A Uni ed Method for the Measurement and Tracking of Narrowband Contacts from an Array of Sensors

A Unified Method for the Measurement and Tracking of Narrowband Contacts from an Array of Sensors Robert E. Zarnich, Ph.D. George Mason University, 2000 Dissertation Director: Dr. Kristine L. Bell This dissertation describes a method in which the contact tracking and narrow band direction nding processes are treated as a joint estimation problem, as opposed to the conventional approach which treats them as two isolated processes. A joint probability density function for the array snap shot batch with moving contacts is formulated. The Maximum A-Posteriori (MAP) estimator for contact states is derived for temporally uncorrelated nondeterministic signals with uncorrelated contact tracks. This estimator is an iterative algorithm employing a Nonlinear Programming (NLP) Penalty Method in conjunction with an Expectation Maximization (EM) algorithm. The NLP is used to estimate the MAP track estimate based on the synthetic signal estimates produced by the EM algorithm. This eliminates the data association step of traditional multitarget tracking approaches. This approach results in a process similar to the EM algorithm for direction nding by Miller and Furhmann, with an additional penalty term imposed by the track distribution. Observations and interpretations of the resulting formulations are given. An informal initialization procedure is presented with rationale for its composition. In addition to the batch estimation procedure, an extension to provide a sequential variant, based on a mov-