作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (12): 197-199. doi: 10.3969/j.issn.1000-3428.2008.12.070

• 多媒体技术及应用 • 上一篇    下一篇

一种快速的视频序列运动分割方法

梁英宏,王知衍,曹晓叶,许晓伟   

  1. (华南理工大学计算机科学与工程学院,广州 510640)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-06-20 发布日期:2008-06-20

High Speed Method for Motion Segmentation in Video Sequences

LIANG Ying-hong, WANG Zhi-yan, CAO Xiao-ye, XU Xiao-wei   

  1. (School of Computer Science & Engineering, South China University of Technology, Guangzhou 510640)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-06-20 Published:2008-06-20

摘要: 提出一种视频序列运动分割的实时方法,该方法通过两次背景更新提取运动前景,其中长程背景更新检测噪声运动区域,并将长时间停留在场景中的物体纳入背景范围,短程背景更新利用单高斯分布模型实现对光线缓慢变化的适应。采用基于颜色空间的方法实现对阴影的消除,通过投影分割提取出不同的运动目标。试验证明该方法能够快速、精确地实现视频序列中多个运动目标的分割,消除背景噪声运动、目标阴影以及场景变化的影响。

关键词: 运动分割, 视频序列, 背景更新, 阴影消除

Abstract:

This paper proposes a real-time motion segmentation method for video sequences. The background image is reconstructed by using the long-term and short-term background updating algorithms. The long-term updating algorithm detects the noisy motion regions and the ghosts (detected as in motion but not corresponding to any real moving object), while the short-term updating algorithm models the background pixel values with single Gaussian distributions to deal with slow lighting changes. The shadows are removed via the color space based approach. Different targets are located with the projection approach. Experimental results prove that the presented method is robust to background noisy motions, shadows and scene changes, and can segment multiple objects precisely and quickly.

Key words: motion segmentation, video sequences, background updating, shadow removing

中图分类号: