基于高斯点特征的红外弱目标探测方法  

Small Target Detection based on Gassian Point Feature

作　　者：王淑敏[1,2] 王琳[1] 明勇[3,4] 

机构地区：[1]许昌职业技术学院信息工程系,河南许昌461000 [2]许昌市耕新信息科学研究院,河南许昌461000 [3]成都理工大学地球物理学院,四川成都610009 [4]国家开放大学,四川成都610051

出　　处：《应用激光》2016年第5期600-604,共5页Applied Laser

基　　金：国家自然科学基金资助项目(项目编号:617071121);四川省教育厅科研项目(项目编号:13ZAO125);河南省高等教育教学改革研究资助项目(项目编号:2014SJGLX432)

摘　　要：提出一种基于高斯点特征的方法来解决红外背景下弱目标的探测问题。首先,利用高斯斑点目标的对称特性构造高斯斑点特征响应函数,利用该函数在红外单帧图像上提取高斯点特征响应图;然后,使用CFAR方法对响应图进行二值分割,并对该图像进行形态学运算去除噪声干扰;最后检测并定位目标,输出目标在图像上的坐标。实验结果表明,提出的方法比传统的滤波探测方法及文献提出的双边滤波算法对高斯斑点目标检测结果更好。A new algorithm based on Gaussian point feature is proposed to solve the small target detection problem under infrared background.Firstly,a Gaussian point feature response function which is structured by the symmetry of Gaussian point is used to extract a Gaussian point feature response image from infrared single frame image.Then,CFAR method is used for response image binary segmentation,and morphological operation to remove noise in the image.Finally,detect and locate target,output the coordinate position of target in image.The experimental results show that the proposed method has obvious advantages of Gaussian point detection as compared to traditional filter detection method and the literature of bilateral filtering algorithm.

关 键 词：高斯点特征 CFAR 红外弱目标探测 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]