首页 | 本学科首页   官方微博 | 高级检索  
     

一种视频序列中运动目标检测算法
引用本文:张起贵,张光伟. 一种视频序列中运动目标检测算法[J]. 昆明理工大学学报(自然科学版), 2010, 35(4): 67-70. DOI: 10.3969/j.issn.1007-855x.2010.04.014
作者姓名:张起贵  张光伟
作者单位:太原理工大学信息工程学院,山西,太原,030024
基金项目:太原理工大学技术开发项目 
摘    要:在现有方法的基础上,提出了一种基于Otsu动态阈值背景差法和三帧差法相结合的运动日标检测方法.首先通过改进的Surendra算法建立背景模型,并由Otsu动态阈值背景差分法得到二值图像,然后与三帧差分法结合,得到可靠的运动目标区域并进行背景实时更新.实验结果表明该方法满足视频序列运动目标检测的实时性和准确性要求.

关 键 词:背景差分  三帧差分  背景模型  运动目标检测  视频序列

A Moving Target Detection Algorithm in Video Sequences
ZHANG Qi-gui,ZHANG Guang-wei. A Moving Target Detection Algorithm in Video Sequences[J]. Journal of Kunming University of Science and Technology(Natural Science Edition), 2010, 35(4): 67-70. DOI: 10.3969/j.issn.1007-855x.2010.04.014
Authors:ZHANG Qi-gui  ZHANG Guang-wei
Affiliation:(Department of Information Engineering,Taiyuan University of Technology,Taiyuan,030024,China)
Abstract:A new motion detection and background updating method is developed based on the background subtraction using Otsu dynamic threshold and three frame differencing.Firstly,a background model is established based on improved Surendra algorithm.The binary image is then obtained using background subtraction,which is then combined with the three frame differencing to gain more reliable moving target region and update background real-timely.It is shown through the result that the method can satisfy the requirement of real-time and accuracy in the video sequences.
Keywords:background subtraction  three frame differencing  background model  moving target detection  video sequence
本文献已被 CNKI 维普 万方数据 等数据库收录!
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