摘要
针对复杂的天空背景,提出了一种基于显著性与尺度空间的红外弱小目标检测算法。首先通过频域残差法对原始图像进行初步处理,缩小红外弱小目标的待识别目标区域;接着利用Do G算子得到预处理后图像的尺度空间并实行特征点检测,获得最佳尺度图像,再对特征图像进行加权融合;最后通过信息熵分割来实现红外弱小目标的检测。仿真结果表明,本文方法跟文献中所提的优秀算法相比,能有效地检测出红外弱小目标,提升了目标图像的信杂比。同时,能很好地适应不同复杂场景,为红外弱小目标的跟踪应用奠定了基础。
An infrared dim small target detection method based on the saliency and scale-space theory is presented for complex sky background. Firstly,a spectral residual is used to deal with the original image in order to reduce identification area of infrared dim target. Secondly,the difference of Gaussian（ Do G） operator is used to obtain scale space of the image after preprocessing,and feature points are detected,which gets an optimal scale image. Then,the feature images are weighted and fused. Finally infrared dim target detection is achieved by the segmentation of information entropy. Simulation results show that,compared with other reference algorithm,the proposed method can detect the infrared dim target more effectively and enhance the SCR of target image. At the same time,the algorithm can effectively detect dim targets in different complex scenes and lay the foundation for an infrared dim target tracking application.
出处
《激光与红外》
CAS
CSCD
北大核心
2015年第4期452-456,共5页
Laser & Infrared
基金
陕西省自然科学基础研究计划工业攻关项目(No.2012K09-09)
2012年度中央高校基本科研业务费专项资金(No.GK201301008)资助
关键词
红外弱小目标
频域残差法
DoG算子
尺度空间
信息熵
infrared dim target
spectral residual
Do G operator
scale-space
information entropy
