| 一种高效的三维运动检索方法 |
| |
| 引用本文： | 向坚.一种高效的三维运动检索方法[J].计算机科学,2008,35(3):84-86. |
| |
| 作者姓名： | 向坚 |
| |
| 作者单位： | 浙江科技学院信息与电子工程学院,杭州,310023;浙江大学计算机学院,杭州,310027 |
| |
| 摘 要： | 随着运动捕获设备的普及,大量的运动数据可以直接得到,从而使得大规模的运动数据库的建立成为可能.在此背景下,研究以检索为核心的运动捕获数据处理技术就显得十分重要了.本文提出了一种对运动捕获数据中的人体的各个关节点提取一种基于三维空间变换规律的3D时空特征的方法,并基于时空运动连续性引入了关键空间的概念.针对各关节点时空特征相对保持独立的特性,本文用每个关节点作为索引,并通过数据驱动决策树的学习方法去分析关节点对运动相似的不同影响,最终实现了一个高效的运动检索系统.
|
| 关 键 词： | 运动捕获 三维时空特征 决策树 运动检索 |
Motion Retrieval Based on 3D Spatial-Temporal Features and Decision Tree |
| |
| XIANG Jian.Motion Retrieval Based on 3D Spatial-Temporal Features and Decision Tree[J].Computer Science,2008,35(3):84-86. |
| |
| Authors: | XIANG Jian |
| |
| Affiliation: | XIANG Jian1,2( School of Information , Electronic Engineering,Zhejiang University of Science , Technology,Hangzhou 310023)1( College of Computer Science,Zhejiang University,Hangzhou 310027)2 |
| |
| Abstract: | With the development of Motion Capture techniques,more and more 3D motion libraries become available. In this paper,we present a novel approach for motion retrieval based on data-driven decision tree with spatial-temporal features. First the 3D time spatial features of each human joint are extracted with the help of keyspace. Given the assumption of the features of each joint is independence,data-driven decision tree is automatically constructed to present the influence of each point during the comparison o... |
| |
| Keywords: | Motion capture 3D spatial-temporal feature Decision tree Motion retrieval |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
