一种有效的道路背景提取与更新算法  

An effective algorithm of road background extraction and updating

作　　者：刘欣页[1] 李文举[1] 高连军[1] 尉秀芹[1] 

机构地区：[1]辽宁师范大学计算机与信息技术学院,辽宁大连116081

出　　处：《微型机与应用》2012年第7期46-48,共3页Microcomputer & Its Applications

基　　金：辽宁省博士启动基金项目(20061052)

摘　　要：针对复杂环境中道路背景图像的快速获取问题,提出了一种快速有效的道路背景提取和更新算法。应用改进的多帧平均算法提取背景,采用改进的Surendra算法对背景进行更新。实验结果表明,该算法能够减轻初始静止车辆对背景建立的影响,能及时消除由于初始帧中目标移动而造成的鬼影,对光线变化鲁棒性高、速度快、更新效果好。Aiming at the problem of fast extracting road background image in complex scenes, an effective algorithm about road background extraction and updating is presented. An improved algorithm for time averaged background images （TABI） is used to the background extraction, then an improved surendra algorithm is applied to the background updating. Experimental results show that the proposed algorithm can reduce the influence of initial static vehicle on the background extraction and eliminate in time the ghosts caused by the motion of objects in the initial frame. The proposed algorithm is robust under lighting variations,fast in speed and satisfactory in updating performance.

关 键 词：背景提取 背景更新 帧间差分 背景差分 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]