| 单目视频中的多视角行为识别方法 |
| |
| 引用本文： | 李妍婷,罗予频,唐光荣.单目视频中的多视角行为识别方法[J].计算机应用,2006,26(7):1592-1594. |
| |
| 作者姓名： | 李妍婷 罗予频 唐光荣 |
| |
| 作者单位： | 清华大学,自动化系,北京,100084;清华大学,自动化系,北京,100084;清华大学,自动化系,北京,100084 |
| |
| 摘 要： | 针对多视角人体行为识别中，因选取单一特征所造成的识别困难，提出了一种基于分类特征提取的多视角行为识别方法。该方法通过有效利用视频的二维图像序列所包含的三维信息、实现对人体朝向的聚类，解决因观察角度不同造成的行为特征难以选取的问题。实验证明，该方法对单目视频中不同角度的行为动作有较高的识别率。
|
| 关 键 词： | 图像序列 运动骨架 行为识别 多视角 |
| 文章编号： | 1001-9081（2006）07-1592-03 |
| 收稿时间： | 2006-01-09 |
| 修稿时间： | 2006-01-09 |
Activity recognition method of multiple view angles from monocular videos |
| |
| LI Yan-ting,LUO Yu-pin,TANG Guang-rong.Activity recognition method of multiple view angles from monocular videos[J].journal of Computer Applications,2006,26(7):1592-1594. |
| |
| Authors: | LI Yan-ting LUO Yu-pin TANG Guang-rong |
| |
| Affiliation: | Department of Automation, Tsinghua University, Beijing 100084, China |
| |
| Abstract: | An activity recognition method of multiple view angles from monocular videos was introduced. To aim at recognition in un-calibrated videos, this method could solve the problem choosing a uniform activity characteristic sector of different view angles by utilizing 3-D information included in 2-D image sequence effectively and classifying human skeleton. The experiments show that it has good recognition rate for activity of different view angles from monocular videos. |
| |
| Keywords: | image sequence motion skeleton activity recognition multiple view angles |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
