A Trajectory Similarity Computation Method based on GAT-based Transformer and CNN model

Trajectory similarity computation is very important for trajectory data mining. It is applied into many trajectory mining tasks, including trajectory clustering, trajectory classification and trajectory search etc. So efficient trajectory similarity computation method is very useful for improving trajectory mining result. Nowadays many trajectory similarity computation methods have been proposed. But these methods don’t take the outline feature of long trajectory into consideration. Thus a new trajectory similarity computation method is proposed in this paper. This method not only takes the long-term dependence feature of long trajectory into consideration, but also considers the outline feature of long trajectory. The proposed method employs GAT-based transformer to extract long-term dependence feature from long trajectory. And it applies Convolutional Neural Network to extract outline feature from long trajectory.