多目标跟踪理论与方法
|
摘要
论文主要研究多目标跟踪问题。数据融合是一种新兴的信息处理技术，它是适用于一个系统中使用多传感器这一特定问题而展开的一种信息处理的研究新方向，并在近几十年中得到了很大的发展，已经应用于诸多军事和民用领域。
由于数据融合是许多传统学科和新兴工程领域相结合而产生的一个新的前沿技术领域，论文首先阐述数据融合这一门新兴的信息处理学科的意义、理论基础、实现技术和研究现状，提供了有关数据融合研究领域的一个概观。论文的重点是在数据融合中的多目标跟踪领域。
在多目标跟踪领域，国内外的学者已经提出了很多在杂波环境下对多目标跟踪的算法，论文在收集大量国内外资料的前提下，指出每种算法的优缺点，综合各种算法，总结出了一种适合工程应用的模型，其中包括了机动目标采用“当前”统计模型。论文针对多杂波环境下的高度机动目标，依据多传感器数据融合的理论基础，基于目标跟踪领域中的概率数据关联算法，对于三个机动目标在杂波环境下的轨迹进行跟踪，并在Matlab环境中，完成了多目标融合跟踪各个阶段的算法仿真，取得了满意的仿真结果，从而证明了整个系统的数据融合目标跟踪算法的有效性。
论文对多传感器条件下的多目标跟踪理论进行了阐述，并在了解了众多国家在此领域的发展近况后，预测了今后多目标跟踪的发展方向。
In this thesis, the problem of target tracking has been studied. Data fusion is a burgeoning field of information processing technology, which was carried out in conditions concerning a system equipped with several sensors. In recent years, data fusion has been developed greatly and been used in many military and civilian fields.
Data fusion is a new foreland technology field, which was generated by combining many traditional subjects and burgeoning subjects, so this thesis expatiate on the meaning, theory foundation, actual technology and research status of data fusion, which was a newly burgeoning subject deal with information. This thesis also applies a survey in the data fusion research field and the focus of this thesis is mult-target tracking field of the data fusion.
In the field of multi-target tracking, scholars in China and other countries have presented many algorithms that treat with multi-target tracking in clutter. On the basis of collecting a lot of data in many countries, this thesis pointed out the virtues and shortcomings of every algorithm and concluded a model that suitable for the application in engineering. That model includes a 'currently' statistical model for the maneuvering targets.
To resolve the question of tracking highly maneuvering targets in clutter with different sensors, the theory of multi-sensor data fusion and algorithm of joint probabilistic data association have been analyzed in depth. In this thesis, with the using of MATLAB simulating tool, it accomplished the tracking of three maneuvering targets in clutter and completed the algorithm emulation of
every phase in multi-target tracking. From the satisfied result of simulation, the validity of target tracking algorithm in whole data fusion system has been proved.
The multi-target tracking theory on the condition of multi-sensor was discussed in this thesis and the future develop direction of multi-target tracking was forecasted on the basis of knowing much recent situation of many countries in this field.
由于数据融合是许多传统学科和新兴工程领域相结合而产生的一个新的前沿技术领域，论文首先阐述数据融合这一门新兴的信息处理学科的意义、理论基础、实现技术和研究现状，提供了有关数据融合研究领域的一个概观。论文的重点是在数据融合中的多目标跟踪领域。
在多目标跟踪领域，国内外的学者已经提出了很多在杂波环境下对多目标跟踪的算法，论文在收集大量国内外资料的前提下，指出每种算法的优缺点，综合各种算法，总结出了一种适合工程应用的模型，其中包括了机动目标采用“当前”统计模型。论文针对多杂波环境下的高度机动目标，依据多传感器数据融合的理论基础，基于目标跟踪领域中的概率数据关联算法，对于三个机动目标在杂波环境下的轨迹进行跟踪，并在Matlab环境中，完成了多目标融合跟踪各个阶段的算法仿真，取得了满意的仿真结果，从而证明了整个系统的数据融合目标跟踪算法的有效性。
论文对多传感器条件下的多目标跟踪理论进行了阐述，并在了解了众多国家在此领域的发展近况后，预测了今后多目标跟踪的发展方向。
In this thesis, the problem of target tracking has been studied. Data fusion is a burgeoning field of information processing technology, which was carried out in conditions concerning a system equipped with several sensors. In recent years, data fusion has been developed greatly and been used in many military and civilian fields.
Data fusion is a new foreland technology field, which was generated by combining many traditional subjects and burgeoning subjects, so this thesis expatiate on the meaning, theory foundation, actual technology and research status of data fusion, which was a newly burgeoning subject deal with information. This thesis also applies a survey in the data fusion research field and the focus of this thesis is mult-target tracking field of the data fusion.
In the field of multi-target tracking, scholars in China and other countries have presented many algorithms that treat with multi-target tracking in clutter. On the basis of collecting a lot of data in many countries, this thesis pointed out the virtues and shortcomings of every algorithm and concluded a model that suitable for the application in engineering. That model includes a 'currently' statistical model for the maneuvering targets.
To resolve the question of tracking highly maneuvering targets in clutter with different sensors, the theory of multi-sensor data fusion and algorithm of joint probabilistic data association have been analyzed in depth. In this thesis, with the using of MATLAB simulating tool, it accomplished the tracking of three maneuvering targets in clutter and completed the algorithm emulation of
every phase in multi-target tracking. From the satisfied result of simulation, the validity of target tracking algorithm in whole data fusion system has been proved.
The multi-target tracking theory on the condition of multi-sensor was discussed in this thesis and the future develop direction of multi-target tracking was forecasted on the basis of knowing much recent situation of many countries in this field.
引文
[1] Y.Bar-Shalom. "Multisensor Tracking of a Maneuvering Target in Clutter". IEEE Transactions on aerospace and Electronic systems VOL AES-25 NO.2 March 1989
[2] Waltz E, L linas J. 《Multisensor data fusion》. Artech House, MA, 1990
[3] Y.Bar-Shalom. "Extension of the probabilistic data association filter to multitarget environment"[c]. Proc Fifth Symptom Nonlinear Estimation, San Diego, CA, 1974.
[4] S.S Blackman. "Multiple target tracking with radar applications" [M]. Artech House, 1986.
[5] Leonard Chin. "Application of neural networks in target tracking data fusion" [J]. IEEE Transactions on Aerospace and Electronic System, 1994,30(1).
[6] Y.Bar-Shalom, Thomas Efortmann. "Tracking and Data Association." Orlando; Academic Press Inc, 1988.
[7] Abpoore,Nruavec,Tnbarker and Mmunger. "Data association problems posed multidimensional assignment problems: algorithm development" [J] SPIE, 1993,1995
[8] Y.Bar-Shalom,Thomas, Fortmann. "Multi-target Tracking Using Joint Probabilistic Data Association" [M]. Newyork :Academic Press, 1988
[9] Y.Bar-Shalom (1981) "On the track-to-track correlation problem."
IEEE Transaction on Automatic Control. AC-26 (Apr.1981) 571-572
[10] Y.Bar-Shalom and Campo.L.(1986) "The effect of the common process noise on the two-sensor fused-track covariance." IEEE Trancesaction on Aerospace and Electronic Systems. AES-22 (Nov. 1986), 803-805
[11] willner.D,Chang ,C.B. and Dunn.K.P.(1976) "Kalman filter algorithms for a multi-sensor system." In Proceedings of the IEEE Conference on Decision and Control. Dec. 1976 p570-574
[12] Willsky.A.S,Bello,M.G.,Castanon,D.A.,Levy.,B.C,and Verghese.G.C(1982) "Combining and updating of local estimates and regional maps along sets of One- dimensional tracks." IEEE Transactions on Automatic Control, AC-27 (Aug. 1982) 799-813
[13] Yaakov Bar-shalom. "Multitarget-Multisensor Tracking: Advanced Applications."Artech House. 1990.
[14] Yaakov Bar-shalom. "Multitarget-Multisensor Tracking: Applications and Advances" Artech House. 1990.
[15] Henk A.P.Blom and Yaakov Bar-shalom. "The Interractive Multiple Model Algorithm for Systems with Markovian Switching Coeffients." IEEE.Trans.on AC. 1998, Vol. 33, No. 8.
[16] J.A.Roecker and C.D.Mcgillem. "Comparison of Two-Sensor Tracking Methods Based on State Vector Fusion and Measurement Fusion." IEEE.Trans. on AES. 1998,Vol.24,No.4.
[17] Y.bar-shalom,K.C.Chang,H.A.P.Blom. "Tracking a Maneuvering Target Using Input Estimation Versus the
Interacting Multiple Model Algorithm." IEEE.Trans.on AES. 1989,Vol.25, No.2.
[18] R.K.SAHA. "Track-to-Track fusion with Dissimilar Sensors." IEEE.Trans.on AES. 1996,Vol.32, No.2.
[19] Guu,J,A,and Wei,C.H(1991) "Tracking technique for maneuvering target with correlated measurement noise and unknown parameters" IEEE Proceeding, Pt.F, 138,3(June 1991), 278-288.
[20] Blom,H.A.P, and Bar-Shalom.Y (1988) "The interacting multiple model algorithm for systems with Makovian switching coefficients" IEEE Transactions on Automatic Control, 33 (Aug.1988), 780-783
[21] Guu, J.A,and Wei, C.H.(1991) "Maneuvering target tracking using IMM method at high measurement frequency." IEEE Transactions on Aerospace and Electronic Systems,27,3(1991),514-519
[22] Gholson,N.H.,and Moose ,R..L. (1997) "Maneuvering target tracking using adaptive state estimation." IEEE Transactions on Aerospace and Electronic Systems, AES- 15 (May 1977),448-456.
[23] Chang,C.B.,and Younes,L.C.(1982) "Mesurement correlation for multiple sensor tracking in dense target environment." IEEE Transactions on Automatic Control, (Dec. 1982), 1250-1252.
[24] Yosko, J (1992) Optimal and sub-optimal fusion of Alpha-Beta target tracks. Masters thesis, Drexel University, Philadelphia, PA, 1992.
[25] Y.Bar-shalom, "Tracking methods in a multitarget environment." IEEE Trans. Automat. Contr., Vol.AC-20, pp.618-626, Aug. 1978
[26] Sengupta,D.,and Hhis,R.A.(1989) Neural solution to the multitarget tracking data association problem. IEEE Transactions on Aerospace and Electronic Systems, 25,1 (Jan, 1989), 96-108
[27] 康耀红。《数据融合理论与应用》．西安电子科技大学出版社，1997
[28] 许升汉，概率论与随机过程，人民邮电出版社，1995年
[29] 王祁 聂伟 张兆礼。“数据融合与智能传感系统传感器技术(Journal Transducer Technology)1998年第17卷第6期
[30] 唐义平，李卫。“多传感器系统的数据融合技术 南京理工大学电光学院 上海航天 1997年第4期 p39
[31] 楼顺天，于卫，闫华梁。MATLAB程序设计语言 西安电子科技大学出版社 1998年
[32] 龙翔“多目标跟踪软件设计” 西北工业大学硕士论文
[33] 施阳，李俊。MATLAB语言工具箱-一Toolbox实用指南。
[34] 李人厚，张平安 等译校。精通MATLAB综合辅导与指南 西安交通大学出版社 1998年
[35] 薛定宇。控制系统计算机辅助设计-MATLAB语言及应用 清华大学出版社 1996年
[36] 孟希哲，线性控制系统，水利电力出版社，1995年
[37] 王永初，任秀珍，现代控制工程的数学基础，化学工业出版社，1985年
[38] 张贤达，现代信号处理，清华大学出版社，1995年
[39] 章潜五，随机信号分析，西北电信工程学院出版社，1986年
[40] 许树声，信号检测与估计，国防工业出版社，1985年
[41] 周锐，申功勋，房建成，祝世平。“多传感器融合目标跟踪”《航空学报》第19卷 第5期，1998年9月
[42] 吴小俊，曹奇英，陈保香，刘同明。“基于Bayes估计的多传感器数据融合方法研究” 2000年7月系统工程理论与实践第7期
[43] 李建勋 敬忠良 杨永胜 戴冠中 金德琨。“主被动多传感器多目标
状态信息融合”《航空学报》第18卷第2期 1997年3月(ACTA AERONAUTICA ET ASTRONAUTICA SINICA Vol.1 8No.2 Mar.1997)
[44] 于源．“基于数据融合理论的多传感器目标跟踪”西北工业大学硕士论文
[45] 宋小全，孙仲康。“多传感器机动目标跟踪”《电子学报》，1997，Vol．25,No．9．
[46] 孙红岩，毛士艺，林品兴。“多传感器数据分层融合性质。”《电子学报》，1996，Vol．24,No．6
[47] 《多传感器数据融合》(赵宗贵等译)
[2] Waltz E, L linas J. 《Multisensor data fusion》. Artech House, MA, 1990
[3] Y.Bar-Shalom. "Extension of the probabilistic data association filter to multitarget environment"[c]. Proc Fifth Symptom Nonlinear Estimation, San Diego, CA, 1974.
[4] S.S Blackman. "Multiple target tracking with radar applications" [M]. Artech House, 1986.
[5] Leonard Chin. "Application of neural networks in target tracking data fusion" [J]. IEEE Transactions on Aerospace and Electronic System, 1994,30(1).
[6] Y.Bar-Shalom, Thomas Efortmann. "Tracking and Data Association." Orlando; Academic Press Inc, 1988.
[7] Abpoore,Nruavec,Tnbarker and Mmunger. "Data association problems posed multidimensional assignment problems: algorithm development" [J] SPIE, 1993,1995
[8] Y.Bar-Shalom,Thomas, Fortmann. "Multi-target Tracking Using Joint Probabilistic Data Association" [M]. Newyork :Academic Press, 1988
[9] Y.Bar-Shalom (1981) "On the track-to-track correlation problem."
IEEE Transaction on Automatic Control. AC-26 (Apr.1981) 571-572
[10] Y.Bar-Shalom and Campo.L.(1986) "The effect of the common process noise on the two-sensor fused-track covariance." IEEE Trancesaction on Aerospace and Electronic Systems. AES-22 (Nov. 1986), 803-805
[11] willner.D,Chang ,C.B. and Dunn.K.P.(1976) "Kalman filter algorithms for a multi-sensor system." In Proceedings of the IEEE Conference on Decision and Control. Dec. 1976 p570-574
[12] Willsky.A.S,Bello,M.G.,Castanon,D.A.,Levy.,B.C,and Verghese.G.C(1982) "Combining and updating of local estimates and regional maps along sets of One- dimensional tracks." IEEE Transactions on Automatic Control, AC-27 (Aug. 1982) 799-813
[13] Yaakov Bar-shalom. "Multitarget-Multisensor Tracking: Advanced Applications."Artech House. 1990.
[14] Yaakov Bar-shalom. "Multitarget-Multisensor Tracking: Applications and Advances" Artech House. 1990.
[15] Henk A.P.Blom and Yaakov Bar-shalom. "The Interractive Multiple Model Algorithm for Systems with Markovian Switching Coeffients." IEEE.Trans.on AC. 1998, Vol. 33, No. 8.
[16] J.A.Roecker and C.D.Mcgillem. "Comparison of Two-Sensor Tracking Methods Based on State Vector Fusion and Measurement Fusion." IEEE.Trans. on AES. 1998,Vol.24,No.4.
[17] Y.bar-shalom,K.C.Chang,H.A.P.Blom. "Tracking a Maneuvering Target Using Input Estimation Versus the
Interacting Multiple Model Algorithm." IEEE.Trans.on AES. 1989,Vol.25, No.2.
[18] R.K.SAHA. "Track-to-Track fusion with Dissimilar Sensors." IEEE.Trans.on AES. 1996,Vol.32, No.2.
[19] Guu,J,A,and Wei,C.H(1991) "Tracking technique for maneuvering target with correlated measurement noise and unknown parameters" IEEE Proceeding, Pt.F, 138,3(June 1991), 278-288.
[20] Blom,H.A.P, and Bar-Shalom.Y (1988) "The interacting multiple model algorithm for systems with Makovian switching coefficients" IEEE Transactions on Automatic Control, 33 (Aug.1988), 780-783
[21] Guu, J.A,and Wei, C.H.(1991) "Maneuvering target tracking using IMM method at high measurement frequency." IEEE Transactions on Aerospace and Electronic Systems,27,3(1991),514-519
[22] Gholson,N.H.,and Moose ,R..L. (1997) "Maneuvering target tracking using adaptive state estimation." IEEE Transactions on Aerospace and Electronic Systems, AES- 15 (May 1977),448-456.
[23] Chang,C.B.,and Younes,L.C.(1982) "Mesurement correlation for multiple sensor tracking in dense target environment." IEEE Transactions on Automatic Control, (Dec. 1982), 1250-1252.
[24] Yosko, J (1992) Optimal and sub-optimal fusion of Alpha-Beta target tracks. Masters thesis, Drexel University, Philadelphia, PA, 1992.
[25] Y.Bar-shalom, "Tracking methods in a multitarget environment." IEEE Trans. Automat. Contr., Vol.AC-20, pp.618-626, Aug. 1978
[26] Sengupta,D.,and Hhis,R.A.(1989) Neural solution to the multitarget tracking data association problem. IEEE Transactions on Aerospace and Electronic Systems, 25,1 (Jan, 1989), 96-108
[27] 康耀红。《数据融合理论与应用》．西安电子科技大学出版社，1997
[28] 许升汉，概率论与随机过程，人民邮电出版社，1995年
[29] 王祁 聂伟 张兆礼。“数据融合与智能传感系统传感器技术(Journal Transducer Technology)1998年第17卷第6期
[30] 唐义平，李卫。“多传感器系统的数据融合技术 南京理工大学电光学院 上海航天 1997年第4期 p39
[31] 楼顺天，于卫，闫华梁。MATLAB程序设计语言 西安电子科技大学出版社 1998年
[32] 龙翔“多目标跟踪软件设计” 西北工业大学硕士论文
[33] 施阳，李俊。MATLAB语言工具箱-一Toolbox实用指南。
[34] 李人厚，张平安 等译校。精通MATLAB综合辅导与指南 西安交通大学出版社 1998年
[35] 薛定宇。控制系统计算机辅助设计-MATLAB语言及应用 清华大学出版社 1996年
[36] 孟希哲，线性控制系统，水利电力出版社，1995年
[37] 王永初，任秀珍，现代控制工程的数学基础，化学工业出版社，1985年
[38] 张贤达，现代信号处理，清华大学出版社，1995年
[39] 章潜五，随机信号分析，西北电信工程学院出版社，1986年
[40] 许树声，信号检测与估计，国防工业出版社，1985年
[41] 周锐，申功勋，房建成，祝世平。“多传感器融合目标跟踪”《航空学报》第19卷 第5期，1998年9月
[42] 吴小俊，曹奇英，陈保香，刘同明。“基于Bayes估计的多传感器数据融合方法研究” 2000年7月系统工程理论与实践第7期
[43] 李建勋 敬忠良 杨永胜 戴冠中 金德琨。“主被动多传感器多目标
状态信息融合”《航空学报》第18卷第2期 1997年3月(ACTA AERONAUTICA ET ASTRONAUTICA SINICA Vol.1 8No.2 Mar.1997)
[44] 于源．“基于数据融合理论的多传感器目标跟踪”西北工业大学硕士论文
[45] 宋小全，孙仲康。“多传感器机动目标跟踪”《电子学报》，1997，Vol．25,No．9．
[46] 孙红岩，毛士艺，林品兴。“多传感器数据分层融合性质。”《电子学报》，1996，Vol．24,No．6
[47] 《多传感器数据融合》(赵宗贵等译)