基于增强局部对比度的红外弱小目标检测方法  

Infrared Dim Small Target Detection Method Based on Enhanced Local Contrast

作　　者：袁明 宋延嵩[2] 张梓祺 赵馨[1] 赵博 Yuan Ming;Song Yansong;Zhang Ziqi;Zhao Xin;Zhao Bo(College of Electronic Information Engineering,Changchun University of Science and Technology,Changchun 130022,Jilin,China;Institute of Space Photoelectrics Technology,Changchun University of Science and Technology,Changchun 130022,Jilin,China)

机构地区：[1]长春理工大学电子信息工程学院,吉林长春130022 [2]长春理工大学空间光电技术研究所,吉林长春130022

出　　处：《激光与光电子学进展》2023年第4期75-81,共7页Laser & Optoelectronics Progress

基　　金：吉林省科学技术厅项目(202002036JC)。

摘　　要：针对局部对比度方法对红外目标进行检测时难以提升目标的显著性及抑制背景困难的问题,提出一种基于特殊预处理的增强局部对比度方法来检测目标。通过快速中值滤波去除高频噪声,通过改进的形态学梯度来抑制背景,通过增强的局部对比度来提高目标的显著性,最后通过自适应阈值来获取需要检测的真实目标。结果表明,同经典人类视觉系统的检测方法相比,所提方法在检测红外弱小目标时具有优越性,在高亮度背景情况下效果更为显著。The local contrast method is difficult to improve the significance of the target and suppress the background in infrared target detection,thus an enhanced local contrast method based on ring special preprocessing is proposed to detect targets.The highfrequency noise is removed by fast median filtering,the background is suppressed by improved morphological gradient,the significance of the target is improved by enhanced local contrast,and finally the real target to be detected is obtained by selfadaptive threshold.The results show that compared with the classical detection methods of human visual system,the proposed method has advantages in detecting infrared weak and small targets,and the effect is more significant in high brightness background.

关 键 词：红外弱小目标 目标检测 人类视觉系统 局部对比度 快速中值滤波 形态学梯度 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]