| Standard multitarget tracking algorithms employ Bayesian updating to associate the highest measurement probability to target tracks. Limitations of traditional tracking algorithms are that measurement-to-track associations do not account for target-type uncertainties, target identities, or incomplete knowledge. The dissertation develops the Joint Belief-Probabilistic Data Association (JBPDA) and the Set-Based Data Association (SBDA) simultaneous tracking and identification algorithms to: advance data association tracking techniques, provide an alternative to Bayesian tracking methods, and demonstrate a fusion of stochastic and set-based uncertainties.; The JBPDA algorithm fuses kinematic-continuous and identification-discrete features to track and identify targets. The set of features includes moving-target indicator (MTI) position hits and high-range resolution (HRR) radar range-bin locations and amplitudes. Kinematic states include target positions, velocities, and poses, where pose is the aspect angle of the target. Using MTI positions and estimated track-pose information, HRR features are extracted to obtain a target belief-ID with an associated belief-pose. To facilitate the combination of continuous-probabilistic and discrete-set mathematics, a belief-probabilistic uncertainty calculus is devised to combine track-pose and belief-pose. The intersection, association, and filtering of track and identification beliefs results in a recursive simultaneous tracking and identification algorithm.; The SBDA uses a belief filter, based on Dempster-Shafer theory, to filter past, estimate current, and predict future tracking and ID beliefs by associating believable events for measurement-to-track updates. Belief sets are constructed spatially over kinematic positions, evidentially over target identifications, and temporally and recursively for stochastic process updates. In contrast to tracking methods which use Bayesian methods, the SBDA is robust to cluttered measurements, can identify an unknown number and type of targets, and captures incomplete knowledge and target maneuvers.; The dissertation research includes: developing state equations for simultaneous tracking and ID, innovating mathematics to combine belief and probabilistic uncertainties, deriving information fusion and mutual information relationships for HRR and MTI measurements, assessing track quality through belief updates, and demonstrating a set-based and belief-probabilistic recursive belief-filtering approaches for simultaneous HRR tracking and identification of moving targets. The results demonstrate that the JBPDA and SBDA effectively track and ID a set of moving targets from cluttered HRR and MTI measurements. |
