录! |
|