Abstract
This paper proposes an online taxi driving anomalous trajectory detection framework for maintaining the city public transport civilisation. The framework consists of two parts: an offline detector building and an online trajectory detection. The former employs a popular route concept to process massive trajectory data and adapts the mapping grid-based anomaly detection method by taking into account spatial and temporal characteristics of the trajectory dataset. The latter maps ongoing trajectory points and detects whether the ongoing driving route is anomalous or reliable. The proposed trajectory anomaly detection method is faster than the existing methods as it involves only simple activities of trajectory point mapping and retrieval procedure, without requiring extra distance or density calculation. In addition, the proposed method has detection accuracy comparable to that of the existing high-performance methods. The application and efficiency of the proposed method are demonstrated using extensive experiments on real datasets.