改进的ViBe运动目标检测算法  

Moving target detection algorithm with improved Vi Be

作　　者：刘春[1] 翟志强[1] 

机构地区：[1]合肥工业大学电气与自动化工程学院,安徽合肥230009

出　　处：《传感器与微系统》2017年第1期123-126,共4页Transducer and Microsystem Technologies

基　　金：安徽省科技攻关项目(1301b042017)

摘　　要：针对传统Vi Be运动目标检测算法提取的目标存在鬼影区域、且有闪烁像素点干扰的问题,提出一种结合Surendra背景更新算法而改进的Vi Be算法进行运动目标检测。利用Surendra算法快速更新背景的特点迭代得到纯净背景;对Vi Be算法检测前景进行像素标记和鬼影分类判别,去除鬼影像素点和闪烁像素点;输出新的前景。实验表明:该算法可以有效地去除Vi Be算法前景检测中的鬼影,并能抑制闪烁像素噪声,获取更精确的前景图像。Aiming at problem of Ghost regions and flicker pixels interference which are existed in target extracted by traditional Vibe moving objects detection algorithm, an improved ViBe algorithm is proposed based on surendra background update algorithm. Characteristics of quick update background of surendra algorithm are applied to iterate and get pure background. Detect foreground of ViBe algorithm are pixel labeled and ghost identified to remove ghost and flicker pixels point. New foreground is output. Experimental results show that the proposed algorithm can effectively remove ghost of foreground detection of ViBe algorithm, and can restrain the flicker pixels noise, and get more accurate foreground image.

关 键 词：Vi Be算法 运动目标检测 鬼影 闪烁像素噪声 Surendra算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]