基于PCA-超效率DEA的目标热红外伪装效果评价研究

Research on evaluation of target thermal infrared camouflage effectbased on PCA-Super efficiency DEA

为解决目标热红外伪装效果评价过程中主观性过强、量化分析不全面等问题,通过分析目标热红外暴露征候,综合提取了温度、纹理、形状及统计等4类一级指标,并细分多个二级指标,建立了热红外伪装效果评价指标体系,引入超效率数据包络分析(DEA)模型对目标热红外伪装效果进行充分评价。针对评价指标集关联性大的情况,运用主成分分析(PCA)法对指标数据降维处理得到相互独立的主成分因子,通过超效率DEA模型进行计算并排序,解决了因指标信息重叠而使得部分评估结果存在偏差的问题。利用PCA-超效率DEA模型,对目标在不同时间及背景下的热红外伪装效果案例进行评价,结果表明,该算法对热红外伪装效果评价更为客观、准确。

In order to solve the problems such as excessive subjectivity and incomplete quantitative analysis in the process of target thermal infrared camouflage effect evaluation,four primary indicators such as temperature,texture,shape and statistics were comprehensively extracted by analyzing the target thermal infrared exposure symptoms,and multiple secondary indicators were subdivided to establish the thermal infrared camouflage effect evaluation index system.The super efficiency data envelopment analysis(DEA)model was introduced to fully evaluate the target thermal infrared camouflage effect.In view of the large correlation of the evaluation index set,the principal component analysis(PCA)method is used to reduce the dimension of the index data to obtain the mutually independent principal component factors.The super efficiency DEA model is used to calculate and sort,which solves the problem that some evaluation results are biased due to the overlapping of index information.The PCA super efficiency DEA model is used to evaluate the thermal infrared camouflage effect of targets in different time and background.The results show that the algorithm is more objective and accurate in evaluating the thermal infrared camouflage effect.