一种人体运动骨骼提取和动画自动生成方法  

An Automated Method for Rigging and Animation of Human Body

作　　者：吴伟和[1,2] 郝爱民[1] 赵永涛[1] 万巧慧[2] 李帅[1] 

机构地区：[1]虚拟现实技术与系统国家重点实验室(北京航空航天大学),北京100191 [2]北京工业大学艺术设计学院,北京100029

出　　处：《计算机研究与发展》2012年第7期1408-1419,共12页Journal of Computer Research and Development

基　　金：国家自然科学基金重点项目(60533070);北京工业大学服务北京创新人才培养基金项目(03500054R4001)

摘　　要：现有的动画生成方法存在手工操作繁琐、模型姿态受局限等问题.提出了一种新的人体模型动画自动生成方法,首先自动提取和识别位于人体四肢和头顶末端的5个特征点,以特征点为起点,计算模型等测地线的中心线.在中心线上根据人体测量学知识,确定关节点的近似位置,然后根据人体骨骼刚性运动特征和运动数据文件提供的骨骼信息,进行关节点精确定位,再通过热力学扩散方程计算顶点权重最后将提取的骨骼采用局部坐标架对齐的方法实现与运动数据匹配,并以运动数据驱动皮肤产生人体动画实验结果表明,与现有算法相比,具有与模型姿态无关、全自动、产生动画效果好等特点.Most existing methods for animating a human body require a lot of manual work, and only deal with human body in some specific poses. We present a novel automated method for animating human bodies. Firstly, five feature points at the end points of head and limbs on human body surface are automatically extracted and recognized. Secondly, by taking the feature points as source points, the geodesic distance isolines on the surface are calculated and the central lines are subsequently constructed. Thirdly, along the central lines, joint positions are roughly determined based on the anthropometry knowledge, and then the joint positions are refined using kinematic characteristics of skeleton and motion data. Forthly, the skin attachment is made by solving for heat equilibrium. Finally, we match the extracted skeleton to motion data by aligning local coordinate frames and then animate the human body using motion data. Experiment results demonstrate that our method is poseindependent and fully automated, and can generate more realistic animation than previous methods.

关 键 词：动画 骨骼提取 测地距离 姿态无关性 人体模型 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]