Abstract
A new image-registration method is presented by integrating the area-based and feature-based methods. The integrated method is characterized by a novel similarity metric based on spatial and mutual information (SMI), the ant colony optimization for continuous domain (ACO), and a two-phase searching strategy. The SMI-based metric takes into account both spatial relations of detected features [spatial information (SI)] and the mutual information (MI) between the reference and sensed images. The spatial relation is to derive a fast transformation of the near global optimum without specifying the initial searching range. The MI is to obtain an optimal transformation with high accuracy. ACO is adopted to optimize SMI for the first time in this paper, as the function of SMI is generally non-convex and irregular. In addition, a two-phase searching strategy is designed to improve the performance of ACO. Phase-1 only considers the SI and finds some low-accurate solutions. Phase-2 considers both SI and MI so it is to search for a more accurate solution. These two phases are switched according to the diversity of the solutions. The proposed integrated method has been tested using the remote-sensing images acquired from different sensors, including TM, SPOT, and SAR. The experimental results indicate that the SMI-based metric is more robust than the conventional metrics which consider SI or MI alone. This method is able to achieve a highly accurate automatic registration of multisensor images.