摘要
虚拟演播室中的模型需要实时运动,从而对组成模型的三角形数量有一定限制。设计了一种基于均值聚类的三维模型简化算法。该算法引入了衡量组成模型的每个顶点的权重因子,利用均值聚类算法对模型的顶点分类,通过统计组成模型三角形边长来调整分类结果,从而生成不同细节层次三角形数量可控的三维模型。实验结果表明,该算法能够在保持原模型轮廓的同时有效减少组成模型的顶点和面的数量,形成不同细节层次的模型,保证虚拟演播室中模型动画的流畅。
The quantity of the triangles are limited by real-time motion of three-dimensional（3D） models in virtual studio. Then, a 3D model simplified algorithm based on clustering is proposed. The algorithm applies a weight factor to every vertex of the o- riginal model, and decreases the number of vertices by the K-means clustering. The length of triangle is analyzed to control the generation of the different levels of details. Experimental results show that the algorithm can produce a series model approximated with the original one, but contain a smaller number of vertices and faces, which improve the models motion effect in virtual studio.
出处
《电视技术》
北大核心
2009年第12期75-77,80,共4页
Video Engineering
基金
国家自然科学基金项目(60572087)
