• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2006, Vol. 28 ›› Issue (2): 63-65.

• 论文 • 上一篇    下一篇

图像序列中运动对象的自动提取方法

赵彦玲[1] 张之超[2] 高振明[2] 张庆超[3]   

  • 出版日期:2006-02-01 发布日期:2010-05-20

  • Online:2006-02-01 Published:2010-05-20

摘要:

本文在快速准确的原则上,仅利用视频序列中的时域信息,提出了一种运动对象的提取方法。首先利用二次帧差求交集的方法求出图像帧的帧差掩模,最后利用二次扫描的方法得到运动对象掩模,填充就可以提取出运动对象。实验证明,该方法提取效果较好,节省了处理时间。

关键词: 运动对象 运动区域 掩模 二次帧差

Abstract:

Based on the rules of speediness and exactness, the method of moving object extraction is proposed only with temporal information. We obtain the frame  difference mask by the intersection of three twice-frame-difference images, then get the moving object mask (MOM) by scanning every column and row. AAt last, by filling MOM with original values we can get the extracted moving object. The experiments show that the method can get a better result with l ess runtime.

Key words: moving object, moving region, frame difference, mask, twice-frame-difference