Abstract
Urban anomalies such as the abnormal flow of
crowds and traffic accidents could result in loss of
life or property if not handled properly. Detecting urban anomalies at the early stage is important to minimize the adverse effects. However, urban anomaly detection is difficult due to two challenges: a) the criteria of urban anomalies varies
with different locations and time; b) urban anomalies of different types may show different signs. In
this paper, we propose a decomposing approach
to address these two challenges. Specifically, we
decompose urban dynamics into the normal component and the abnormal component. The normal component is merely decided by spatiotemporal features, while the abnormal component is
caused by anomalous events. We then extract spatiotemporal features and estimate the normal component accordingly. At last, we derive the abnormal component to identify anomalies. We evaluate our method using both real-world and synthetic
datasets. The results show our method can detect
meaningful events and outperforms state-of-the-art
anomaly detecting methods by a large margin