A Tracking Method Based on Target Classification and Recognition
Pu Perry Wang, Jianwei Wang · 2019
To solve the precise tracking problem of unknown targets in the air, the method based on target classification and recognition is to select different motion models for different type of targets. In this paper, there are three unknown air targets: fighters, civil aircraft and helicopters. Firstly, different accurate motion models are designed for these three targets. Bayesian inference is used to classify and identify the target with the target state and signal. With the classification result, the suited motion model is selected for tracking. The result shows that compared with the standard Interacting Multiple Model (IMM) algorithm, this method can reduce the error of target tracking by about 10%. It shows that making accurate models for the target motion can effectively improve the tracking accuracy of the unknown target with the accurate classification result.