预览加载中，请您耐心等待几秒...

粒子滤波算法在机动目标跟踪中的应用研究的中期报告.docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

粒子滤波算法在机动目标跟踪中的应用研究的中期报告 Introduction Theparticlefilteralgorithmhasbeenwidelyusedinthefieldoftargettrackingduetoitsabilitytohandlenonlinearandnon-Gaussiansystems.Inthisresearch,weapplytheparticlefilteralgorithmfortrackingamaneuveringtarget.Thisreportsummarizestheprogresswehavemadeduringthefirsthalfoftheresearch. ProblemFormulation Weconsidertheproblemoftrackingamaneuveringtargetusingmeasurementsobtainedfromasensor.Thetargetstateisdenotedbyx,whichincludesposition,velocity,andacceleration.Themeasurementvectorisdenotedbyz,whichincludespositionmeasurementswithmeasurementnoise.Wemodelthetargetmotionusingaconstant-velocitymodelwithGaussiannoiseforacceleration. Methodology Weusethefollowingstepstoimplementtheparticlefilteralgorithm: 1.Initialization-Weinitializetheparticlefilterwithasetofparticles.Eachparticlerepresentsapossibletargetstate,drawnfromthepriordistribution.Weassumeanuniformdistributionfortheinitialparticles. 2.Prediction-Wepredictthetargetstateateachtimestepbyapplyingtheconstant-velocitymodelwithGaussiannoise.Weupdateeachparticlebyaddingarandomaccelerationdrawnfromtheaccelerationnoisedistribution. 3.Update-Weupdatetheweightofeachparticlebycomparingthepredictedmeasurementwiththeactualmeasurementobtainedfromthesensor.WeuseaGaussianlikelihoodfunctiontocomputetheweight. 4.Resampling-Weresampletheparticlesbasedontheirweights.Theparticleswithhigherweightsaremorelikelytoberesampled. 5.Estimation-Weestimatethetargetstatebycomputingtheweightedaverageoftheparticles. ResultsandDiscussion WeimplementedtheparticlefilteralgorithminMATLABandtesteditonsimulateddata.WecomparedtheperformanceoftheparticlefilteralgorithmwiththeextendedKalmanfilteralgorithm. ThesimulationresultsshowedthattheparticlefilteralgorithmachievedbettertrackingperformancethantheextendedKalmanfilteralgorithmintrackingthemaneuveringtarget.Theparticlefilteralgorithmwasabletohandlethenonlinearandnon-Gaussiansystemandprovidemoreaccuratetrackingresults. Conclusion Wehavemadeprogressinapplyingtheparticlefilteralg