A Novel Traffic Flow Reduction Method Based on Incomplete Vehicle History Spatio-Temporal Trajectory Data

In order to improve the effect of path planning in emergencies, missing position imputation and velocity restoration vehicle trajectory provide data support for emergency analysis. At present, there are many methods fill information, but they basically restore after analyzing a large number datasets. However, reduction method with few training sets needs be further explored. For this purpose, novel cube model (TDC) is designed store time, position, information hierarchically data. Based on model, three Hierarchical Trace-Back algorithms HTB-p, HTB-v, HTB-KF proposed paper. Finally, experiments verify that conduct different sample sets, it has satisfactory performance individual points segments.