中文摘要：

针对现有的多目标跟踪方法中，检测概率和量测噪声协方差等模型参数未知时目标跟踪性能下降的问题，提出了一种联合估计检测概率和量测噪声协方差的势概率假设密度（cardinalized probability hypothesis density ,CPHD）目标跟踪方法。首先对多参数未知的多目标跟踪问题进行建模，将检测概率看作是某个分布中的变量，继而可以通过估计该分布的均值来作为检测概率，再利用变分贝叶斯方法对量测噪声协方差进行估计，最后给出了算法的高斯实现。仿真结果表明，所提算法在检测概率和量测噪声协方差联合未知环境下具有较好的目标跟踪性能。

英文摘要：

Since the multi-object tracking performance of the traditional method will decline with unknown model parameters, a CPHD target tracking algorithm is proposed to jointly estimate the detection probability and measurement noise covariance. Firstly, for model the unknown parameters of multiple targets tracking, the detection probability is considered as a variable in a distribution. The detection probability can be obtained by estimating the mean of the distribution. Then, the Variational Bayesian method is used to estimate the covariance of the measurement noise. Finally, the Gaussian implementation of this algorithm is presented. Simulation results show that the algorithm has good tracking performance under jointly unknown detection probability and the covariance of the measurement noise.