基于权重强化局部方差对比的红外小目标检测  

Infrared Small Target Detection Based on Weighted Strength and Local Variance Properties

作　　者：张国峰 马洪兵 艾斯卡尔·艾木都拉[1] ZHANG Guofeng;MA Hongbing;Askar Hamdulla(College of Information Science and Engineering,Xinjiang University,Urumqi 830046,China;Department of Electronic Engineering,Tsinghua University,Beijing 100084,China;School of Mechanical and Electrical Engineering,Changji Vocational and Technical College,Changji 831103,China)

机构地区：[1]新疆大学信息科学与工程学院,乌鲁木齐830046 [2]清华大学电子工程系,北京100084 [3]昌吉职业技术学院机电工程分院,新疆昌吉8311003

出　　处：《电讯技术》2021年第10期1263-1269,共7页Telecommunication Engineering

基　　金：上海航天科技创新基金资助项目(SAST2019-48)。

摘　　要：针对红外图像中背景与目标对比度低、边缘高亮的问题,提出了一种用于红外小目标检测的局部方差对比测度算法。该算法由局部方差对比测度的计算和权重强化函数的设计两个模块组成:局部区域对比利用目标区域三层图像块模型之间的方差差异突出增强真实目标;权重强化函数的设计是为了能更好地抑制背景杂波,充分考虑了目标的统计特征、目标与其相邻背景的统计差异和背景的统计特征。实验结果表明,该方法在增强小目标和抑制背景杂波方面具有较好的效果,时间较短,鲁棒性好。For the problems of low contrast between background and target and highlighted edge of infrared image,an infrared image detection method based on local variance contrast measure is proposed.It consists of two modules,calculation of the local variance contrast measure and design of weighted strength function.In comparison of local area,the difference of variance between the three-layer image block models in the target area is used to highlight and enhance true target.The design of weighted strength function is to suppress the background clutter in a better way,the statistical characteristics of the target,the statistical difference between the target and its adjacent background,and the statistical characteristics of the background are fully considered.The experimental results show that the proposed method is effective in enhancing small targets and suppressing background clutter with short time and good robustness.

关 键 词：红外图像 小目标检测 权重强化 局部方差 三层图像块 

分 类 号：TN911.73[电子电信—通信与信息系统]