复杂背景下实时运动目标的提取  

Real-time extraction of object in clutter background

作　　者：李岩[1] 何昕[1] 魏仲慧[1] 王军[1] 

机构地区：[1]中国科学院长春光学精密机械与物理研究所

出　　处：《光学技术》2008年第3期372-374,共3页Optical Technique

基　　金：国家计划863资助项目

摘　　要：提出了一种结合帧间减法与背景自适应更新的算法,结合高速图像处理平台,以满足实时运动目标的提取。着眼于算法的高速性并提出一种足够快的方法用于弹道测量系统。用高斯分布建立每个像素的灰度模型,这个分布用来区分前景和背景像素以便用来更新背景模型。实验表明该系统可以满足靶场弹道测量任务实时性的要求,传统大量占用系统资源的算法在该系统中得到改善,大大提高了系统的实时性。An algorithm base on two consecutive frames and adaptive background updating with a high performance image processing plat is presented to do the real time moving target extracting. The speed of algorithm is concentrated and a method that fast enough to be used in ballistic measuring system is presented. The history of each pixel using Gaussian distribution is modded. The distribution are used to clarify the pixe[ to foreground and background pixel and thus to update the background model. The results show that the system fit the need of real time measuring. In this system, the traditional arithmetic that time-consuming largely is improved.

关 键 词：实时图像处理 目标提取 光学测量 自适应背景更新 

分 类 号：TH74[机械工程—光学工程]