ALGORITHM FOR MULTIPLE EXTENDED TARGET TRACKING

This paper introduces a novel algorithm for multi–extended object tracking, which is based on probabilistic–statistical modelling, machine learning, and optimization theory. The proposed approach encompasses methods modelling the state of extended objects, data association, predicting updating objects at each time step. performance was assessed compared with other existing algorithms using simulation in MATLAB. emulates scenarios are tracked while moving under various noise levels. Simulation results demonstrate that can effectively detect track trajectories multiple different levels, utilizing both linear non–linear measurements from an array sensors. Furthermore, estimates not only number kinematic states targets but also provides approximate evaluation their size. algorithm, terms accuracy target estimation, superior to comparable algorithms, particularly high–noise environments. Potential applications this include tracking context autonomous driving, driver assistance, safety assurance, domains.