上海交通大学学报

上海交通大学学报（自然版）

• 自动化技术、计算机技术 • 上一篇    下一篇

基于融合MPEG-7描述子和二次预测机制的视频自动分类算法

陈斌，蒋兴浩，孙锬锋   

  1. （上海交通大学 信息安全工程学院,上海市信息安全综合管理技术研究重点实验室， 上海 200240）
  • 收稿日期:2009-06-05 修回日期:1900-01-01 出版日期:2010-03-30 发布日期:2010-03-30

An Automatic Video Classification Scheme Based on Combination of MPEG7 Descriptors and SecondPrediction Strategy

CHEN Bin,JIANG Xinghao，SUN Tanfeng   

  1. (1.School of Information Security Engineering, Shanghai Information Security Management and Technology Research Key Lab, Shanghai Jiaotong University, Shanghai 200240, China)
  • Received:2009-06-05 Revised:1900-01-01 Online:2010-03-30 Published:2010-03-30

摘要： 针对互联网上日益增长的视频数量，提出了一种大量融合MPEG7描述子并启用二次预测机制的视频自动分类方法.研究了颜色、纹理、形状、运动等9种MPEG7描述子，从5类视频中提取并融合这些描述子作为视频的整体特征，输入支持向量机（SVM）中进行模型训练和预测.在传统支持向量机的11方法中，通过启用二次预测机制来提高分类的准确率.实验结果表明，该方法与其他方法相比有较高的准确率，适合大规模、复杂环境下的视频自动分类任务.

关键词: 视频分类, MPEG-7描述子, 二次预测, 支持向量机

Abstract: To deal with the growing amount of videos on the Internet, this paper presented a scheme for automatic video classification based on the combination of MPEG7 descriptors and secondprediction strategy. Nine MPEG7 descriptors such as color, texture, shape and motion were extracted from five different genres of videos and combined as a whole representative feature. Then it was put into an SVM classifier to train the model and predict. The traditional 11 method was modified with a secondprediction strategy to improve the classification accuracy. The experiments on a broad range of video data demonstrate that the accuracy of our classification scheme is higher than other existing schemes and the scheme is suitable for the largescale video classification task under a complex environment.

中图分类号: