Sequential versus parallel architecture for Multiple sensors Multiple target tracking

In this paper, we propose to compare Parallel and sequential architectures for Multi-sensor Multi-target tracking. This contribution aims to contribute in solving the problem of model-based body motion estimation by using data coming from multiple visual sensors. To ensure accurate track we use the interacting multiple model (IMM) associated with the unscented Kalman filter (IMM-UKF). To resolve the problem of data association, the JPDA approach is combined with the IMM-UKF algorithm, the derived algorithm is noted JPDA-IMM-UKF. Finally the simulation results show clearly the superiority of the sequential architecture, according to the parallel one, on terms of precision and track loss ratio.