A Support System for Making Archive of Bi-directional Remote Lecture: Photometric Calibration

摘要

We are developing a system that supports making lecture movie archive. This system enables us to combine CG or another movie with a lecture scene movie by using intelligent computer vision techniques, and supports us to generate an effective lecture archive. In this paper, we concentrate on a scenario to generate a movie that seems to be like a lecture done in one lecture room based on two movies of lectures done in different remote lecture rooms. Because the source movies are captured on the different camera work and the different illumination condition, not only geometric calibration but also photometric calibration are important to make the target movie realistic. To overcome this problem, we propose a photometric calibration technique based on "fast separation of direct and global components" method. By using this method, estimation of color of illumination on the scene becomes more stable than our conventional method.