An Efficient Implementation of the Generalized Labeled Multi-Bernoulli Filter

This paper proposes an efficient implementation of the generalized labeled multi-Bernoulli (GLMB) filter by combining the prediction and update into a single step. In contrast to an earlier implementation that involves separate truncations in the prediction and update steps, the proposed implementation requires only one truncation procedure for each iteration, which can be performed using a standard ranked assignment algorithm. Furthermore, we propose a new truncation technique based on Gibbs sampling that drastically reduces the complexity of the filter without sacrificing tracking performance.