Selection of features and evaluation of visual measurements for 3-D robotic visual tracking

An overview is presented of the vision techniques that are used in order to automatically select features, measure features' displacements, and evaluate measurements during 3-D robotic visual tracking. The most robust technique proves to be the sum-of-squared differences (SSD) optical flow technique. Several techniques for the evaluation of the measurements are presented. These techniques can also be used for the selection of features for tracking in conjunction with several numerical criteria that guarantee the robustness of the servoing. The results from the application of these techniques to real images are discussed.<
>