基于近红外图像的自动报靶方法研究  

Research on Automatic Target Reporting Method Based on Near Infrared Image

作　　者：王浩 王劲松[1,2] 高奔 唐卓 杨业涛 WNAG Hao;WANG Jinsong;GAO Ben;TANG Zhuo;YAHG Yetao(School of Opto-Electronic Engineering,Changchun University of Science and Technology,Changchun 130022;Zhongshan Institute of Changchun University of Science and Technology,Zhongshan 528437)

机构地区：[1]长春理工大学光电工程学院,长春130022 [2]长春理工大学中山研究院,中山528437

出　　处：《长春理工大学学报（自然科学版）》2023年第2期55-62,共8页Journal of Changchun University of Science and Technology(Natural Science Edition)

基　　金：吉林省重点研发项目(20180201025GX)。

摘　　要：针对传统的自动报靶系统易受环境光照的影响,提出一种基于近红外图像的自动报靶方法。先对靶面图像进行模板匹配、几何校正、裁剪等预处理,再采用直方图均衡化对灰度图像进行增强,得到对比度较高的靶面图像,并提出了一种基于分水岭图像分割的弹孔识别方法,解决了传统自动报靶对字符和环线处理不干净的问题,利用Sober算子对弹孔边缘检测并计算出弹孔圆心坐标,最后基于线性约束的环值判定算法完成环值判定。实验结果表明:在不同的环境光照下,本文方法弹孔识别准确度可达93.7%,符合野外射击训练要求。Aiming at the problem that the current automatic target reporting system based on traditional image processing is greatly affected by ambient light,combined with the characteristics of near-infrared imaging that is not affected by light,this paper proposes an automatic target reporting method based on near-infrared images.Due to the problems of poor resolution,low contrast and blurred visual effects in the near-infrared image,histogram equalization was used to enhance the grayscale image,and a bullet hole recognition method based on watershed image segmentation was proposed,which solved the problem of traditional automatic reporting.Targets deal with the problem of unclean characters and ring lines,and the ring value judgment of the target is completed by using the ring area feature mark.Finally,a linear constraint-based ring value determination algorithm is used to complete the ring value determination.The experimental results show that the accuracy of bullet hole recognition can reach 93.7%under different ambient lighting,which meets the requirements of field shooting training.

关 键 词：自动报靶 近红外图像 分水岭算法 图像增强 

分 类 号：TN911[电子电信—通信与信息系统]