1. Introduction

The SIFT keypoint detector and descriptor [17], although over a decade old, have proven remarkably successful in a number of applications using visual features, including object recognition [17], image stitching [28], visual mapping [25], etc. However, it imposes a large computational burden, especially for real-time systems such as visual odometry, or for low-power devices such as cellphones. This has led to an intensive search for replacements with lower computation cost; arguably the best of these is SURF [2]. There has also been research aimed at speeding up the computation of SIFT, most notably with GPU devices [26].