J4

• 研究论文 • 上一篇    下一篇

一种新的镜头边界检测算法

田玉敏;赵缙;吴自力
  

  1. (西安电子科技大学 计算机外部设备研究所,陕西 西安 710071)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-04-20 发布日期:2008-03-28

Shot boundary detection algorithm based on co-histogram

TIAN Yu-min;ZHAO Jin;WU Zi-li
  

  1. (Research Inst. of Computer Peripherals, Xidian Univ., Xi′an 710071, China)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-04-20 Published:2008-03-28

摘要: 提出基于联合直方图的镜头边界检测算法,利用相邻帧帧间联合直方图关于对角线的对称度在同一镜头内很高,而在镜头切换处很低的特性,定义相邻帧的相似度,通过对相似度做差分突出切变特征,同时引入有限自动机提高渐变检测的鲁棒性,并将切变和渐变检测紧密结合,获得了较好的检测效果.对多种类型的视频序列进行测试的实验结果表明,检测结果达到了95.6%的查全率和95.8%的查准率.

关键词: 视频检索, 镜头边界检测, 联合直方图, 切变, 渐变

Abstract: A new algorithm based on the co-histogram between two consecutive frames is presented. In the algorithm, the similarity is defined based on the co-histogram symmetry which is high in the same shot, but low in a shot transition. The similarity effectively reveals the transition characteristics. The difference of similarities is used to enhance the abrupt transition features, and a Finite-State Automata is used to improve the robustness in detecting gradual transition. Experiments testing various videos show that the algorithm achieves a performance with 95.6% recall and 95.8% precision.

Key words: video retrieval, shot boundary detection, co-histogram, abrupt transition, gradual transition

中图分类号: 

  • TP391