基于高斯混合模型机载下视运动目标检测方法  

Moving Target Detection Method for Airborne Platform Based on Gaussian Mixture Model

作　　者：徐保勇[1] 王媛丽[2] 王平[1] 高颖慧[1] 范庆明[1] 

机构地区：[1]国防科学技术大学ATR国家重点实验室,长沙410073 [2]北京特种工程设计研究院,北京100028

出　　处：《重庆理工大学学报（自然科学）》2011年第11期56-62,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61103082);国家重点实验室基金资助项目(9140A01010309KG01);武器装备预研基金资助项目(9140C8002011204)

摘　　要：针对机载光电系统目标检测的特点,提出了一种基于平台运动补偿与高斯混合模型相结合的下视场景运动目标检测方法。通过图像配准实现平台的运动补偿,然后建立自适应高斯混合模型,经背景差法提取运动目标,采用多次假设检验的方式剔除提取出来的潜在目标中的干扰目标。实验结果证明,该方法对机载运动平台下运动目标检测快速有效。Based on the characteristics of the objects detection in airborne optoelectronic systems,an algorithm for detecting moving object in downward-looking systems,which combines the platform motion compensation and Gaussian mixture models（GMM）,is proposed in this paper.Firstly,this algorithm compensates the motion for the airborne platform by image registration,then constructs adaptive Gaussian mixture models,and extracts the moving objects using background-subtracting method.At last,the interfering objects are eliminated by multilevel hypothesis testing.Experimental results demonstrate that the proposed algorithm is fast and effective for the objects detection under the airborne platform.

关 键 词：机载平台 运动目标检测 平台运动补偿 高斯混合模型 

分 类 号：TN911.73[电子电信—通信与信息系统]