In recent years, image registration has become extremely important in remote sensing applications. Image registration refers to the fundamental task in image processing to match two or more pictures which have been taken of the same object or scene, for example, at different times, from different sensors, or from different viewpoints.

The main reason for the increased significance of image registration in remote sensing is that remote sensing is currently moving towards operational use in many important applications, both at social and scientific levels. These applications include, for example, the management of natural disasters, assessment of climate changes, management of natural resources, and the preservation of the environment; all of which involve the monitoring of the Earth's surface over time. Furthermore, there is an increasing availability of images with different characteristics, thanks to shorter revisiting times of satellites, increased flexibility of use (different acquisition modalities) and the evolution of sensor technologies. Therefore, a growing need emerges to simultaneously process different data, that is, remote sensing images, for information extraction and data fusion. This includes the comparison (integration or fusion) of newly acquired images with previous images taken with different sensors or with different acquisition modalities or geometric configurations – or with cartographic data. The remote images can, therefore, be multitemporal (taken at different dates), multisource (derived from multiple sensors), multimode (obtained with different acquisition modalities), or stereo-images (taken from different viewpoints).