计算机应用

• 图形与图像处理(Graphics and image proces • 上一篇    下一篇

基于运动点积累的视频运动目标提取

孟苑 王伟   

  1. 西安电子科技大学 西安电子科技大学
  • 收稿日期:2008-06-25 修回日期:2008-08-19 发布日期:2008-12-01 出版日期:2008-12-01
  • 通讯作者: 孟苑

Moving objects extraction in video sequence based on moving point accumulation

<a href="http://www.joca.cn/EN/article/advancedSearchResult.do?searchSQL=(((Meng Yuan[Author]) AND 1[Journal]) AND year[Order])" target="_blank">Meng Yuan</a>   

  • Received:2008-06-25 Revised:2008-08-19 Online:2008-12-01 Published:2008-12-01
  • Contact: Meng Yuan 孟苑

摘要: 通过对视频中运动目标特点的分析,提出了一种提取背景图像的算法。使用运动点积累的方法来更新背景图像,然后应用背景差分准确检测出场景中的运动目标。由于视觉的相似性,使得检测出的目标包含阴影,最后使用阴影滤波函数去除阴影,得到完整的运动物体。实验结果表明,本算法具有较好的实时性和适应性,能检测出比较完整的运动目标信息。

关键词: 背景提取, 运动点积累, 背景差分, 运动目标检测, 阴影检测

Abstract: Through the analysis on the characteristics of the moving objects in video sequence, a method to acquire background was proposed. Moving point accumulation was applied to extract the background, and then background subtraction was employed to detect moving objects. Because of visual comparability, the result included shadow. Shadow filter function was used to remove the shadow to get the completely moving objects. Experimental results show that the algorithm is efficient, adaptive, and establishes a foundation for advanced image processing.

Key words: background extraction, moving point accumulation, background subtraction, moving objects detection, shadow detection