In this paper, we proposed a hierarchical clustering framework to classify vehicle motion trajectories in real traffic video based on their pairwise similarities. First raw trajectories are pre-processed and resampled at equal space intervals. Then spectral clustering is used to group trajectories with similar spatial patterns. Dominant paths and lanes can be distinguished as a result of two-layer hierarchical clustering. Detection of novel trajectories is also possible based on the clustering results. Experimental results demonstrate the superior performance of spectral clustering compared with conventional fuzzy K-means clustering and some results of anomaly detection are presented.
Similarity based vehicle trajectory clustering and anomaly detection
2005-01-01
272432 byte
Conference paper
Electronic Resource
English
Similarity Based Vehicle Trajectory Clustering and Anomaly Detection
British Library Conference Proceedings | 2005
|Trajectory anomaly detection system and online trajectory anomaly detection method
European Patent Office | 2024
|