A semi-Markov multiple event filter for maneuvering targets

Tracking maneuvering targets is a difficult problem due to unpredictable maneuvers which change the target's state and/or dynamics. To ensure track accuracy a filter needs to model the target correctly and quickly respond to maneuvers. A new sequential filter is proposed which attempts to improve upon existing algorithms in several areas. A more flexible internal model is used to describe effects of maneuver events. Maneuver hypotheses have improved temporal accuracy. A semi-Markov process is used to describe the probability of an event occurring as a function of time. In simulated test scenarios the new algorithm performs as well as or significantly better than Interacting Multiple Model filter.