A probabilistic nearest neighbor filter algorithm for m validated measurements

The probabilistic nature of the nearest neighbor measurement in a cluttered environment is shown to be varying with respect to the number of validated measurements. Incorporating the number of validated measurements into the design of the probabilistic nearest neighbor filter (PNNF) produces a new data association proposed in this correspondence. The proposed algorithm for aerial target tracking in a cluttered environment is tested by a series of Monte Carlo simulation runs, and it turns out that the new filter has less sensitivity for the unknown spatial density of false measurements and better tracking performance than the existing PNNF that does not utilize the current number of validated measurements