首页 | 官方网站   微博 | 高级检索  
     

基于检索的人体运动识别和模拟
引用本文:赵国英,李振波,邓宇,李华.基于检索的人体运动识别和模拟[J].计算机研究与发展,2006,43(2):368-374.
作者姓名:赵国英  李振波  邓宇  李华
作者单位:1. 中国科学院计算技术研究所智能信息处理重点实验室,北京,100080;中国科学院研究生院,北京,100049
2. 中国科学院计算技术研究所智能信息处理重点实验室,北京,100080
基金项目:国家科技攻关项目;科技部科研项目;国家科技攻关项目
摘    要:运动识别和模拟是人体运动分析中重要的研究内容,实现了以检索为基础的实验性的运动分析系统.小波矩具有平移、旋转和缩放不变性,能够提取局部多层次特征,被用来作为特征描述运动序列以及动作,根据相似性实现运动识别,利用动态时间变形(DTW)实现序列的动作匹配,在poser建模、依据正多面体分割的金字塔模型得到多视点投影视频的数据库中进行识别和匹配,并以三维模型的形式显示出来.实验结果可以模拟人体运动以及为进一步分析提供初始分析数据.

关 键 词:小波矩  运动识别  动作检索
收稿时间:11 15 2004 12:00AM
修稿时间:2004-11-152005-05-27

Human Motion Recognition and Simulation Based on Retrieval
Zhao Guoying,Li Zhenbo,Deng Yu,Li Hua.Human Motion Recognition and Simulation Based on Retrieval[J].Journal of Computer Research and Development,2006,43(2):368-374.
Authors:Zhao Guoying  Li Zhenbo  Deng Yu  Li Hua
Affiliation:1.Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Scienees, Beijing 100080; 2 Graduate University, Chinese Academy of Sciences, Beijing 100049
Abstract:Motion recognition and simulation are important in human motion analysis. In this paper, an experimental motion analysis system based on retrieval is implemented. Wavelet moments are translation, rotation and scale invariant, and can extract local multi-level features, so they are applied as features to describe motion sequence and actions. Motion recognition is implemented based on the similarity of motion sequences, while action match is addressed using dynamic time warping (DTW). Resulted motion simulation is represented in 3D models. Experiments show the algorithm based on retrieval is efficient for motion recognition and simulation. Retrieval results can simulate human motion, or provide the coarse human motion configuration data for further analysis.
Keywords:wavelet moment  motion recognition  action retrieval
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号