TR-ODE: Robust Vehicle Trajectory Recovery via Seq2Seq Learning with GRU-ODE-Bayes

Recovering fine-grained urban vehicle trajectory data hold great potential for understanding mobility patterns and improving the efficiency of transportation systems. Most existing solutions rely on regularly sampled GPS points, which capture data only from participating vehicles. In this work, we exploit traffic camera observation data for city-wide vehicle trajectory recovery. Nevertheless, there are two major challenges. First, traffic cameras are sparsely deployed at road intersections, resulting in uneven vehicle observations and irregular sampling intervals. Second, substantial uncertainty arises when reconstructing trajectories between distant consecutive observations. To address the above challenges, we propose TR-ODE , a novel encoder-decoder framework based on Neural Ordinary Differential Equations for continuous-time trajectory recovery. Specifically, TR-ODE employs customized GRU-ODE-Bayes to evolve hidden states between observations and update the current hidden state to incorporate the incoming observations. By incorporating a multi-task learning block, TrajRec , our method integrates road embeddings and self-attention scores to assist in simultaneous predictions on road segments and moving ratios for trajectory recovery. Extensive experimental studies on two real-world datasets demonstrate that TR-ODE outperforms state-of-the-art methods in vehicle trajectory recovery from irregular observations, reducing MAE and RMSE by up to 17.11% and 14.47%, respectively.