虚拟实景对象建模与表现  

Modeling and Presentation of Virtual Reality Object

作　　者：徐玮[1] 王炜[1] 张茂军[1] 高辉[1] 

机构地区：[1]国防科技大学信息系统与管理学院,湖南长沙410073

出　　处：《计算机仿真》2009年第12期214-217,共4页Computer Simulation

基　　金：国家自然科学基金项目(60803101);湖南省自然科学基金项目(08JJ5027)

摘　　要：虚拟对象是指物体的数字化外观仿真模型,与基于图形的虚拟对象相比,基于图像的虚拟对象具有绘制速度与物体复杂度无关、实时性强、可轻易达到相片级的视觉表现效果以及建模简单等特点,在许多领域都具有广泛的应用前景。传统的基于图像的虚拟对象建模需已知相机参数或图像深度信息,建模繁琐复杂。针对该问题,提出一种可实用的基于图像的虚拟对象简化模型——虚拟实景对象,对该模型建模只需围绕待建模物体周围采集一圈实景图像,无需已知相机参数或图像深度信息,表现时则采用视图合成方法来合成未采集图像视点的虚拟视图,从而实现对物体的连续自由观察。实验结果表明,该方法不仅建模过程简单,而且可以实现对虚拟对象的360度连续自由操纵。Image -based virtual object can be applied in many fields. Traditional modeling for image -based object needs to know the parameter of camera or image depth, and modeling process is fussy and complex. This paper presents a predigesting model for image - based virtual object, named virtual reality object, which only needs to collect several images around the object without parameter of camera or image depth. When presenting the object, in order to realize continuous browsing, the method of view synthesis is used to synthetize virtual view of the viewpoint where image has not be collected. The result of experiment indicates that the method is not only easy, but also can realize manipulating virtual object freely in 360 degree.

关 键 词：视图合成 角点匹配 基于图像的渲染 虚拟实景对象 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]