Robust multi-sensor generalized labeled multi-Bernoulli filter

This paper proposes an efficient and robust algorithm to estimate target trajectories with unknown detection profiles clutter rates using measurements from multiple sensors. In particular, we propose combine the multi-sensor Generalized Labeled Multi-Bernoulli (MS-GLMB) filter Cardinalized Probability Hypothesis Density (CPHD) filters rates. The probability is augmented filtering state space for joint estimation. Experimental results show that proposed exhibits near-optimal performance in sense it comparable optimal MS-GLMB operating true rate probability. More importantly, outperforms other studied when profile are time-variant. attributed ability of learn background parameters on-the-fly.