Tour into the video

Abstract

Tour Into the Picture (TIP) proposed by Horry et al. [1] is a method for generating a sequence of walk-through images from a single reference image. By navigating a 3D scene model constructed from the image, TIP provides convincing 3D effects. Assuming that the image has one vanishing point, they proposed the scene modeling scheme called spidery mesh with which the users can make their imagination real as they find or feel in the 2D image. This thesis presents a system that creates walk-through images from a video sequence by generalizing the idea of TIP. To address various problems in dealing with a video sequence rather than a single image, the proposed system is designed to have the following features: First, the system incorporates a new modeling scheme based on a vanishing line (or vanishging circle) identified in the video, which is more general and simpler than the previous method. Second, a semi-automatic background detection technique is employed in conjunction with a 4-parameter motion model for image registration. Third, we developed a highly interactive image segmentation tool called enhance lane to extract the foreground objects at each frame. The purpose of this work is to let users experience the feel of navigating into a video sequence with their own interpretation and imagination about the given scene. The proposed system covers various types of video films of dynamic scenes such as sports coverage, cartoon animation, movie films, etc., in which objects are continuously changing their shapes and locations. It can also be used to produce a variety of synthetic video sequences by importing and merging dynamic foreign objects with the original video.