Selecting promising landmarks

Abstract

Many approaches to visual servoing and mobile robot navigation are based on tracking feature points or landmarks in images, but not all features points are equally effective as landmarks. Here we develop methods for selecting within an image those landmarks which are both perceptually salient and visually distinctive, and consequently are readily recognized in a second image acquired from a different viewpoint. Empirically, we characterize the performance of the recognition method and then demonstrate that the selection process does in fact choose the landmarks which are more likely to be recognized.