A study of the sensitivity of automatic image registration algorithms to initial conditions

While automatic image registration algorithms are usually being evaluated with regards to their accuracy, it is often useful to relate this accuracy to the "initial conditions", i.e., the distance between the initial navigation geolocation and the correct result In this paper, we describe a modular framework that was built to describe registration algorithms, and we utilize this framework to attempt to classify different registration components and algorithms in terms of their responses to the initial conditions. Performances will be evaluated on synthetic data, multi-temporal and multi-sensor data. All results of the study will be presented at the conference and will be useful for two different purposes: (1) provide automatic quality assessment of the geo-location of remote sensing data by performing inter-algorithm consistency studies; and (2) be the foundations for the design of future on-board applications including planetary exploration.