Anomaly detection based on sparse coding with two kinds of dictionaries

In this paper, we propose a novel method to detect anomaly from videos based on sparse reconstruction. Different from the traditional methods, two kinds of dictionaries are employed for anomaly detection with one representing the global dictionary and the other indicating the online one. The global dictionary is first trained on training samples, and then used for the local online dictionary learning and anomaly detection. A novel updating scheme is proposed in the local online dictionary learning for an accurate anomaly detection. Experiments on the public databases show that our method can effectively detect abnormal events in complex scenes.