Data Mining Algorithm for Moving Object Trajectory

Aiming at the poor effect and long recognition time of data mining algorithm for moving target trajectory recognition, a data mining algorithm based on improved Hausdorff distance is proposed. The position and angle of abnormal trajectory data are detected by calculating the distance between trajectory classification and sub trajectory line segments, and the trajectory unit is established by using the improved Hausdorff distance algorithm to optimize the similarity matching structure. Experimental results show that the algorithm has low error pruning rate in identifying moving target trajectory, improves the detection efficiency of moving target trajectory recognition data, and ensures the quality of moving target trajectory recognition data mining

Identifying Wrong-Way Driving Incidents from Regular Traffic Videos Using Unsupervised Trajectory-based Method

Currently, transportation agencies have implemented different wrong-way driving (WWD) detection systems based on loop detectors, radar detectors, or thermal cameras. Such systems are often deployed at fixed locations in urban areas or on toll roads. The majority of rural interchange terminals does not have real-time detection systems for WWD incidents. Portable traffic cameras are used to temporarily monitor WWD activities at rural interchange terminals. However, it has always been a time-consuming task to manually review those videos to identify WWD incidents. The objective of this study was to develop an unsupervised trajectory-based method to automatically detect WWD incidents from regular traffic videos (not limited by mounting height and angle). The principle of the method includes three primary steps: vehicle recognition and trajectory generation, trajectory clustering, and outlier detection. This study also developed a new subtrajectory-based metric that makes the algorithm more adaptable for vehicle trajectory classification in different road scenarios. Finally, the algorithm was tested by analyzing 357 h of traffic videos from 14 partial cloverleaf interchange terminals in seven U.S. states. The results suggested that the method could identify all the WWD incidents in the testing videos with an average precision of 80%. The method significantly reduced person-hours for reviewing the traffic videos. Furthermore, the new method could also be applied in detecting and extracting other kinds of abnormal traffic activities, such as illegal U-turns.

Modeling Trajectories with Neural Ordinary Differential Equations

Recent advances in location-acquisition techniques have generated massive spatial trajectory data. Recurrent Neural Networks (RNNs) are modern tools for modeling such trajectory data. After revisiting RNN-based methods for trajectory modeling, we expose two common critical drawbacks in the existing uses. First, RNNs are discrete-time models that only update the hidden states upon the arrival of new observations, which makes them an awkward fit for learning real-world trajectories with continuous-time dynamics. Second, real-world trajectories are never perfectly accurate due to unexpected sensor noise. Most RNN-based approaches are deterministic and thereby vulnerable to such noise. To tackle these challenges, we devise a novel method entitled TrajODE for more natural modeling of trajectories. It combines the continuous-time characteristic of Neural Ordinary Differential Equations (ODE) with the robustness of stochastic latent spaces. Extensive experiments on the task of trajectory classification demonstrate the superiority of our framework against the RNN counterparts.