基于自控蝙蝠算法智能优化粒子滤波的机动目标跟踪方法
|
摘要
标准粒子滤波重采样过程中对粒子的直接删除会导致粒子贫化,并且综合性价比不高,难以满足高频段精密跟踪雷达的需求.针对上述问题,本文提出了基于自控蝙蝠算法优化粒子滤波的机动目标跟踪方法.该方法首先在粒子滤波中引入蝙蝠算法,用粒子表征蝙蝠个体,模拟蝙蝠群体搜索猎物的过程,使粒子向高似然区域移动.同时,改进算法将粒子接受新状态的比例作为反馈量,设计了自适应闭环控制策略对算法的全局搜索能力和局部搜索能力进行全程动态控制,使得粒子分布更加合理,从而进一步提高了粒子滤波的精度.最后在分别在基础非线性滤波模型和强机动强干扰目标跟踪模型中对改进算法的性能进行了测试.实验结果表明,改进算法提高了目标跟踪的精度.
Resampling of particle filters will cause particle depletion and the comprehensive performance is low,which can hardly meet the requirement of high frequency accurate radar. To address the problem,a novel adaptive control bat algorithm optimized particle filter for maneuvering target tracking was proposed in this paper. It introduced bat algorithm into particle filter and took particle as bat individual to simulate the process of hunting and made particles move to high likelihood area. Meanwhile,by taking proportion of accepting as feedback, the improved algorithm designed closed-loop control strategy and controlled the balance between ability of global optimization and local optimization and improved rationality of particles distribution and accuracy of filter. Finally, the improved algorithm was tested in basic nonlinear filter model and strong maneuveringjamming target tracking model. The experimental results prove that the new algorithm conduces to enhancement of the precision for target tracking.
Resampling of particle filters will cause particle depletion and the comprehensive performance is low,which can hardly meet the requirement of high frequency accurate radar. To address the problem,a novel adaptive control bat algorithm optimized particle filter for maneuvering target tracking was proposed in this paper. It introduced bat algorithm into particle filter and took particle as bat individual to simulate the process of hunting and made particles move to high likelihood area. Meanwhile,by taking proportion of accepting as feedback, the improved algorithm designed closed-loop control strategy and controlled the balance between ability of global optimization and local optimization and improved rationality of particles distribution and accuracy of filter. Finally, the improved algorithm was tested in basic nonlinear filter model and strong maneuveringjamming target tracking model. The experimental results prove that the new algorithm conduces to enhancement of the precision for target tracking.
引文
[1]HOSSEIN T N,AKIHIRO T,SEIICHI M.On-road multivehicle tracking using deformable object model and particle filter w ith improved likelihood estimation[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(2):748-758.
[2]LI H W,WANG J.Particle filter for manoeuvring target tracking via passive radar measurements w ith glint noise[J].IET Radar,Sonar and Navigation,2012,6(3):180-189.
[3]王伟,余玉揆,郝燕玲.一种新型混合并行粒子滤波频率估计方法[J].电子学报,2016,44(3):740-746.WANG Wei,YU Yu-kui,HAO Yan-ling.A novel parallel particle filter for frequency estimation[J].Acta Electronica Sinica,2016,44(3):740-746.(in Chinese)
[4]叶有时,刘淑芬,孙强,等.改进粒子滤波算法在深空红外小目标跟踪中的应用[J].电子学报,2015,43(8):1506-1512.YE You-shi,LIU Shu-fen,SUN Qiang,et al.Application of improved particle filter algorithm in deep space infrared small target tracking[J].Acta Electronica Sinica,2015,43(8):1506-1512.(in Chinese)
[5]DU M,NAN X M,GUAN L.Monocular human motion tracking by using DE-M C particle filter[J].IEEE Transactions on Image Processing,2013,22(10):3852-3865.
[6]蒋蔚,伊国兴,曾庆双.多普勒辅助测量IMM-PF机动目标跟踪[J].宇航学报,2011,32(2):343-348.JIANG Wei,YI Guo-xing,ZENG Qing-shuang.M aneuvering target tracking using IM M-PF w ith Doppler-aided measurement[J].Journal of Astrophysics,2011,32(2):343-348.(in Chinese)
[7]FOO P H,NG G W.Combining the interacting multiple model method w ith particle filters for maneuvering target tracking[J].IET Radar,Sonar and Navigation,2011,5(3):234-255.
[8]王晓,韩崇昭.基于混合采样的多模型机动目标跟踪算法[J].自动化学报,2013,39(7):1152-1156.WANG Xiao,HAN Chong-Zhao.A multiple model particle filter for maneuvering target tracking based on composite sampling[J].Acta Automatica Sinica,2013,39(7):1152-1156.(in Chinese)
[9]CHEN Z M,QU Y X,LIU B,et al.Improved multiple model target tracking algorithm based on particle filter[J].Proceedings of IM ech E Part G:Journal of Aerospace Engineering,2016,230(4):747-759.
[10]张琪,胡昌华,乔玉坤.基于权值选择的粒子滤波算法研究[J].控制与决策,2008,23(1):117-120.ZHANG Qi,HU Chang-hua,QIAO Yu-kun.Particle filter algorithm based on w eight selected[J].Control and Decision,2008,23(1):117-120.(in Chinese)
[11]LI T,SATTAR T P,SUN S.Deterministic resampling:Unbiased sampling to avoid sample impoverishment in particle filters[J].Signal Processing,2012,92(7):1637-1645.
[12]PAWEL M S,ZSóFIA L,ROBERT B.Saturated particle filter:Almost sure convergence and improved resampling[J].Automatica,2013,49:147-159.
[13]YU Y,ZHENG X.Particle filter with ant colony optimization for frequency offset estimation in OFDM systems w ith unknow n noise distribution[J].Signal Processing,2011,91(5):1339-1342.
[14]ZHONG J,FUNG Y F.Case study and proofs of ant colony optimization improved particle filter algorithm[J].IET Control Theory&Applications,2012,6(5):689-697.
[15]XIAN W,LONG B,LI M,et al.Prognostics of lithiumion batteries based on the verhulst model,particle sw arm optimization and particle filter[J].IEEE Transactions on Instrumentation and M easurement,2013,63(1):2-17.
[16]邱雪娜,刘士荣,吕强.基于信息分享机制的粒子滤波算法及其在视觉跟踪中的应用[J].控制理论与应用,2010,27(12):1724-1730.QIU Xu-na,LIU Shi-rong,LQiang.Particle filter algorithm based on information-shared mechanism and its application to visual tracking[J].Control Theory&Applications,2010,27(12):1724-1730.(in Chinese)
[17]陈志敏,薄煜明,吴盘龙,等.基于自适应粒子群优化的新型粒子滤波在目标跟踪中的应用[J].控制与决策,2013,28(2):193-200.CHEN Zhi-min,BO Yu-ming,WU Pan-long,et al.Novel particle filter algorithm based on adaptive particle sw arm optimization and its application to radar target tracking[J].Control and Decision,2013,28(2):193-200.(in Chinese)
[18]YANG X S.A new bat-inspired algorithm[A].Studies Computational Intelligence:Nature Inspired Cooperative Strategies for Optimization(NICSO)[C].Berlin Heidelberg:Springer,2010,Vol284.65-74.
[19]LI L L,ZHOU Y Q.A novel complex-valued bat algorithm[J].Neural Computing&Applications,2014,25(6):1369-1381.
[20]CHEN Y T,SHIEH C S,HORNG M F,et al.A guidable bat algorithm based on doppler effect to improve solving efficiency for optimization problems[J].Lecture Notes in Computer Science,2014,8871(1):373-383.
[21]RODRIGUES D,PEREIRA L A M,NAKAMURA R Y M,et al.A w rapper approach for feature selection based on bat algorithm and optimum-path forest[J].Expert Systems w ith Applications,2014,41(5):2250-2258.
[22]BACK T.Evolutionary Algorithms in Theory and Practice:Evolution Strategies,Evolutionary Programming,Genetic Algorithms[M].Oxford:Oxford University Press,1996.
[2]LI H W,WANG J.Particle filter for manoeuvring target tracking via passive radar measurements w ith glint noise[J].IET Radar,Sonar and Navigation,2012,6(3):180-189.
[3]王伟,余玉揆,郝燕玲.一种新型混合并行粒子滤波频率估计方法[J].电子学报,2016,44(3):740-746.WANG Wei,YU Yu-kui,HAO Yan-ling.A novel parallel particle filter for frequency estimation[J].Acta Electronica Sinica,2016,44(3):740-746.(in Chinese)
[4]叶有时,刘淑芬,孙强,等.改进粒子滤波算法在深空红外小目标跟踪中的应用[J].电子学报,2015,43(8):1506-1512.YE You-shi,LIU Shu-fen,SUN Qiang,et al.Application of improved particle filter algorithm in deep space infrared small target tracking[J].Acta Electronica Sinica,2015,43(8):1506-1512.(in Chinese)
[5]DU M,NAN X M,GUAN L.Monocular human motion tracking by using DE-M C particle filter[J].IEEE Transactions on Image Processing,2013,22(10):3852-3865.
[6]蒋蔚,伊国兴,曾庆双.多普勒辅助测量IMM-PF机动目标跟踪[J].宇航学报,2011,32(2):343-348.JIANG Wei,YI Guo-xing,ZENG Qing-shuang.M aneuvering target tracking using IM M-PF w ith Doppler-aided measurement[J].Journal of Astrophysics,2011,32(2):343-348.(in Chinese)
[7]FOO P H,NG G W.Combining the interacting multiple model method w ith particle filters for maneuvering target tracking[J].IET Radar,Sonar and Navigation,2011,5(3):234-255.
[8]王晓,韩崇昭.基于混合采样的多模型机动目标跟踪算法[J].自动化学报,2013,39(7):1152-1156.WANG Xiao,HAN Chong-Zhao.A multiple model particle filter for maneuvering target tracking based on composite sampling[J].Acta Automatica Sinica,2013,39(7):1152-1156.(in Chinese)
[9]CHEN Z M,QU Y X,LIU B,et al.Improved multiple model target tracking algorithm based on particle filter[J].Proceedings of IM ech E Part G:Journal of Aerospace Engineering,2016,230(4):747-759.
[10]张琪,胡昌华,乔玉坤.基于权值选择的粒子滤波算法研究[J].控制与决策,2008,23(1):117-120.ZHANG Qi,HU Chang-hua,QIAO Yu-kun.Particle filter algorithm based on w eight selected[J].Control and Decision,2008,23(1):117-120.(in Chinese)
[11]LI T,SATTAR T P,SUN S.Deterministic resampling:Unbiased sampling to avoid sample impoverishment in particle filters[J].Signal Processing,2012,92(7):1637-1645.
[12]PAWEL M S,ZSóFIA L,ROBERT B.Saturated particle filter:Almost sure convergence and improved resampling[J].Automatica,2013,49:147-159.
[13]YU Y,ZHENG X.Particle filter with ant colony optimization for frequency offset estimation in OFDM systems w ith unknow n noise distribution[J].Signal Processing,2011,91(5):1339-1342.
[14]ZHONG J,FUNG Y F.Case study and proofs of ant colony optimization improved particle filter algorithm[J].IET Control Theory&Applications,2012,6(5):689-697.
[15]XIAN W,LONG B,LI M,et al.Prognostics of lithiumion batteries based on the verhulst model,particle sw arm optimization and particle filter[J].IEEE Transactions on Instrumentation and M easurement,2013,63(1):2-17.
[16]邱雪娜,刘士荣,吕强.基于信息分享机制的粒子滤波算法及其在视觉跟踪中的应用[J].控制理论与应用,2010,27(12):1724-1730.QIU Xu-na,LIU Shi-rong,LQiang.Particle filter algorithm based on information-shared mechanism and its application to visual tracking[J].Control Theory&Applications,2010,27(12):1724-1730.(in Chinese)
[17]陈志敏,薄煜明,吴盘龙,等.基于自适应粒子群优化的新型粒子滤波在目标跟踪中的应用[J].控制与决策,2013,28(2):193-200.CHEN Zhi-min,BO Yu-ming,WU Pan-long,et al.Novel particle filter algorithm based on adaptive particle sw arm optimization and its application to radar target tracking[J].Control and Decision,2013,28(2):193-200.(in Chinese)
[18]YANG X S.A new bat-inspired algorithm[A].Studies Computational Intelligence:Nature Inspired Cooperative Strategies for Optimization(NICSO)[C].Berlin Heidelberg:Springer,2010,Vol284.65-74.
[19]LI L L,ZHOU Y Q.A novel complex-valued bat algorithm[J].Neural Computing&Applications,2014,25(6):1369-1381.
[20]CHEN Y T,SHIEH C S,HORNG M F,et al.A guidable bat algorithm based on doppler effect to improve solving efficiency for optimization problems[J].Lecture Notes in Computer Science,2014,8871(1):373-383.
[21]RODRIGUES D,PEREIRA L A M,NAKAMURA R Y M,et al.A w rapper approach for feature selection based on bat algorithm and optimum-path forest[J].Expert Systems w ith Applications,2014,41(5):2250-2258.
[22]BACK T.Evolutionary Algorithms in Theory and Practice:Evolution Strategies,Evolutionary Programming,Genetic Algorithms[M].Oxford:Oxford University Press,1996.