CAJ | 학술논문

在机动多目标跟踪问题中，目标数未知或随时间而变化，概率假设密度（PHD）滤波可以在每一时间步估计多目标状态和目标数，但单模型方法不能给出精确的估计。提出了一种交互多模型PHD滤波方法，建立多模型描述多目标运动方式，利用PHD滤波结合多模型跟踪目标运动轨迹。同时，给出了多传感器交互多模型PHD滤波方法，以提高目标跟踪精度。
재궤동다목표근종문제중，목표수미지혹수시간이변화，개솔가설밀도（PHD）려파가이재매일시간보고계다목표상태화목표수，단단모형방법불능급출정학적고계。제출료일충교호다모형PHD려파방법，건립다모형묘술다목표운동방식，이용PHD려파결합다모형근종목표운동궤적。동시，급출료다전감기교호다모형PHD려파방법，이제고목표근종정도。
In mameuvering multiple-target tracking problem, the number of targets was unknown or varied with time, proba-bility hypothesis density(PHD)filter can be used to estimate the multi-target state and the number at each time step, but single model method may not provide accurate estimates. In this paper, a interactive multiple model PHD filter was pro-posed, and then multiple sensor interactive multiple model PHD filter was proposed to improve the tracking of multiple ma-neuvering targets. PHD particle filter implementation was used to perform the proposed method consisting of multiple mam-euvering targets.