基于数据驱动的激光图像弱小目标定位研究  

Research on weak and small target location in laser image based on data driving

作　　者：黄建军[1] 彭雪梅[1] HUANG Jianjun;PENG Xuemei(Nanchang Institute of Technology,Nanchang 330044,China)

机构地区：[1]南昌理工学院,南昌330044

出　　处：《激光杂志》2022年第9期109-113,共5页Laser Journal

基　　金：江西省教育厅科学技术研究项目(No.GJJ191012)。

摘　　要：当前定位方法难以精确实现激光图像弱小目标定位,为此提出了基于数据驱动的激光图像弱小目标定位方法。首先采集弱小目标的激光图像,并进行预处理,抑制一些噪声对弱小目标的激光图像干扰,然后采用数据驱动技术对弱小目标的激光图像进行学习,建立激光图像弱小目标定位模型,最后与测试结果表明,本方法的图像弱小目标定位效果明显优于对经典方法,数据驱动的激光图像弱小目标定位准确率超过94.22%,提升了弱小目标定位的召回率,图像弱小目标定位时间控制在9 s以内,可用于后续的图像弱小目标检测与跟踪。current positioning methods are difficult to accurately locate the weak and small target in laser image.Therefore,a data-driven weak and small target positioning method in laser image is proposed.Firstly,the laser image of the weak and small target is collected and preprocessed to suppress the interference of some noise on the laser image of the weak and small target,and then the data-driven technology is used to learn the laser image of the weak and small target,and the laser image weak and small target positioning model is established.Finally,the experimental results show that the image weak and small target positioning effect of this method is obviously better than that of the classical method,The accuracy of data-driven laser image dim target positioning exceeds 94.22%,which improves the recall rate of dim target positioning.The image dim target positioning time is controlled within 9 s,which can be used for subsequent image dim target detection and tracking.

关 键 词：数据驱动 激光图像 弱小目标 定位准确率 对比测试 

分 类 号：TN279[电子电信—物理电子学]