A Survey of Single-Scene Video Anomaly Detection

This article summarizes research trends on the topic of anomaly detection in video feeds of a single scene. We discuss the various problem formulations, publicly available datasets and evaluation criteria. We categorize and situate past research into an intuitive taxonomy and provide a comprehensive comparison of the accuracy of many algorithms on standard test sets. Finally, we also provide best practices and suggest some possible directions for future research.

1 Introduction

Video anomaly detection is the task of localizing anomalies in space and/or time in a video, where anomalies are simply activities that are out of the ordinary. Anomalies are also referred to as abnormalities, novelties, and outliers among other similar terms. Examples range from unattended bags at airports, to people falling down, to a person loitering outside a building. We follow the definition provided in [1],