Adaptively modeling the target birth intensity while maintaining the filtering efficiency is a challenging issue in multi-target tracking (MTT). Generally, the target birth probability is predefined as a constant and only the target birth density is considered in existing adaptive birth models, resulting in deteriorated target tracking accuracy, especially in the target appearing cases. In addition, the existing adaptive birth models also give rise to a decline in operation efficiency on account of the extra birth modeling calculations. To properly adapt the real variation of the number of newborn targets and improve the multi-target tracking performance, a novel fast sequential Monte Carlo (SMC) adaptive target birth intensity cardinality balanced multi-target multi-Bernoulli (CBMeMBer) filter is proposed in this paper. Through adaptively conducting the target birth probability in a pre-processing step, which incorporates the information of current measurements to correct the pre-setting of the target birth probability, the proposed filter can truly adapt target birth cases and achieve better tracking accuracy. Moreover, the implementation efficiency can be improved significantly by employing a measurement noise-based threshold in the likelihood calculations of the multi-target updating. Simulation results verify the effectiveness of the proposed filter.

The deployment of sensors in multi-sensor network systems needs to measure the actual state of the target. There may be significant errors in transmitting information to each sensor node through the sensor network system, which cannot accurately reflect the actual target state, resulting in the sensor network generating wrong measurements and instructions. The accuracy of target state estimation is affected by two factors: random noise in the process of sensor measurement and random delay of sensor data information in the network transmission process. Because of the above problems, this paper designs a probabilistic time window multi-sensor arithmetic average fusion multi-target tracking algorithm that can resist these interference factors, compensate for the random delay, and calculate the correct probability cumulative value of different sensor nodes in the time window, and then adjusts the probability hypothesis density filter update value as the multi-sensor fusion weight to reduce the negative impact of random interference on the sensor measurement. The simulation results show that under the condition of accurate probability information of random noise and random delay, compared with the traditional arithmetic average fusion and GCI fusion algorithms, the proposed probabilistic time window multi-sensor network arithmetic average fusion algorithm has the most minor tracking error and is more suitable for complex tracking scenarios with clutter and detection probability changes.

The cardinality-balanced multi-target multi-Bernoulli (CBMeMBer) filter is a promising solution for multi-target tracking. However, the performance of the CBMeMBer filter will be degraded severely by outliers in the presence of heavy-tailed process noise and measurement noise. To address this challenging issue, a novel CBMeMBer filter called the Student’s t mixture CBMeMBer (STM-CBMeMBer) filter is proposed in this paper, by assuming that the joint probability density function (pdf) of the state and process noise and the joint pdf of the state and measurement noise follow joint Student’s t distributions. Following that, a closed-form solution of the CBMeMBer recursion is obtained by approximating the probability density parameter of the multi-Bernoulli as a STM. The proposed algorithm is a generalization of existing Gaussian mixture CBMeMBer (GM-CBMeMBer) filter, and it reduces to the GM-CBMeMBer filter in some special cases. Simulation results demonstrate that robust multi-target tracking can be achieved in the presence of outliers in process and measurement noises.

Aiming at the problem of asynchronous multi-target tracking, this paper studies the AA fusion optimization problem of multi-sensor networks. Firstly, each sensor node runs a PHD filter, and the measurement information obtained from different sensor nodes in the fusion interval is flood communicated into composite measurement information. The Gaussian component representing the same target is associated with a subset by distance correlation. Then, the Bayesian Cramér–Rao Lower Bound of the asynchronous multi-target-tracking error, including radar node selection, is derived by combining the composite measurement information representing the same target. On this basis, a multi-sensor-network-optimization model for asynchronous multi-target tracking is established. That is, to minimize the asynchronous multi-target-tracking error as the optimization objective, the adaptive optimization design of the selection method of the sensor nodes in the sensor network is carried out, and the sequential quadratic programming (SQP) algorithm is used to select the most suitable sensor nodes for the AA fusion of the Gaussian components representing the same target. The simulation results show that compared with the existing algorithms, the proposed algorithm can effectively improve the asynchronous multi-target-tracking accuracy of multi-sensor networks.

Gaussian mixture probability hypothesis density (GM-PHD) filtering based on random finite set (RFS) is an effective method to deal with multi-target tracking (MTT). However, the traditional GM-PHD filter cannot form a continuous track in the tracking process, and it is easy to produce a large number of redundant invalid likelihood functions in a dense clutter environment, which reduces the computational efficiency and affects the update result of target probability hypothesis density, resulting in excessive tracking error. Therefore, based on the GM-PHD filter framework, the target state space is extended to a higher dimension. By adding a label set, each Gaussian component is assigned a label, and the label is merged in the pruning and merging step to increase the merging threshold to reduce the Gaussian component generated by dense clutter update, which reduces the computation in the next prediction and update. After pruning and merging, the Gaussian components are further clustered and optimized by threshold separation clustering, thus as to improve the tracking performance of the filter and finally realizing the accurate formation of multi-target tracks in a dense clutter environment. Simulation results show that the proposed algorithm can form a continuous and reliable track in dense clutter environment and has good tracking performance and computational efficiency.

In complex electromagnetic environments, existing multi-target tracking algorithms often suffer from performance degradation. To address this challenge, this paper proposes a Distributed Multi-Sensor LMB algorithm based on RCS information assistance. The algorithm models target RCS information parameters using a non-stationary autoregressive Gamma process to achieve Bayesian RCS estimation. This method comprises two main steps: single-node local filtering and multi-node information fusion. During the local filtering phase, the target state is first extended by introducing RCS information parameters to establish the likelihood function, thereby deriving updated prediction and update equations. This process fully utilizes the target's RCS information to enhance the distinction between targets and clutter. Subsequently, based on this information, we establish a label matching quality model and combine label historical data to achieve label matching among multiple nodes. This matching process enables effective fusion of multi-sensor data, thereby improving overall tracking accuracy. Simulation experiment results demonstrate that the proposed method exhibits strong effectiveness and robustness in dense clutter environments and under low detection probability conditions.