Multimodal continuous ant colony optimization for multisensor remote sensing image registration with local search

Abstract

Abstract Due to the large differences between different imaging sensors, multisensor remote sensing image registration is a challenging work. Multisensor remote sensing image registration can be formulated as a multimodal problem, and general optimization methods may get trapped into a local optimum when solving complex multimodal problems. In this paper, we introduce a multimodal continuous ant colony optimization algorithm for multisensor remote sensing image registration, and an efficient optimization method is designed as local search operation. Multimodal continuous ant colony optimization algorithm can preserve high diversity and has the global search ability for multimodal problems. Meanwhile, efficient local search operation can improve the efficiency and provide the accurate result. The experimental results have demonstrated the effectiveness and robustness of the proposed method.