首页 | 本学科首页   官方微博 | 高级检索  
     

融合帧差和Vibe的运动目标检测算法
引用本文:魏洪涛,李瑾.融合帧差和Vibe的运动目标检测算法[J].计算机应用研究,2017,34(5).
作者姓名:魏洪涛  李瑾
作者单位:武汉理工大学 信息学院,武汉理工大学 信息学院
基金项目:国家自然科学基金资助项目
摘    要:Vibe算法是一种快速高效的背景建模算法,但该算法在运动目标检测过程中会产生鬼影。本文针对Vibe算法中鬼影消除缓慢的问题,结合多个场景的交通视频提出一种通过连续两帧前景背景像素时域变化来判断鬼影像素点并消除的方法,该方法加快了鬼影的消除速度。同时,对于视频拍摄场景中的背景噪声,采用了对前景图进行开闭操作去除小像素点以及对目标区域的空洞进行填充处理。实验表明,改进的Vibe算法能够加快鬼影的消除,并且与帧差法以及混合高斯建模算法相比,前景检测效果更精确。

关 键 词:运动目标检测  Vibe算法  帧差法  鬼影消除
收稿时间:2016/3/28 0:00:00
修稿时间:2017/3/5 0:00:00

A moving object detection algorithm using Vibe combined with frame-difference
Wei Hongtao and Li Jin.A moving object detection algorithm using Vibe combined with frame-difference[J].Application Research of Computers,2017,34(5).
Authors:Wei Hongtao and Li Jin
Affiliation:School of Information Engineering, Wuhan University of Technology,
Abstract:Vibe algorithm is an effective and quick background modeling algorithm. During the moving target detection, the Vibe will produce the ghost and eliminate slowly. In order to solve the problems caused by the execution of Vibe algorithm, this paper proposes an improved algorithm for the traffic video. The ghost pixel is judged by the change of two consecutive frames in time domain, which can speed up the ghost to eliminate. In addition, to solve the noise in the complex background, we apply a morphology post-processing with opening operation and closing operation to remove the noise, then filling the holes in the target zone to highlight the prospect target. Experiments show that the improved algorithm can absorb the ghost quickly and detect the foreground better compared with frame-difference and GMM.
Keywords:moving object detection  vibe algorithm  frame-difference algorithm  ghost elimination
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号