For radar high resolution range profile (HRRP) recognition, three aspects are of great importance to improve the performance, i.e. discrimination for outlier, classification for inner and an accurate description for f...For radar high resolution range profile (HRRP) recognition, three aspects are of great importance to improve the performance, i.e. discrimination for outlier, classification for inner and an accurate description for feature space. To tackle these issues, a novel target recognition method is designed, denoted by the multiple support vectors (multi-SV) method. With the proposed method, a special framework is constructed by a treble correlate support vector model to segment the feature space to two regions with the distribution of density, and then the description and classification hyperplane for each region are achieved. Based on the support vector framework, this method needs less memory and computation complexity to fit practical radar HRRP recognition. Finally, the experiment based on the measured data verifies the excellent performance of this method.展开更多
Orthogonal frequency division multiplexing(OFDM) radar with multicarrier phase-coded waveforms has been recently introduced to achieve high range resolution.The conventional method for obtaining the high resolution ...Orthogonal frequency division multiplexing(OFDM) radar with multicarrier phase-coded waveforms has been recently introduced to achieve high range resolution.The conventional method for obtaining the high resolution range profile(HRRP) is based on matched filters.A method of synthesizing HRRP based on the fast Fourier transform(FFT) and decoding is proposed.The mathematical expressions of HRRP are derived by assuming an elementary scenario of point-scattering targets.Based on the characteristic of OFDM multicarrier signals,it mainly analyzes the influence on HRRP exerted by several factors,such as velocity compensation errors,the sampling frequency offset,and so on.The conclusions are significant for the design of the OFDM imaging radar.Finally,the simulation results demonstrate the validity of the conclusions.展开更多
Two novel schemes are proposed to synthesize high resolution range profile (HRRP) based on co-located multiple-input multiple-output (MIMO) system in the context of the joint radar and communication system. The differ...Two novel schemes are proposed to synthesize high resolution range profile (HRRP) based on co-located multiple-input multiple-output (MIMO) system in the context of the joint radar and communication system. The difference between two schemes is the pattern of selecting pulses, which depends on the demand for the velocity information. The system, a type of frequency diverse array (FDA), takes full advantage of the phase-coded orthogonal frequency division multiplexing (OFDM) signal. Furthermore, the complete discrete form of the phase-coded OFDM echoes is utilized to derive the HRRP processing. The velocity estimation in the second scheme aims to eliminate velocity ambiguity, and high velocity can be retrieved exactly. Meanwhile, the imaging method is investigated with random frequency coding applied to an array. The desired performance of resolving velocity ambiguity and suppressing noise is shown by means of comparisons with previous work. The advantages in the radar imaging and the significance of the work are concluded in the end.展开更多
特征选择是雷达目标识别流程中一个较为关键的环节,通过对原始特征集进行筛选,挑选出其中的优质特征构成新的特征子集,可以有效增加识别准确率,提升识别效率。为了提升开放环境下高分辨距离像(High Range Resolution Profile,HRRP)的识...特征选择是雷达目标识别流程中一个较为关键的环节,通过对原始特征集进行筛选,挑选出其中的优质特征构成新的特征子集,可以有效增加识别准确率,提升识别效率。为了提升开放环境下高分辨距离像(High Range Resolution Profile,HRRP)的识别性能,针对现有特征选择方法基于闭集假设,无法有效应对实际应用中存在库外目标导致的开集识别(Open Set Recognition,OSR)性能下降问题,本文提出了一种基于局部离群因子(Local Outlier Factor,LOF)的HRRP开集识别特征选择方法。首先,从原始HRRP中提取15维特征向量作为原始特征集;其次,该方法引入聚合性概念,并使用LOF作为其度量,通过评估特征子集的聚合性来保证其在OSR时具有最小的开放空间风险。同时,采用重心法评估特征子集的可分性,并使用前向搜索算法优化特征选择过程,确保所选特征子集为维数约束下的最优解。实验结果表明:利用所提方法选择的特征子集在开集环境下识别性能优于现有特征提取方法,提升了开集环境下高分辨距离像的识别性能。展开更多
传统的雷达高分辨距离像(High Resolution Range Profile,HRRP)序列识别方法依赖于人工提取特征,并且在使用现有的经典深度学习方法识别小数据集时存在梯度消失和过拟合问题,导致收敛速度慢,识别率低。针对上述问题,提出了一种基于注意...传统的雷达高分辨距离像(High Resolution Range Profile,HRRP)序列识别方法依赖于人工提取特征,并且在使用现有的经典深度学习方法识别小数据集时存在梯度消失和过拟合问题,导致收敛速度慢,识别率低。针对上述问题,提出了一种基于注意力机制的集成Inception网络模型,通过集成Attention-Inception单分支网络,实现了HRRP序列更深层次特征的提取;通过对模型的损失函数加入L2正则化,缓解小数据集在集成网络中的过拟合问题;利用Inception Ⅰ和Inception Ⅱ结构提取HRRP序列多尺度特征,并引入注意力机制计算特征序列的分配权重;加入残差结构,减缓了集成网络梯度消失问题。在预处理后的HRRP序列上进行实验结果表明,所提方法的目标识别率达到93.3%,并且与未去除噪声的HRRP序列相比目标识别率提高了14.67%。展开更多
给出了一种结合幂变换的高分辨率距离像 (High Resolution Range Profile,简称 HRRP)的预处理新方法。根据时域 -频域能量等价性 ,利用功率平均形成一种频域平均模板。基于美国 MSTAR(Moving and Stationary TargetAcquisition and Reco...给出了一种结合幂变换的高分辨率距离像 (High Resolution Range Profile,简称 HRRP)的预处理新方法。根据时域 -频域能量等价性 ,利用功率平均形成一种频域平均模板。基于美国 MSTAR(Moving and Stationary TargetAcquisition and Recognition)展开更多
针对多极化高分辨率一维距离像(high range resolution profile,HRRP)在目标识别过程中存在计算量和数据量大、识别算法复杂的问题,提出一种基于Bagging-SVM动态集成的目标识别方法。该方法首先提取多极化HRRP平移不变特征向量,然后运用...针对多极化高分辨率一维距离像(high range resolution profile,HRRP)在目标识别过程中存在计算量和数据量大、识别算法复杂的问题,提出一种基于Bagging-SVM动态集成的目标识别方法。该方法首先提取多极化HRRP平移不变特征向量,然后运用Bagging方法结合基于动态互信息的特征选择方法生成基分类器,最后引入基分类器差异度进行选择性集成。实验验证该方法在缩减数据规模和计算量的同时,能有效利用多极化特征信息,得到较高的分类正确率,并且松弛了HRRP目标的姿态敏感性。展开更多
针对实数单极化高分辨率一维距离像(high resolution range profile,HRRP)缺失了目标的极化信息和相位信息的问题,研究了复数全极化HRRP目标特征提取方法,为合理有效运用所提取的目标信息,提出一种基于Bagging的选择性集成算法,并在此...针对实数单极化高分辨率一维距离像(high resolution range profile,HRRP)缺失了目标的极化信息和相位信息的问题,研究了复数全极化HRRP目标特征提取方法,为合理有效运用所提取的目标信息,提出一种基于Bagging的选择性集成算法,并在此基础上设计了复数全极化HRRP目标识别方法,最后通过实验验证该方法具有良好的稳健性和可分性。展开更多
文摘For radar high resolution range profile (HRRP) recognition, three aspects are of great importance to improve the performance, i.e. discrimination for outlier, classification for inner and an accurate description for feature space. To tackle these issues, a novel target recognition method is designed, denoted by the multiple support vectors (multi-SV) method. With the proposed method, a special framework is constructed by a treble correlate support vector model to segment the feature space to two regions with the distribution of density, and then the description and classification hyperplane for each region are achieved. Based on the support vector framework, this method needs less memory and computation complexity to fit practical radar HRRP recognition. Finally, the experiment based on the measured data verifies the excellent performance of this method.
基金supported by the National Natural Science Foundation of China (6087213461072117)
文摘Orthogonal frequency division multiplexing(OFDM) radar with multicarrier phase-coded waveforms has been recently introduced to achieve high range resolution.The conventional method for obtaining the high resolution range profile(HRRP) is based on matched filters.A method of synthesizing HRRP based on the fast Fourier transform(FFT) and decoding is proposed.The mathematical expressions of HRRP are derived by assuming an elementary scenario of point-scattering targets.Based on the characteristic of OFDM multicarrier signals,it mainly analyzes the influence on HRRP exerted by several factors,such as velocity compensation errors,the sampling frequency offset,and so on.The conclusions are significant for the design of the OFDM imaging radar.Finally,the simulation results demonstrate the validity of the conclusions.
基金supported by the National Natural Science Foundation of China(6107116361071164+8 种基金6147119161501233)the Fundamental Research Funds for the Central Universities(NP2014504)the Aeronautical Science Foundation(20152052026)the Electronic&Information School of Yangtze University Innovation Foundation(2016-DXCX-05)the Funding for Outstanding Doctoral Dissertation in NUAA(BCXJ15-03)the Funding of Jiangsu Innovation Program for Graduate Education(KYLX15 0281)the Fundamental Research Funds for the Central Universitiespartly funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PADA)
文摘Two novel schemes are proposed to synthesize high resolution range profile (HRRP) based on co-located multiple-input multiple-output (MIMO) system in the context of the joint radar and communication system. The difference between two schemes is the pattern of selecting pulses, which depends on the demand for the velocity information. The system, a type of frequency diverse array (FDA), takes full advantage of the phase-coded orthogonal frequency division multiplexing (OFDM) signal. Furthermore, the complete discrete form of the phase-coded OFDM echoes is utilized to derive the HRRP processing. The velocity estimation in the second scheme aims to eliminate velocity ambiguity, and high velocity can be retrieved exactly. Meanwhile, the imaging method is investigated with random frequency coding applied to an array. The desired performance of resolving velocity ambiguity and suppressing noise is shown by means of comparisons with previous work. The advantages in the radar imaging and the significance of the work are concluded in the end.
文摘特征选择是雷达目标识别流程中一个较为关键的环节,通过对原始特征集进行筛选,挑选出其中的优质特征构成新的特征子集,可以有效增加识别准确率,提升识别效率。为了提升开放环境下高分辨距离像(High Range Resolution Profile,HRRP)的识别性能,针对现有特征选择方法基于闭集假设,无法有效应对实际应用中存在库外目标导致的开集识别(Open Set Recognition,OSR)性能下降问题,本文提出了一种基于局部离群因子(Local Outlier Factor,LOF)的HRRP开集识别特征选择方法。首先,从原始HRRP中提取15维特征向量作为原始特征集;其次,该方法引入聚合性概念,并使用LOF作为其度量,通过评估特征子集的聚合性来保证其在OSR时具有最小的开放空间风险。同时,采用重心法评估特征子集的可分性,并使用前向搜索算法优化特征选择过程,确保所选特征子集为维数约束下的最优解。实验结果表明:利用所提方法选择的特征子集在开集环境下识别性能优于现有特征提取方法,提升了开集环境下高分辨距离像的识别性能。
文摘给出了一种结合幂变换的高分辨率距离像 (High Resolution Range Profile,简称 HRRP)的预处理新方法。根据时域 -频域能量等价性 ,利用功率平均形成一种频域平均模板。基于美国 MSTAR(Moving and Stationary TargetAcquisition and Recognition)
文摘针对多极化高分辨率一维距离像(high range resolution profile,HRRP)在目标识别过程中存在计算量和数据量大、识别算法复杂的问题,提出一种基于Bagging-SVM动态集成的目标识别方法。该方法首先提取多极化HRRP平移不变特征向量,然后运用Bagging方法结合基于动态互信息的特征选择方法生成基分类器,最后引入基分类器差异度进行选择性集成。实验验证该方法在缩减数据规模和计算量的同时,能有效利用多极化特征信息,得到较高的分类正确率,并且松弛了HRRP目标的姿态敏感性。
文摘针对实数单极化高分辨率一维距离像(high resolution range profile,HRRP)缺失了目标的极化信息和相位信息的问题,研究了复数全极化HRRP目标特征提取方法,为合理有效运用所提取的目标信息,提出一种基于Bagging的选择性集成算法,并在此基础上设计了复数全极化HRRP目标识别方法,最后通过实验验证该方法具有良好的稳健性和可分性。