复杂背景下运动目标检测方法  

Detection method for moving target in complex environment

作　　者：徐功益[1] 蔡敬菊[1] 宿丁[1] 

机构地区：[1]中国科学院光电技术研究所

出　　处：《红外与激光工程》2007年第6期992-995,共4页Infrared and Laser Engineering

基　　金：国家863计划高新技术预研课题资助项目(2003AA823050)

摘　　要：利用相邻两帧图像的运动信息更新特征块提取阈值,实时地提取出当前帧图像中最能体现背景运动特征的特征块。采用块匹配的运动估计方法获取了各块的运动矢量,再依据所有特征块运动矢量的统计特性提取出背景运动矢量来配准差分,实现了目标的检测。实验结果表明,此方法能有效地检测复杂背景下的运动目标。In this method, an adaptive threshold is adopted to extract the blocks which can stand for the motion characteristic of the background using the motion information of the two sequential frames of image. Block matching is applied to each block to estimate its motion vector. And then the motion vector of the background can be achieved based on the statistic characteristic of the motion vectors of the blocks. At last, the moving target is detected after image registration and difference operation. Experimental results show that the algorithm works efficiently in detecting the moving target in complex environment.

关 键 词：复杂背景 运动目标检测 块匹配 运动矢量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]