雷达与ESM综合多目标检测、跟踪与识别
|
摘要
为在预警监视系统中对多目标的检测、跟踪、识别过程进行统一处理,提出一种基于跳转马尔可夫系统模型高斯混合概率假设密度滤波(jump Markov system model Gaussian mixture probability hypothesis density filtering,JMS-GMPHDF)算法的雷达、电子支援措施(electronic support measures,ESM)综合多目标检测、跟踪与识别方法。该方法首先根据不同类别目标设计各自的多目标多模型高斯混合概率假设密度滤波器,并在各滤波器处理过程中同时对高斯项进行编号;然后,根据目标速度与加速度模型信息进行高斯项综合与类别判决,同时根据ESM测量信息进行型号判决;最后,通过航迹综合管理,形成具有运动状态信息以及类别、型号、航迹编号信息的确定航迹。仿真实验验证了该方法能够有效综合雷达、ESM测量数据,在进行多目标检测、跟踪的同时进行正确的类别、型号判决,并形成确定航迹。
For recognizing the multi-target simultaneously with those targets detected and tracked in modern early warning and surveillance system,based on the jump Markov system model Gaussian mixture probability hypothesis density filtering(JMS-GMPHDF),a method is proposed for multi-target detection,tracking and recognition by fusion of radar and electronic support measures(ESM)sensors.First,the independent multi-target multi-model Gaussian mixture probability hypothesis density filter for each class of targets is designed,and Gaussian terms labels in each filtering process are given.Then,the Gaussian terms are merged and the class is estimated by targets velocity and acceleration model,and the type is estimated by ESM measurement.Finally,by managing tracks,determinate tracks with kinematic states,class,type,and track number are formed.Simulation results suggest that the proposed method can recognize the targets effectively and formulate correct tracks during the detecting and tracking process.
For recognizing the multi-target simultaneously with those targets detected and tracked in modern early warning and surveillance system,based on the jump Markov system model Gaussian mixture probability hypothesis density filtering(JMS-GMPHDF),a method is proposed for multi-target detection,tracking and recognition by fusion of radar and electronic support measures(ESM)sensors.First,the independent multi-target multi-model Gaussian mixture probability hypothesis density filter for each class of targets is designed,and Gaussian terms labels in each filtering process are given.Then,the Gaussian terms are merged and the class is estimated by targets velocity and acceleration model,and the type is estimated by ESM measurement.Finally,by managing tracks,determinate tracks with kinematic states,class,type,and track number are formed.Simulation results suggest that the proposed method can recognize the targets effectively and formulate correct tracks during the detecting and tracking process.
引文
[1]Challa S,Pulford G W.Joint target tracking and classification using radar and ESM sensors[J].IEEE Trans.on Aerospace and Electronic Systems,2001,37(3):1039-1055.
[2]Caromicoli A,Kurien T.Multitarget identification in airborne surveillance[C]∥Proc.of the SPIE Aerospace Pattern Recognition,1989:161-176.
[3]Mahler R.A theoretical foundation for the Stein-Winter probability hypothesis density(PHD)multitarget tracking approach[C]∥Proc.of the MSS National Symposium on Sensor and Data Fusion,2000:99-117.
[4]Mahler R.Statistical multisource-multitarget information fusion[M].Fan H Q Trans.Beijing:National Defence Industry Press,2013.(Mahler R.多源多目标统计信息融合[M].范红旗译.北京:国防工业出版社,2013.)
[5]Yang F,Wang Y Q,Liang Y,et al.A survey of PHD filter based multi-target tracking[J].Acta Automatica Sinica,2013,39(11):1944-1956.(杨峰,王永齐,梁彦,等.基于概率假设密度滤波方法的多目标跟踪技术综述[J].自动化学报,2013,39(11):1944-1956.)
[6]Wu X H,Huang G M,Gao J.Multi-target probability hypothesis density filtering with unknown probability of detection[J].Control and Decision,2014,29(1):57-63.(吴鑫辉,黄高明,高俊.未知探测概率下多目标PHD跟踪算法[J].控制与决策,2014,29(1):57-63.)
[7]Nannuru S,Coates M,Rabbat M.Multi-sensor PHD and CPHD flters[R].Montreal:Computer Networks Research Lab of McGill University,2014.
[8]Vo B N,Ma W K.The Gaussian mixture probability hypothesis density filter[J].IEEE Trans.on Signal Processing,2006,54(11):4091-4104.
[9]Beard M,Vo B T,Vo B N,et al.A partially uniform target birth model for Gaussian mixture PHD/CPHD filtering[J].IEEE Trans.on Aerospace and Electronic Systems,2013,49(4):1-16.
[10]Pasha S A,Vo B N,Tuan H D,et al.A Gaussian mixture PHD filter for jump Markov system models[J].IEEE Trans.on Aerospace and Electronic Systems,2009,45(3):919-936.
[11]Jiang X X,Yang X G,Li S,et al.Bearings-only tracking of multiple maneuvering targets using GMPHD algorithm based on IMM in acoustic sensors array networks[J].Journal of Computational Information Systems,2013,9(12):4877-4884.
[12]Zajic T,Ravichandra B,Mahler R,et al.Joint tracking and identification with robustness against unmodeled targets[C]∥Proc.of the SPIE Signal Processing,Sensor Fusion,and Target Recognition XII,2003:279-290.
[13]Yang W,Fu Y W,Li X,et al.Joint detection,tracking and classification algorithm for multiple maneuvering targets based on LGJMS-GMPHDF[J].Journal of Electronics&Information Technology,2012,34(2):398-403.(杨威,付耀文,黎湘,等.基于LGJMS-GMPHDF的多机动目标联合检测、跟踪与分类算法[J].电子与信息学报,2012,34(2):398-403.)
[14]Yang W,Fu Y W,Li X,et al.Joint detection,tracking and classification algorithm of multiple maneuvering targets using MMPHDF[J].Science China Information Sciences,2012,42(7):893-906.(杨威,付耀文,黎湘,等.基于MMPHDF的多机动目标联合检测、跟踪与分类算法[J].中国科学:信息科学,2012,42(7):893-906.)
[15]Angelova D,Mihaylova L.Joint target tracking and classification with particle filtering and mixture Kalman filtering using kinematic radar information[J].Elsevier Digital Signal Processing,2006,16(2):180-204.
[16]Panta K.Multi-target tracking using 1st moment of random finite[D].Australia:The University of Melbourne,2007.
[17]Panta K,Vo B N,Clark D.An efficient track management systems for the Gaussian mixture probability hypothesis density(GM-PHD)tracker[C]∥Proc.of the 4th International Conference of the IEEE Intelligent Sensing and Information Processing,2006:230-235.
[2]Caromicoli A,Kurien T.Multitarget identification in airborne surveillance[C]∥Proc.of the SPIE Aerospace Pattern Recognition,1989:161-176.
[3]Mahler R.A theoretical foundation for the Stein-Winter probability hypothesis density(PHD)multitarget tracking approach[C]∥Proc.of the MSS National Symposium on Sensor and Data Fusion,2000:99-117.
[4]Mahler R.Statistical multisource-multitarget information fusion[M].Fan H Q Trans.Beijing:National Defence Industry Press,2013.(Mahler R.多源多目标统计信息融合[M].范红旗译.北京:国防工业出版社,2013.)
[5]Yang F,Wang Y Q,Liang Y,et al.A survey of PHD filter based multi-target tracking[J].Acta Automatica Sinica,2013,39(11):1944-1956.(杨峰,王永齐,梁彦,等.基于概率假设密度滤波方法的多目标跟踪技术综述[J].自动化学报,2013,39(11):1944-1956.)
[6]Wu X H,Huang G M,Gao J.Multi-target probability hypothesis density filtering with unknown probability of detection[J].Control and Decision,2014,29(1):57-63.(吴鑫辉,黄高明,高俊.未知探测概率下多目标PHD跟踪算法[J].控制与决策,2014,29(1):57-63.)
[7]Nannuru S,Coates M,Rabbat M.Multi-sensor PHD and CPHD flters[R].Montreal:Computer Networks Research Lab of McGill University,2014.
[8]Vo B N,Ma W K.The Gaussian mixture probability hypothesis density filter[J].IEEE Trans.on Signal Processing,2006,54(11):4091-4104.
[9]Beard M,Vo B T,Vo B N,et al.A partially uniform target birth model for Gaussian mixture PHD/CPHD filtering[J].IEEE Trans.on Aerospace and Electronic Systems,2013,49(4):1-16.
[10]Pasha S A,Vo B N,Tuan H D,et al.A Gaussian mixture PHD filter for jump Markov system models[J].IEEE Trans.on Aerospace and Electronic Systems,2009,45(3):919-936.
[11]Jiang X X,Yang X G,Li S,et al.Bearings-only tracking of multiple maneuvering targets using GMPHD algorithm based on IMM in acoustic sensors array networks[J].Journal of Computational Information Systems,2013,9(12):4877-4884.
[12]Zajic T,Ravichandra B,Mahler R,et al.Joint tracking and identification with robustness against unmodeled targets[C]∥Proc.of the SPIE Signal Processing,Sensor Fusion,and Target Recognition XII,2003:279-290.
[13]Yang W,Fu Y W,Li X,et al.Joint detection,tracking and classification algorithm for multiple maneuvering targets based on LGJMS-GMPHDF[J].Journal of Electronics&Information Technology,2012,34(2):398-403.(杨威,付耀文,黎湘,等.基于LGJMS-GMPHDF的多机动目标联合检测、跟踪与分类算法[J].电子与信息学报,2012,34(2):398-403.)
[14]Yang W,Fu Y W,Li X,et al.Joint detection,tracking and classification algorithm of multiple maneuvering targets using MMPHDF[J].Science China Information Sciences,2012,42(7):893-906.(杨威,付耀文,黎湘,等.基于MMPHDF的多机动目标联合检测、跟踪与分类算法[J].中国科学:信息科学,2012,42(7):893-906.)
[15]Angelova D,Mihaylova L.Joint target tracking and classification with particle filtering and mixture Kalman filtering using kinematic radar information[J].Elsevier Digital Signal Processing,2006,16(2):180-204.
[16]Panta K.Multi-target tracking using 1st moment of random finite[D].Australia:The University of Melbourne,2007.
[17]Panta K,Vo B N,Clark D.An efficient track management systems for the Gaussian mixture probability hypothesis density(GM-PHD)tracker[C]∥Proc.of the 4th International Conference of the IEEE Intelligent Sensing and Information Processing,2006:230-235.