Master-Auxiliary: an efficient aggregation strategy for video anomaly detection

TL;DR

This paper introduces an efficient aggregation strategy for video anomaly detection that combines multiple detectors by selecting a master and auxiliary detectors, improving detection accuracy through credible frame analysis and voting.

Contribution

It proposes a novel aggregation method that leverages credible frames and event continuity to enhance anomaly detection performance in surveillance videos.

Findings

Achieves state-of-the-art results on multiple datasets.

Effectively combines multiple detectors for improved accuracy.

Utilizes credible frame voting to enhance detection reliability.

Abstract

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.