Multi-target PHD filtering: proposition of extensions to the multi-sensor case

摘要: Common difficulties in multi-target tracking arise from the fact that system state and collection of measures are unordered their size evolve randomly through time. The random finite set theory provides a powerful framework to cope with these issues. This document focuses more particularly on PHD (Probability Hypothesis Density) filter proposed by Mahler. first part this report is synthesis Mahler's work aims at providing thorough description construction single-sensor filter. Then, based few leads provided Mahler, second proposes several extensions multi-sensor case.