A comparative assessment of similarity measures for registration of multi-temporal remote sensing images

Accurate registration of multi-temporal remote sensing images is essential for various change detection applications. Mutual information (MI) has been used as a similarity measure for registration of medical images widely. Its application in remote sensing is relatively new. A number of algorithms may be used to estimate the joint histogram to compute mutual information, but they may suffer from interpolation-induced artifacts Linder certain conditions. In this paper, we investigate the use of a new joint histogram estimation algorithm called generalized partial volume estimation (GPVE) for computing mutual information to register multi-temporal remote sensing images. The performance is evaluated with other popular similarity measures namely mean squared difference (MSD) and non-nalized cross correlation (NCC) The experimental results show that higher order GPVE algorithms have the ability to significantly reduce interpolation-induced artifacts. In addition, mutual information based image registration performed using the GPVE algorithm produces better registration consistency than the other two similarity measures used for the registration of multi-temporal remote sensing images.