A Data-driven Neural Network Used on Maneuvering Target Tracking

Maneuvering target tracking is a key issue in the field of target tracking. The target tracking based on the motion model is hard to accurately predict and track maneuvering target. This article design a data-driven neural network to complete the maneuvering target tracking. A maneuver trajectory generator and trajectory mapper are designed to generate enough trajectory sample, providing data-driven support for training the neural network. The DTN network was trained based on the trajectory sample and the trained DTN network is able to effectively track the maneuvering target. Simulation result demonstrates that the DTN has high accuracy and efficiency than the traditional model prediction method on maneuvering target tracking.