Master-Auxiliary: an efficient aggregation strategy for video anomaly detection
This work addresses the challenge of improving detection accuracy in surveillance systems by efficiently combining detectors, though it appears incremental as it builds on existing aggregation methods.
The paper tackles the problem of aggregating multiple detectors for video anomaly detection by proposing a master-auxiliary strategy that extracts credible abnormal and normal frames to assist the master detector, achieving state-of-the-art performance on multiple datasets.
The aim of surveillance video anomaly detection is to detect events that rarely or never happened in a certain scene. Generally, different detectors can detect different anomalies. This paper proposes an efficient strategy to aggregate multiple detectors. First, the aggregation strategy chooses one detector as master detector by experience, and sets the remaining detectors as auxiliary detectors. Then, the aggregation strategy extracts credible information from auxiliary detectors, including credible abnormal (Cred-a) frames and credible normal (Cred-n) frames. After that, the frequencies that each video frame being judged as Cred-a and Cred-n are counted. Applying the events' time continuity property, more Cred-a and Cred-n frames can be inferred. Finally, the aggregation strategy utilizes the Cred-a and Cred-n frequencies to vote to calculate soft weights, and uses the soft weights to assist the master detector. Experiments are carried out on multiple datasets. Comparing with existing aggregation strategies, the proposed strategy achieves state-of-the-art performance.