— Several recent algorithms have formulated the SLAM problem in terms of non-linear pose graph optimization. These algorithms are attractive because they offer lower computationa...
Visual tracking, in essence, deals with non-stationary data streams that change over time. While most existing algorithms are able to track objects well in controlled environments,...
In many computer vision tasks, scene changes hinder the generalization ability of trained classifiers. For instance, a human detector trained with one set of images is unlikely t...