Abstract
Visual tracking is to track a moving target in a sequence of images. In template-based visual tracking, a reference image is given as a target for visual tracking. Template-based tracking is achieved by minimizing the difference between a given reference image and a region extracted from a warped current image at each time. Many template-based visual tracking techniques have been proposed, but none of them are perfect. This paper discusses an evaluation method of template-based visual tracking techniques using a robotic manipulator.
