Centralized multiple-view information fusion for multi-object tracking using labeled multi-Bernoulli filters

In many applications, the states of an unknown number of objects need to be estimated using measurements that are acquired from multiple sensors with different fields of view. When object labels are part of their states, the problem is called the multi-sensor multi-object tracking problem. This paper presents a new solution for statistical fusion of multisensor information in such problems where the sensors form a centralized network. Assuming that a labeled multi-Bernoulli (LMB) filter is running at each sensor node, we suggest a new approach to fuse the multiple LMB posteriors in a centralized manner. The fused posterior is designed to incorporate all the information provided by multiple sensor nodes for each object label. Numerical experiments involving challenging multi-sensor multi-object tracking scenarios show that the proposed method outperforms the state of the art.