Vehicle trajectory clustering for traffic intersection surveillance
Mei Yeen Choong, Lorita Angeline, Renee Ka Yin Chin, Kiam Beng Yeo, Kenneth Tze Kin Teo · 2016
Traffic data obtained from surveillance system has been vital for traffic operators to monitor the traffic flow at a traffic intersection. However, detailed information of the traffic flow such as the behavioural manoeuvres is not sufficiently provided by the inductive-loop traffic detectors. Thus, vehicles trajectory dataset is selected as traffic data input in traffic simulation for modelling the traffic flow. In this paper, clustering on the vehicle trajectory dataset is simulated to group the data via similarity function based on Longest Common Subsequence (LCSS). To evaluate the clustering result, Rand Index (RI) is implemented to compare the simulated result with the ground-truth result.