基于希尔伯特黄变换的雷达HRRP目标识别
|
摘要
提出了一种基于希尔伯特黄变换(HHT)的雷达高分辨距离像(HRRP)目标识别方法。首先,为了解决HRRP强度敏感性和平移敏感性问题,对原始HRRP采取预处理操作,从而得到经相关对齐后的归一化HRRP;然后对经相关对齐后的归一化HRRP进行HHT,得到Hilbert谱特征;最后采用字典学习模型对不同目标的Hilbert谱特征实现目标识别决策。通过处理雷达实测数据对所提算法进行验证,结果显示对3类飞机目标平均识别精度达到了93.55%,体现了该算法对雷达HRRP目标的良好识别性能。
In the field of radar high resolution range profile(HRRP)target recognition,an effective method based on Hilbert Huang transform(HHT)is proposed.Firstly,in order to deal with the time-shift and amplitude-scale sensitivity of HRRP,apreprocessing operation is performed on the original HRRP to obtain a normalized HRRP after the correlation alignment.Then the Hilbert spectral features are obtained by the HHT of the normalized HRRP after the correlation alignment.Finally,the dictionary learning model is used to realize the target recognition of Hilbert spectral features of different targets.The proposed algorithm is verified by processing the measured data of the radar.The results show that the average recognition accuracy of the three types of aircraft targets reaches 93.55%,which shows the good recognition performance of the proposed algorithm for radar HRRP targets.
In the field of radar high resolution range profile(HRRP)target recognition,an effective method based on Hilbert Huang transform(HHT)is proposed.Firstly,in order to deal with the time-shift and amplitude-scale sensitivity of HRRP,apreprocessing operation is performed on the original HRRP to obtain a normalized HRRP after the correlation alignment.Then the Hilbert spectral features are obtained by the HHT of the normalized HRRP after the correlation alignment.Finally,the dictionary learning model is used to realize the target recognition of Hilbert spectral features of different targets.The proposed algorithm is verified by processing the measured data of the radar.The results show that the average recognition accuracy of the three types of aircraft targets reaches 93.55%,which shows the good recognition performance of the proposed algorithm for radar HRRP targets.
引文
[1]BAI X,ZHOU F,BAO Z,et al.High-resolution radar imaging of space targets based on HRRP series[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(5):2369-2381.
[2]DU L,LIU H W,WANG P H,et al.Noise robust radar HRRP targets recognition based on multitask factor analysis with small training data size[J].IEEE Transactions on Signal Processing,2012,60(7):3546-3559.
[3]冯博,陈渤,王鹏辉,等.利用稳健字典学习的雷达高分辨距离像目标识别算法[J].电子与信息学报,2015,37(6):1457-1462.
[4]但波,姜永华,李敬军,等.雷达高分辨距离像自适应角域划分方法[J].系统工程与电子技术,2014,36(11):2178-2185.
[5]SHI L,WANG P,LIU H,et al.Radar HRRP statistical recognition with Local Factor Analysis by automatic Bayesian Ying Yang harmony learning[C].IEEE International Conference on Acoustics Speech and Signal Processing,IEEE,2010:1878-1881.
[6]郭尊华,李达,张伯彦.雷达高距离分辨率一维像目标识别[J].系统工程与电子技术,2013,35(1):53-60.
[7]GUO Y,XIAO H,FU Q.Least square support vector data description for HRRP-based radar target recognition[J].Applied Intelligence,2016,46(2):1-8.
[8]PAN M,JIANG J,LI Z,et al.Radar HRRP recognition based on discriminant deep autoencoders with small training data size[J].Electronics Letters,2016,52(20):1725-1727.
[9]郑纯丹,周代英.稀疏分解在雷达一维距离像中的应用.雷达科学与技术期刊[J],2013,11(1):55-58.
[10]张新征,刘书君,秦建红,等.基于距离像时频非负稀疏编码的SAR目标识别[J].系统工程与电子技术,2014,36(10):1934-1941.
[11]杨孟交,刘文波.巴克豪森信号希尔伯特黄变换分析及特征提取[J].电子测量技术,2017,40(8):180-183,188.
[12]田贵云,高斌,高运来,等.铁路钢轨缺陷伤损巡检与监测技术综述[J].仪器仪表学报,2016,37(8):1763-1780.
[13]王锋,李天刚,刘美全.被动探测中相关Hilbert时延估计方法研究[J].电子测量技术,2014,37(8):34-37.
[14]齐会娇,王英华,丁军,等.基于多信息字典学习及稀疏表示的SAR目标识别[J].系统工程与电子技术,2015,37(6):1280-1287.
[15]苗晟,王威廉,姚绍文.Hilbert-Huang变换发展历程及其应用[J].电子测量与仪器学报,2014,28(8):812-818.
[16]袁家雯,刘文波,张弓.基于统计建模的字典学习算法在HRRP的应用[J].系统工程与电子技术,2018,40(1):1-8.
[17]FENG B,DU L,SHAO C,et al.Radar HRRP target recognition based on robust dictionary learning with small training data size[C].Radar Conference(RADAR),IEEE,2013:1-4.
[18]刘冰,付平,孟升卫.基于正交匹配追踪的压缩感知信号检测算法[J].仪器仪表学报,2010,31(9):1959-1964.
[2]DU L,LIU H W,WANG P H,et al.Noise robust radar HRRP targets recognition based on multitask factor analysis with small training data size[J].IEEE Transactions on Signal Processing,2012,60(7):3546-3559.
[3]冯博,陈渤,王鹏辉,等.利用稳健字典学习的雷达高分辨距离像目标识别算法[J].电子与信息学报,2015,37(6):1457-1462.
[4]但波,姜永华,李敬军,等.雷达高分辨距离像自适应角域划分方法[J].系统工程与电子技术,2014,36(11):2178-2185.
[5]SHI L,WANG P,LIU H,et al.Radar HRRP statistical recognition with Local Factor Analysis by automatic Bayesian Ying Yang harmony learning[C].IEEE International Conference on Acoustics Speech and Signal Processing,IEEE,2010:1878-1881.
[6]郭尊华,李达,张伯彦.雷达高距离分辨率一维像目标识别[J].系统工程与电子技术,2013,35(1):53-60.
[7]GUO Y,XIAO H,FU Q.Least square support vector data description for HRRP-based radar target recognition[J].Applied Intelligence,2016,46(2):1-8.
[8]PAN M,JIANG J,LI Z,et al.Radar HRRP recognition based on discriminant deep autoencoders with small training data size[J].Electronics Letters,2016,52(20):1725-1727.
[9]郑纯丹,周代英.稀疏分解在雷达一维距离像中的应用.雷达科学与技术期刊[J],2013,11(1):55-58.
[10]张新征,刘书君,秦建红,等.基于距离像时频非负稀疏编码的SAR目标识别[J].系统工程与电子技术,2014,36(10):1934-1941.
[11]杨孟交,刘文波.巴克豪森信号希尔伯特黄变换分析及特征提取[J].电子测量技术,2017,40(8):180-183,188.
[12]田贵云,高斌,高运来,等.铁路钢轨缺陷伤损巡检与监测技术综述[J].仪器仪表学报,2016,37(8):1763-1780.
[13]王锋,李天刚,刘美全.被动探测中相关Hilbert时延估计方法研究[J].电子测量技术,2014,37(8):34-37.
[14]齐会娇,王英华,丁军,等.基于多信息字典学习及稀疏表示的SAR目标识别[J].系统工程与电子技术,2015,37(6):1280-1287.
[15]苗晟,王威廉,姚绍文.Hilbert-Huang变换发展历程及其应用[J].电子测量与仪器学报,2014,28(8):812-818.
[16]袁家雯,刘文波,张弓.基于统计建模的字典学习算法在HRRP的应用[J].系统工程与电子技术,2018,40(1):1-8.
[17]FENG B,DU L,SHAO C,et al.Radar HRRP target recognition based on robust dictionary learning with small training data size[C].Radar Conference(RADAR),IEEE,2013:1-4.
[18]刘冰,付平,孟升卫.基于正交匹配追踪的压缩感知信号检测算法[J].仪器仪表学报,2010,31(9):1959-1964.