Abstract:

To address the constraints imposed by missing trajectory data in surveillance systems on the efficacy of civil aviation safety monitoring, as well as the limitations on the development and application of advanced technologies within trajectory-based operational frameworks, a completion method for trajectory based on image representation and collaborative feature perception was proposed. A conversion strategy for trajectory image representation was designed to reformulate the trajectory completion task as a deterministic image completion problem, effectively circumventing the cumulative error problem of traditional time-series data caused by the limitation of recurrent neural network inference mechanisms. A regression model fusing a multi-kernel hybrid attention module and a multi-head multi-domain fusion self-attention module was constructed to achieve the collaborative extraction of local and global spatial-temporal features, thereby effectively accomplishing the precise completion of missing trajectories. Systematic experiments based on the real-world OpenSky trajectory dataset demonstrate that the proposed method has significant advantages in trajectory completion performance and exhibits excellent generalization capability on large-scale datasets. Ablation experiments also further validate the important role of each innovative module in the model in performance enhancement.

Key words: intelligent air traffic, trajectory completion, trajectory image representation, image completion, Transformer