Predicting Next Local Appearance for Video Anomaly Detection

TL;DR

This paper introduces a fast, generalizable adversarial approach for local video anomaly detection that predicts future object appearances to identify anomalies based on reconstruction errors.

Contribution

It proposes a novel adversarial framework that efficiently predicts next-frame object appearances for anomaly detection, improving speed and scene generalization over existing methods.

Findings

Competitive with state-of-the-art performance

Significantly faster training and inference

Better generalization to unseen scenes

Abstract

We present a local anomaly detection method in videos. As opposed to most existing methods that are computationally expensive and are not very generalizable across different video scenes, we propose an adversarial framework that learns the temporal local appearance variations by predicting the appearance of a normally behaving object in the next frame of a scene by only relying on its current and past appearances. In the presence of an abnormally behaving object, the reconstruction error between the real and the predicted next appearance of that object indicates the likelihood of an anomaly. Our method is competitive with the existing state-of-the-art while being significantly faster for both training and inference and being better at generalizing to unseen video scenes.