MetaMLIR: Meta-Learning With Multilevel Integration for Motion Pattern Recognition of Maneuvering Targets

Pattern recognition of maneuvering target is challenging due to its rapidly changing patterns and uncertainties. Short-term trajectories are essential for capturing dynamic motion changes. However, existing deep-learning based methods rely on long-term trajectories to extract more comprehensive information, making them less effective with limited data. In this paper, we focus on recognizing short-term trajectories and propose a multilevel integrated framework that narrows the latent search space