A Video Annotation Tool Using Vision-based AR Technology

In this paper, we present a video annotation tool using vision-based Augmented Reality (AR) technology. We apply AR technology and computer vision method for making videos with 3D annotations such as image textures, video clips, 3D objects and 3D text. A planar object is manually selected in the static scene, while it can be semi-automatically tracked in the dynamic scene. Tracking of the planar object is called marker-less tracking, which is often used in AR applications. When user selects a planar object in the real image, external camera parameters are estimated from 4 corner points of the planar object. As a marker-less tracking method, we use SURF feature based descriptors and the trackers. 3D annotation is rendered on the selected (or tracked) planar object.