An interacting multiple-model algorithm with switch time conditions based on adaptive transition probabilities
is proposed for tracking maneuvering targets, which ensures that the filter approximates target posterior state reasonably by
presetting switch time conditions of the model. The model can match the target motion well in real time by using transition
probabilities adaption algorithm. The theoretic and simulation analysis show that the proposed algorithm can help the filter
achieving optimal performance, make the model probability more reasonable and track the target more accurately than IMM
and STC-IMM algorithms. At the same time, it performs well on the stability and adaption.