视频检测系统中的背景更新算法研究

摘要

实际场景中环境是动态变化的,如灯光或太阳光产生的亮、暗变化以及由于太阳光照射角度产生的阴影位置变化等情况。需要对背景进行实时更新。为此,提出了一种基于分块的无初始背景约束的更新方法。算法在一定时间内根据块匹配判断该块是否处于稳定状态,进而利用块的均值和方差决定此块是否处于连续的稳定状态,从而判定该块是否需要更新。算法通过现场数据实验,包括隧道中车流量较小的、隧道中车流量较大的、隧道出口光线变化剧烈的、隧道出口阴影位置变化等环境,结果表明在各种环境下背景更新都有较好的效果。%Changes of environment is dynamic,such as light,the sun light and shadow area under different reflections.In these conditions it needs real-time background updating.This paper presents a method of background updating based on block.Algorithm is done according to the block matching in stable condition in a certain period,then use block mean and variance to decide whether this block in the continuous stable state,and decide whether the block need updating,through a lot of experiments,including the condition in the tunnel,the light changes in the tunnel and the shadow position changes,etc.The results indicate that background updating have better effect.