Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (16): 197-199.DOI: 10.3778/j.issn.1002-8331.2010.16.057

• 图形、图像、模式识别 • Previous Articles     Next Articles

Moving object detection and shadow removal based on background reconstruction

LIU Chao,HE Ming-yi,FU Yong   

  1. School of Electronics and Information Technology,Northwestern Polytechnical University,Xi’an 710072,China
  • Received:2008-11-25 Revised:2009-02-13 Online:2010-06-01 Published:2010-06-01
  • Contact: LIU Chao


刘 超,何明一,付 勇   

  1. 西北工业大学 电子信息学院,西安 710072
  • 通讯作者: 刘 超

Abstract: An approach to detect moving object and remove shadow with a static camera is proposed,which uses the block background reconstruction based on average intensity and image energy to update the background,associated with background subtraction,connected component detection as well as morphologic filter to achieve the moving object detection and then the edge information of the shadow which is implemented by edge detection algorithm is used to detect and remove the candidate shadow region.The experimental result indicates the method is effective in detecting moving target and suppressing shadow.

Key words: background reconstruction, moving object detection, shadow suppressing, edge information

摘要: 提出了一种静止摄像机条件下的运动目标检测和去除阴影的方法。该方法采用以图像亮度和能量大小为判断依据的分块背景重建方法来快速更新背景,并结合背景相减法,网格化连通域检测,形态学滤波等步骤来检测和提取运动目标,同时运用边缘检测获取阴影边缘信息,并结合形态学运算来去除阴影区域,恢复出完整物体目标。实验结果表明,该方法能够有效地检测出运动目标和抑制阴影。

关键词: 背景重建, 运动目标检测, 阴影抑制, 边缘信息

CLC Number: