基于背景差分法和帧间差分法的车辆运动目标检测  

A New Vehicle Moving Detection Method Based on Background Difference and Frame Difference

作　　者：罗敏 刘洞波[1] 文浩轩 陈鑫海 宋丹[1] LUO Min;LIU Dong-bo;WEN Hao-xuan;CHEN Xin-hai;SONG Dan(College of Computer and Communication,Hunan Institute of Engineering,Xiangtan 411104,China)

机构地区：[1]湖南工程学院计算机与通信学院

出　　处：《湖南工程学院学报（自然科学版）》2019年第4期58-61,共4页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湖南省研究生科研创新项目(CX2017B783);国家级大学生创新创业训练计划项目(201711342010)

摘　　要：针对背景差分法和帧间差分法在检测车辆运动目标时存在阴影的问题,提出一种结合背景差分法和帧间差分法去除阴影的车辆运动目标检测算法.首先采用均值法从图像序列建模获取背景,通过背景差分法对当前帧进行差分得到背景差分图,二值化得到二值图.然后利用改进Robert算子对二值图与背景差分图进行边缘检测.最后通过对两张边缘图像进行帧间差分,得到去除阴影的车辆运动目标.Aiming at the problems of background difference and frames difference in separating vehicle moving object,this paper proposes a target detection algorithm combining Background Difference and Frames Difference to remove shadow.First,the mean value method is used to obtain the background image from the sequence image,and the current frame and background image for background difference is used to get the background difference image,and binarization is used to get the binary image.Then,the improved Robert operator is used to detect the edge of the binary image and background difference image.Two edge image frame difference is done to get the object of suppressing shadow.

关 键 词：目标检测 背景差分法 帧间差分法 ROBERT算子 阴影去除 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]