Dynamic feature point detection for visual servoing using multiresolution critical-point filters

In this paper we examine the selection of feature points for visual servoing methods using multiresolution critical-point filters (CPF). With the increased number of feature points made available to us using CPF, we hope to improve the robustness of the system by allowing the algorithm to automatically detect usable feature points on virtually any object without any a priori knowledge of the object. Furthermore, the algorithm revises these points at each iteration to account for events that may have otherwise caused feature points to be lost and led to the visual servo method ending in failure.