基于主成分分析的目标热红外伪装效果评价研究  

Research on target thermal infrared camouflage effect evaluation based on PCA

作　　者：郑自强 李凌 乔宇 吕城龙 ZHENG Zi-qiang;LI Ling;QIAO Yu;LV Cheng-long(Graduate School,The Army Engineering University of PLA,Nanjing 210007,China;Engineering College of Field Engineering,The Army Engineering University of PLA,Nanjing 210007,China)

机构地区：[1]陆军工程大学研究生院,江苏南京210007 [2]陆军工程大学野战工程学院,江苏南京210007

出　　处：《激光与红外》2023年第3期431-438,共8页Laser & Infrared

基　　金：军委科技委基础加强计划技术领域基金项目(No.2019-JCJQ-JJ-005)资助。

摘　　要：为解决目标热红外伪装效果评价主观性强、量化分析不全面等问题,综合提取了温度、纹理、形状及统计4类一级指标,并细分提取10个二级指标,建立评价指标体系。针对多属性决策问题权重难以客观确定的缺陷,运用PCA对评价指标进行主成分分析,降维处理后选取影响热红外伪装效果的主成分因子,计算综合分值并排序。利用该算法对在不同时间和背景下的坦克模型热红外伪装效果进行评价,结果表明该算法对目标热红外伪装效果评价行之有效,可为指挥员判别热红外伪装方案优劣提供决策参考。In order to solve the problems of strong subjectivity and incomplete quantitative analysis of target thermal infrared camouflage effect evaluation,four first-level indicators of temperature,texture,shape and statistics were comprehensively extracted,and 10 second-level indicators were subdivided to establish an evaluation index system.Aiming at the defect that the weight of the multi-attribute decision-making problem is difficult to objectively determine,PCA is used to analyze the principal components of the evaluation indicators.The algorithm is used to evaluate the thermal infrared camouflage effect of the tank model under different times and backgrounds.The results show that the algorithm is effective in evaluating the thermal infrared camouflage effect of the target,and can provide decision-making reference for the commander to judge the pros and cons of the thermal infrared camouflage scheme.

关 键 词：伪装效果评价 热红外 图像特征 主成分分析 主成分因子 

分 类 号：E951.4[军事—军事工程] TN976[电子电信—信号与信息处理]