利用改进型AAGD算法的红外小目标检测  

Infrared small target detection using improved aagd algorithm

作　　者：罗莎[1] 朱新琰[1] 陈新锐[1] 卢运娇[2] 李美求[3] LUO Sha;ZHU Xinyan;CHEN Xinrui;LU Yunjiao;LI Meiqiu(Department of Electronic Information Engineering,Beihai Vocational College,Beihai 536000,China;Department of mechanical and electrical engineering,Beihai Vocational College,Beihai 536000,China;College of Mechanical Engineering,Yangtze University,Jingzhou 434203,China)

机构地区：[1]北海职业学院电子信息工程系,广西北海536000 [2]北海职业学院机电工程系,广西北海536000 [3]长江大学机械工程学院,湖北荆州434023

出　　处：《光学技术》2021年第5期632-640,共9页Optical Technique

基　　金：国家重点研发计划项目(2016YFC0303703);2019年度广西高校中青年教师基础能力提升项目(2019KY1593)。

摘　　要：针对红外目标检测中小目标检测精度较低的问题,提出了一种利用改进型平均绝对灰度差(AAGD)算法的红外小目标检测。针对AAGD算法的缺点,在其基础上,融合灰度与显著性特征,用于核相关滤波器,以解决红外目标特征简单且信息量少的问题;提出一种自适应双滑动窗口,针对不同区域调节聚合窗口形状及像素点权重,以实现高强度结构背景附近的机动目标的匹配,提高小目标检测的准确度;利用MATLAB仿真平台对所提方法进行实验论证,结果表明,所提方法能够在噪声、高强度锐利边缘和结构背景等复杂图像中准确检测出小目标,且其准确度、稳定性、执行时间等方面均优于其他对比方法。Aiming at the problem of low detection accuracy of small target in infrared target detection,an improved Average Absolute Gray Difference(AAGD)algorithm is proposed to detect small infrared targets.Firstly,in view of the shortcomings of aagd algorithm,on the basis of it,the gray and saliency features are fused and used in the kernel correlation filter to solve the problem of simple features and less information of infrared target.Then,an adaptive double sliding window is proposed,which adjusts the shape of the aggregation window and the weight of pixels according to different regions to realize the matching of maneuvering targets near the background of high-intensity structure and improve the accuracy of small target detection.Finally,Experimental demonstration of the proposed method based on the MATLAB simulation platform shows that the proposed method can accurately detect small targets in complex images such as noise,high-intensity sharp edges and structural backgrounds,and its accuracy,stability and execution time are better than other comparison methods.

关 键 词：红外小目标检测 改进型AAGD算法 混合特征提取 核相关滤波器 自适应双滑动窗口 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]