Analysis of feasibility and advantages of multi‐source image registration using regional features

Abstract

Automatic registration of multi-source remote sensing data is a challenging task due to the high non-linearity of radiometric differences among various data. Feature extraction is a key enabling technique in registration algorithm design. In this letter, we prove the feasibility of using extracted regional features for multi-source image registration. In particular, regional features can be extracted through pixel-level image classification, and existing off-the-shelf algorithms can be directly adopted. Experiment results demonstrate the robustness of the regionalfeature-based registration method.

Image matching via progressive priors

“…A fundamental issue in computer vision (e.g. image registration1) is establishing reliable correspondences in an image pair of the same scene. A two‐stage strategy is usually used for image matching.…”