一种去光照干扰方法在行人检测中的应用  

Method of illumination changes elimination applied in pedestrian detection

作　　者：孙炜[1] 杨鹏飞[1] 王聪[1] 李飞[1] 郑来芳 

机构地区：[1]湖南大学电气与信息工程学院,长沙410082

出　　处：《计算机应用研究》2014年第11期3514-3516,3520,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61072121);湖南省自然科学基金资助项目(12JJ2035);国家教育部高等学校博士学科点专项科研基金资助项目(20130161110009)

摘　　要：在基于图像差分的行人检测算法中,光照的变化对提取图片中的行人干扰非常大,一般的自适应背景更新方法很难消除光照快速变化带来的影响。为了解决这一问题,设计了一种基于直方图分布特征相似性的光照变化干扰去除方法,分析了光照干扰前后两幅图片局部区域的直方图分布特征相似性原理,给出了图像直方图分布特征相似性测量方法及评价参数——标准差。通过对光照频繁变化环境下相邻两帧图片进行差分实验,结果表明,该方法能够克服光照突然变化的干扰且鲁棒性好,能够准确分割出运动目标和抑制大幅度光照变化带来的干扰。The change of illumination have a serious effect on pedestrian detection algorithms based on image difference,gen-eral adaptive background updating methods is difficult to eliminate the effects of illumination change.This paper proposed a new method of illumination changes elimination based on similarity of histogram distribution to solve this problem.It analyzed similarity of histogram distribution on local area between illumination changed image and normal image.It presented standard deviation of image which could use to measure similarity of histogram distribution.Through image difference experiment be-tween two adjacent frames acquired under light frequency change environment,it shows that the method has a outstanding per-formance in robustness which can segment the moving targets accurately and restrain the changes of illumination significantly.

关 键 词：光照变化 行人检测 图像差分 直方图分布 图像标准差 视频监控 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]