计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (3): 246-248.DOI: 10.3778/j.issn.1002-8331.2010.03.075

• 工程与应用 • 上一篇    

基于背景更替和动态扩展滤波的目标提取方法

王双林,康慕宁,邓正宏,李建文   

  1. 西北工业大学 计算机学院,西安 710072
  • 收稿日期:2008-07-24 修回日期:2008-10-06 出版日期:2010-01-21 发布日期:2010-01-21
  • 通讯作者: 王双林

Object separating algorithm based on background alternation and dynamic expanding filter

WANG Shuang-lin,KANG Mu-ning,DENG Zheng-hong,LI Jian-wen   

  1. School of Computer Science,Northwestern Polytechnical University,Xi’an 710072,China
  • Received:2008-07-24 Revised:2008-10-06 Online:2010-01-21 Published:2010-01-21
  • Contact: WANG Shuang-lin

摘要: 减背景法是计算机视觉领域常用的前景目标获取方法,减背景法的关键是背景模型的建立和更新以及减除背景后的噪声滤除。基于统计的背景建模方法计算量都比较大,背景更替方法建模避免了大量的计算。动态扩展滤波法是一种对前景目标信息破坏程度低,对噪声具有很好滤出效果的滤波方法。在摄像头静止的情况下,利用背景更替的背景建模及更新方法结合动态扩展滤波能够提取出清晰的前景目标。

Abstract: Background subtraction is a method used mostly to get foreground objects in computer vision field;the keys of background subtraction are the building and updating of background and filtering of noises.The method based on background alternation needs a little of computation than the one based on statistic.Dynamic expanding filtering can do a little damage to the foreground objects and remove noises very well.When the camera is immobile,by using the methods mentioned,the foreground objects can be gotten clearly.

中图分类号: