This paper summarizes and extends recent results in Multiple-Target Tracking theory and applies the results to an Ocean Surveillance example. The relevant features of ships are characterized by either discrete-valued or continuous-valued state variables. An algorithm is developed which estimates both types of state variables. The inclusion of the attribute information aids the data association problem but complicates the target representation. In addition, the algorithm is capable of initiating tracks, accounting for false or missing reports, and processing sets of dependent reports. As each measurement is received, probabilities are calculated for the hypotheses that the measurement came from previously known targets in a target file, from a new target, or that the measurement is false. As more measurements are received, the probabilities of joint hypotheses are calculated recursively using all available information, such as: density of unknown targets, density of false targets, the probability of detection, location uncertainty and attribute data such as target identity, target type, contact number, and type radar. This branching technique allows correlation of a measurement with its source based upon subsequent, as well as previous data. To keep the number of hypotheses reasonable, unlikely hypotheses are eliminated and hypotheses with similar target estimates are combined.