iBOAT: Isolation-Based Online Anomalous Trajectory Detection

• Published in: IEEE transactions on intelligent transportation systems 2013-06, Vol.14 (2), p.806-818
• Main Authors: Chao Chen, Daqing Zhang, Castro, P. S., Nan Li, Lin Sun, Shijian Li, Zonghui Wang
• Format: Article
• Language: English
• Subjects: Accuracy; Anomalous trajectory detection; Cities and towns; Computer Science; Global Positioning System; Global Positioning System (GPS) traces; Indexes; isolation; Networking and Internet Architecture; online; Roads; Trajectory; Vehicles
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2013.2238531

Trajectories obtained from Global Position System (GPS)-enabled taxis grant us an opportunity not only to extract meaningful statistics, dynamics, and behaviors about certain urban road users but also to monitor adverse and/or malicious events. In this paper, we focus on the problem of detecting anomalous routes by comparing the latter against time-dependent historically "normal" routes. We propose an online method that is able to detect anomalous trajectories "on-the-fly" and to identify which parts of the trajectory are responsible for its anomalousness. Furthermore, we perform an in-depth analysis on around 43 800 anomalous trajectories that are detected out from the trajectories of 7600 taxis for a month, revealing that most of the anomalous trips are the result of conscious decisions of greedy taxi drivers to commit fraud. We evaluate our proposed isolation-based online anomalous trajectory (iBOAT) through extensive experiments on large-scale taxi data, and it shows that iBOAT achieves state-of-the-art performance, with a remarkable performance of the area under a curve (AUC) ≥ 0.99.