Tracking from airborne cameras is very challenging, since most assumptions made for fixed cameras do not hold. Therefore, com- pensation of platform ego-motion is seen as a necessary pre-processing step. Most existing methods perform image registration or matching, which involves costly image transformations, and have a restricted opera- tional range. In this paper, a novel ego-motion compensation approach is presented, that transforms the local search window of the visual tracker. This is much more computationally efficient, and can be applied re- gardless of the amount of texture in the background. Experiments with ground truth and tracker output data are conducted and show the va- lidity of the approach. 1    «

Tracking from airborne cameras is very challenging, since most assumptions made for fixed cameras do not hold. Therefore, com- pensation of platform ego-motion is seen as a necessary pre-processing step. Most existing methods perform image registration or matching, which involves costly image transformations, and have a restricted opera- tional range. In this paper, a novel ego-motion compensation approach is presented, that transforms the local search window of the visual tracker. This is much...    »