强跟踪输入估计概率假设密度多机动目标跟踪算法

针对多机动目标跟踪中，目标数目未知及加速度不确定的问题，提出一种强跟踪输入估计（modifiedinputestimation，MIE）概率假设密度多机动目标跟踪算法．在详细分析算法的基础上，通过引入强跟踪多重渐消因子，以不同速率实时调节滤波器各个通道的预测协方差及相应的滤波器增益，从而实现MIE算法对加速度未知或发生人幅度突变的机动目标白适应跟踪能力；并将该算法与概率假设密度滤波算法有效结合，町以较好地跟踪未知数目的多机动目标．仿真结果表明，新算法比传统的多机动目标跟踪算法具有更岛的跟踪精度，且具有较好的实时性．

Strong tracking modified input estimation probability hypothesis density for multiple maneuvering targets tracking

To deal with the unknown target number and the uncertain acceleration in tracking multiple maneuvering targets, we propose a new adaptive probability hypothesis density(PHD) algorithm based on the strong tracking modified input estimation(STMIE) technique. First, strong tracking filter multiple fading factors are introduced to the MIE algorithm which adjusts the prediction covariance and the corresponding filter gain with different rate in real time to make the MIE method tracking high maneuvering targets perfectly; and then, the adaptive MIE method is combined with the PHD filter to track multiple maneuvering targets. Simulation results show that the proposed algorithm is with higher tracking precision and better real-time performance than the traditional multiple maneuvering target tracking algorithms.