| 基于序列模式挖掘的田径视频分类 |
| |
| 引用本文： | 方园,肖国强,代毅. 基于序列模式挖掘的田径视频分类[J]. 微计算机信息, 2011, 0(3) |
| |
| 作者姓名： | 方园 肖国强 代毅 |
| |
| 作者单位： | 西南大学计算机与信息科学学院; |
| |
| 摘 要： | 现有的体育视频分析方法大多都专注于重要事件的提取,而忽视了如何对这些事件进行组织和语义分析。本文提出了一种基于序列模式挖掘的田径视频镜头分类算法。本文主要围绕两个问题展开——特征提取和语义规则的定义。在特征提取阶段,自动的将田径视频镜头分割为一系列可识别的运动事件序列,然后使用机器学习的算法对每类行为事件进行识别。在语义规则定义阶段,使用序列模式挖掘方法发现其中的频繁序列,在此基础上进行。实验选用了上千段田径视频镜头进行测试,结果显示了本文算法进行田径视频镜头分类的有效性。
|
| 关 键 词： | 语义 田径视频 频繁序列模式 视频分类 |
A Novel Classification Based on Sequential Pattern Mining in Track and Field Videos |
| |
| FANG Yuan XIAO Guo-qiang DAI Yi. A Novel Classification Based on Sequential Pattern Mining in Track and Field Videos[J]. Control & Automation, 2011, 0(3) |
| |
| Authors: | FANG Yuan XIAO Guo-qiang DAI Yi |
| |
| Affiliation: | FANG Yuan XIAO Guo-qiang DAI Yi(College of Computer & Information Science,Southwest University,Chongqing,China) |
| |
| Abstract: | The majority of existing work on sports video analysis concentrates on highlight extraction.Little work focuses on the important issue as how the extracted highlights should be organized.In this paper,we present a shot classification approach based on sequential pattern mining to automatically segmenting a video into a sequence of recognizable action events.Two research challenges of highlight ranking are addressed,namely affective feature extraction and semantic analysis.A set of visual features,are extrac... |
| |
| Keywords: | Semantic Track and Field Video Frequent Sequential Pattern Video Classification |
| 本文献已被 CNKI 等数据库收录！ |
|
