您的位置:首页  > 论文页面

基于关键特征的运动搜索方法

发表时间:2014-02-28  浏览量:1800  下载量:687
全部作者: 黄天羽
作者单位: 北京理工大学软件学院
摘 要: 为实现快速的运动搜索,提出一种基于关键特征的运动搜索方法。该方法应用时空Isomap对运动捕捉数据进行降维,从而保留运动的关键特征;然后对运动的低维嵌入进行简单的迭代,对关键运动特征所在的关键帧进行定位;并动态地建立一个二叉关键(binary keyfeature splitting,BKS)特征树。实验证明:经过少量的预处理时间,可以获得实时、有效的运动搜索结果。
关 键 词: 计算机应用;多媒体检索;运动检索;关键运动特征;二叉关键特征树
Title: Motion retrieval method based on key features
Author: HUANG Tianyu
Organization: School of Software, Beijing Institute of Technology
Abstract: In order to obtain the rapid motion retrieval, a fast motion retrieval method based on key motion features is proposed. The method applies the spatio-temporal Isomap on effective aspects of motion data to yield a reduced low-dimension space, where the main characteristics of motion are kept. The lower complexity of the embedded motion curve allows a simple iterative method which locates the key-poses of the original motion. The paper presents a dynamic method of constructing a binary keyfeature splitting (BKS) tree with significant points to search for a given motion example. The experiment proves that, with proper dynamic algorithm and key-pose selection in terms of spatio-temporal variations, the method can consume a small amount of pre-processing time, and achieve precise and effective retrieval.
Key words: computer application; multimedia retrieval; motion retrieval; key motion feature; binary keyfeature splitting tree
发表期数: 2014年2月第4期
引用格式: 黄天羽. 基于关键特征的运动搜索方法[J]. 中国科技论文在线精品论文,2014,7(4):363-369.
 
0 评论数 0
暂无评论
友情链接