chapter  2
5 Pages

5D Video Avatar for Networked VRPhoto System

Over last few years, various research activities on avatar generation have been reported. At first, a CG-based avatar has been proposed but it is used in limited applications due to its weakness, i.e., the lack of reality. To overcome the weakness, an image (video)-based avatar has been developed, where the texture of the avatar is segmented from background image and then augmented into virtual world. However, augmenting 2D video avatars onto virtual world is unnatural, since 2D video avatars do not have 3D position information, in general [1]. As a result, it is difficult to allow 2D video avatars to interact with real or virtual objects. To relieve these problems, a 3D video avatar has been developed. However, it usually takes time in generating 3D video avatar and requires extensive computational power in modelling and rendering the avatars [2]. Though 2.5D video avatar has been proposed as a compromise between 2D and 3D video avatars, it also has various limitations since the avatar is generated by exploiting chroma-keying in segmenting a user from the captured image [3].