基于模糊综合评判的车辆目标SAR仿真图像评估方法
|
摘要
为了验证理论建模计算合成孔径雷达(synthetic aperture radar,SAR)仿真图像的准确性,给出基于层次分析法(analytic hierarchy process,AHP)、模糊综合评判(fuzzy comprehensive evaluation,FCE)、图像特征与Fisher可分性及目标识别等知识综合的车辆目标SAR仿真图像评估方法。首先确定五级评语集{优秀,良好,中等,较差,很差},然后根据AHP构建评估因素集,分别利用Fisher可分性判据和目标识别率确定二级FCE的两层权重向量,再依据图像相似度评价标准区间构建模糊隶属函数,最后将权重向量和模糊关系矩阵合成计算出仿真和实测图像的FCE结果,即模糊向量,对模糊向量按照最大隶属原则给出评价结果。通过对车辆目标的仿真与实测SAR图像进行比对分析结果显示,该方法可以准确客观地反映出SAR仿真与实测图像之间的相似程度。
In order to evaluate the veracity of synthetic aperture radar(SAR)images by theoretical modeling,a vehicle SAR simulation images validation method is proposed by synthesizing analytic hierarchy process(AHP),fuzzy comprehensive evaluation(FCE),and the technology of image features,Fisher criterion,and target recognition.Firstly,five-degree comments{excellent,good,fair,poor,and very poor}are determined.Secondly,the evaluation factors are established based on the AHP,and then the first-level and second-level weight vectors are obtained by the recognition rates and the Fisher criterion,respectively.Thirdly,the fuzzy membership functions are constructed according to the standard of image similarity.Finally,the result vector of FCE between the simulated and measured images is computed by integrating the weight vectors and the fuzzy matrices,and then the final evaluation result is given by the maximum rule from the vector.By comparing and analyzing the experimental results of vehicles of SAR simulated and measured images,the proposed evaluation method is effective on reflecting the similarities of the simulated and measured images.
In order to evaluate the veracity of synthetic aperture radar(SAR)images by theoretical modeling,a vehicle SAR simulation images validation method is proposed by synthesizing analytic hierarchy process(AHP),fuzzy comprehensive evaluation(FCE),and the technology of image features,Fisher criterion,and target recognition.Firstly,five-degree comments{excellent,good,fair,poor,and very poor}are determined.Secondly,the evaluation factors are established based on the AHP,and then the first-level and second-level weight vectors are obtained by the recognition rates and the Fisher criterion,respectively.Thirdly,the fuzzy membership functions are constructed according to the standard of image similarity.Finally,the result vector of FCE between the simulated and measured images is computed by integrating the weight vectors and the fuzzy matrices,and then the final evaluation result is given by the maximum rule from the vector.By comparing and analyzing the experimental results of vehicles of SAR simulated and measured images,the proposed evaluation method is effective on reflecting the similarities of the simulated and measured images.
引文
[1]周明俊,陆军,高贵,等.基于RCS精确预估的机动目标切片仿真方法[J].计算机应用研究,2009,26(7):2274-2276.ZHOU M J,LU J,GAO G,et al.Simulation method of SAR slice images of vehicle targets based on RCS precise prediction[J].Application Research of Computers,2009,26(7):2274-2276.
[2]李仁杰,计科峰,邹焕新,等.基于电磁散射特性计算的目标SAR图像仿真[J].雷达科学与技术,2010,8(5):395-400.LI R J,JI K F,ZOU H X,et al.Simulation of SAR imagery of target based on electromagnetic scattering characteristic computation[J].Radar Science and Technology,2010,8(5):395-400.
[3]计科峰,张爱兵,邹焕新,等.典型地面车辆目标SAR图像仿真与评估[J].雷达科学与技术,2010,8(3):223-228.JI K F,ZHANG A B,ZOU H X,et al.Simulation and evaluation of SAR imagery of typical ground vehicles[J].Radar Science and Technology,2010,8(3):223-228.
[4]张锐,洪峻,明峰.基于电磁散射的复杂目标SAR回波与图像仿真[J].电子与信息学报,2010,32(12):2836-2841.ZHANG R,HONG J,MING F.SAR echo and image simulation of complex targets based on electromagnetic scattering[J].Journal of Electronics&Information Technology,2010,32(12):2836-2841.
[5]董纯柱,殷红成,王超.基于射线管分裂方法的SAR场景快速消隐技术[J].雷达学报,2012,1(4):436-440.DONG C Z,YIN H C,WANG C.A fast hidden surface removal approach for complex SAR scene based on adaptive ray-tube splitting method[J].Journal of Radars,2012,1(4):436-440.
[6]JIA L,JIA X,HUANG C G.SAR raw data generation and image simulation of aircrafts on the runway[C]∥Proc.of the 7th International Congress on Image and Signal Processing,2014:1115-1119.
[7]PENG L J,LIU M,LIU X H,et al.SAR image classification based on CNN in real and simulation datasets[C]∥Proc.of the9th SPIE International Conference on Graphic and Image Processing,2017.
[8]JI K F,ZHANG A B,ZOU H X,et al.Simulation of SAR images of ground vehicles[C]∥Proc.of the SPIE Automatic Target Recognition and Image Analysis,2009.
[9]WU F,WANG C,WEN X Y,et al.SAR image simulation for object’s feature analysis[C]∥Proc.of the 4th International Workshop on Earth Observation and Remote Sensing Applications,2016:4-6.
[10]HARALD A,TIMO K,MANFRED H,et al.Identification of maritime target objects from high resolution TerraSAR-X data using SAR simulation[C]∥Proc.of the SPIE Radar Sensor Technology XVIII,2014.
[11]JI K F,ZHAO Z,XING X W,et al.SAR imagery simulation of ship based on electromagnetic calculations and sea clutter modeling for classification applications[C]∥Proc.of the 35th International Symposium on Remote Sensing of Environment,IOP Conference Series:Earth and Environmental Science,2014.
[12]ZHANG M,ZHAO Y,NIE D.EM scattering and SAR image simulation from composite sea-ship scene based on a weighted multi-path model[C]∥Proc.of the SPIE Remote Sensing of the Ocean,Sea Ice,Coastal Waters,and Large Water Regions,2016.
[13]PHILIP L D.Measured and predicted synthetic aperture radar target comparison[J].IEEE Trans.on Aerospace and Electronic Systems,2002,38(1):25-37.
[14]胡利平,董纯柱,邢笑宇,等.SAR图像目标和阴影径向积分特征评估[J].电波科学学报,2014,29(2):254-259.HU L P,DONG C Z,XING X Y,et al.An evaluation method of SAR images based on radial integral features of target and shadow[J].Chinese Journal of Radio Science,2014,29(2):254-259.
[15]ORLANDI A,ANTONINI G,POLISINI C,et al.Progress in the development of a 2Dfeature selective validation method[C]∥Proc.of the IEEE International Symposium on Electromagnetic Compatibility,2008:1-6.
[16]毕长剑,董冬梅,张双建,等.作战模拟训练效能评估[M].北京:国防工业出版社,2014.BI C J,DONG D M,ZHANG S J,et al.Operational simulation training effectiveness evaluation[M].Beijing:National Defense Industry Press,2014.
[17]句彦伟,张燕.ISAR图像质量评估方法[J].系统工程与电子技术,2015,37(2):297-303.JU Y W,ZHANG Y.Research on ISAR image quality evaluation[J].Systems Engineering and Electronics,2015,37(2):297-303.
[18]LAO G C,YE W,LI G J,et al.A quality evaluation method of SAR image based on grayscale image and electromagnetic scattering characteristics[C]∥Proc.of the 8th SPIE International Conference on Digital Image Processing,2016.
[19]胡利平,刘宏伟,吴顺君.基于多分类器融合的SAR图像自动目标识别方法[J].系统工程与电子技术,2008,30(5):839-842.HU L P,LIU H W,WU S J.Radar target recognition based SAR image and classifiers fusion[J].Systems Engineering and Electronics,2008,30(5):839-842.
[20]CIRIC M,IGNJATOVIC J,BOGDANOVIC S.Uniform fuzzy relations and fuzzy functions[J].Fuzzy Sets and Systems,2009,160(8):1054-1081.
[21]MARQUES DE SA J P.Pattern recognition concepts,methods and applications[M].New York:Spring,2001.
[22]刘俊卿.基于ROI的双尺度边缘结构相似度图像质量评价方法[D].昆明:昆明理工大学,2013.LIU J Q.Image quality assessment of dual-scale edge structure similarity based on region of interest[D].Kunming:Kunming University of Science and Technology,2013.
[23]苗启广,刘娟,宁淑婷.基于模糊综合评判的机场打击效果评估[J].系统工程与电子技术,2012,34(7):1395-1399.MIAO Q G,LIU J,NING S T.Battle damage assessment of airport based on fuzzy comprehensive evaluation[J].Systems Engineering and Electronics,2012,34(7):1395-1399.
[2]李仁杰,计科峰,邹焕新,等.基于电磁散射特性计算的目标SAR图像仿真[J].雷达科学与技术,2010,8(5):395-400.LI R J,JI K F,ZOU H X,et al.Simulation of SAR imagery of target based on electromagnetic scattering characteristic computation[J].Radar Science and Technology,2010,8(5):395-400.
[3]计科峰,张爱兵,邹焕新,等.典型地面车辆目标SAR图像仿真与评估[J].雷达科学与技术,2010,8(3):223-228.JI K F,ZHANG A B,ZOU H X,et al.Simulation and evaluation of SAR imagery of typical ground vehicles[J].Radar Science and Technology,2010,8(3):223-228.
[4]张锐,洪峻,明峰.基于电磁散射的复杂目标SAR回波与图像仿真[J].电子与信息学报,2010,32(12):2836-2841.ZHANG R,HONG J,MING F.SAR echo and image simulation of complex targets based on electromagnetic scattering[J].Journal of Electronics&Information Technology,2010,32(12):2836-2841.
[5]董纯柱,殷红成,王超.基于射线管分裂方法的SAR场景快速消隐技术[J].雷达学报,2012,1(4):436-440.DONG C Z,YIN H C,WANG C.A fast hidden surface removal approach for complex SAR scene based on adaptive ray-tube splitting method[J].Journal of Radars,2012,1(4):436-440.
[6]JIA L,JIA X,HUANG C G.SAR raw data generation and image simulation of aircrafts on the runway[C]∥Proc.of the 7th International Congress on Image and Signal Processing,2014:1115-1119.
[7]PENG L J,LIU M,LIU X H,et al.SAR image classification based on CNN in real and simulation datasets[C]∥Proc.of the9th SPIE International Conference on Graphic and Image Processing,2017.
[8]JI K F,ZHANG A B,ZOU H X,et al.Simulation of SAR images of ground vehicles[C]∥Proc.of the SPIE Automatic Target Recognition and Image Analysis,2009.
[9]WU F,WANG C,WEN X Y,et al.SAR image simulation for object’s feature analysis[C]∥Proc.of the 4th International Workshop on Earth Observation and Remote Sensing Applications,2016:4-6.
[10]HARALD A,TIMO K,MANFRED H,et al.Identification of maritime target objects from high resolution TerraSAR-X data using SAR simulation[C]∥Proc.of the SPIE Radar Sensor Technology XVIII,2014.
[11]JI K F,ZHAO Z,XING X W,et al.SAR imagery simulation of ship based on electromagnetic calculations and sea clutter modeling for classification applications[C]∥Proc.of the 35th International Symposium on Remote Sensing of Environment,IOP Conference Series:Earth and Environmental Science,2014.
[12]ZHANG M,ZHAO Y,NIE D.EM scattering and SAR image simulation from composite sea-ship scene based on a weighted multi-path model[C]∥Proc.of the SPIE Remote Sensing of the Ocean,Sea Ice,Coastal Waters,and Large Water Regions,2016.
[13]PHILIP L D.Measured and predicted synthetic aperture radar target comparison[J].IEEE Trans.on Aerospace and Electronic Systems,2002,38(1):25-37.
[14]胡利平,董纯柱,邢笑宇,等.SAR图像目标和阴影径向积分特征评估[J].电波科学学报,2014,29(2):254-259.HU L P,DONG C Z,XING X Y,et al.An evaluation method of SAR images based on radial integral features of target and shadow[J].Chinese Journal of Radio Science,2014,29(2):254-259.
[15]ORLANDI A,ANTONINI G,POLISINI C,et al.Progress in the development of a 2Dfeature selective validation method[C]∥Proc.of the IEEE International Symposium on Electromagnetic Compatibility,2008:1-6.
[16]毕长剑,董冬梅,张双建,等.作战模拟训练效能评估[M].北京:国防工业出版社,2014.BI C J,DONG D M,ZHANG S J,et al.Operational simulation training effectiveness evaluation[M].Beijing:National Defense Industry Press,2014.
[17]句彦伟,张燕.ISAR图像质量评估方法[J].系统工程与电子技术,2015,37(2):297-303.JU Y W,ZHANG Y.Research on ISAR image quality evaluation[J].Systems Engineering and Electronics,2015,37(2):297-303.
[18]LAO G C,YE W,LI G J,et al.A quality evaluation method of SAR image based on grayscale image and electromagnetic scattering characteristics[C]∥Proc.of the 8th SPIE International Conference on Digital Image Processing,2016.
[19]胡利平,刘宏伟,吴顺君.基于多分类器融合的SAR图像自动目标识别方法[J].系统工程与电子技术,2008,30(5):839-842.HU L P,LIU H W,WU S J.Radar target recognition based SAR image and classifiers fusion[J].Systems Engineering and Electronics,2008,30(5):839-842.
[20]CIRIC M,IGNJATOVIC J,BOGDANOVIC S.Uniform fuzzy relations and fuzzy functions[J].Fuzzy Sets and Systems,2009,160(8):1054-1081.
[21]MARQUES DE SA J P.Pattern recognition concepts,methods and applications[M].New York:Spring,2001.
[22]刘俊卿.基于ROI的双尺度边缘结构相似度图像质量评价方法[D].昆明:昆明理工大学,2013.LIU J Q.Image quality assessment of dual-scale edge structure similarity based on region of interest[D].Kunming:Kunming University of Science and Technology,2013.
[23]苗启广,刘娟,宁淑婷.基于模糊综合评判的机场打击效果评估[J].系统工程与电子技术,2012,34(7):1395-1399.MIAO Q G,LIU J,NING S T.Battle damage assessment of airport based on fuzzy comprehensive evaluation[J].Systems Engineering and Electronics,2012,34(7):1395-1399.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |