A tracking algorithm based on association probability for radar against deceptive chaff

This paper proposes a new tracking algorithm for radar based on association probability of each observation to confront deceptive chaff. When deceptive chaff is released, conventional tracking algorithm such as nearest neighbour which keeps only a single hypothesis may lose efficacy once it chooses false target. Hence the possibility of every observation coming from real target is taken into account in the proposed method. The association probability of observations has been discussed at length, and the tracking algorithm using Kalman filter with association probability as weights is proposed. The performance of the proposed algorithm is validated by numerical simulation, which outperforms the conventional algorithms especially when deceptive chaff existed.