Survey on video anomaly detection in dynamic scenes with moving cameras

TL;DR

This survey comprehensively reviews moving camera video anomaly detection (MC-VAD), covering datasets, approaches, challenges, and future directions across various application domains and environments.

Contribution

It is the first extensive survey on MC-VAD, analyzing existing methods, datasets, challenges, and proposing future research directions in this emerging field.

Findings

Compiled 25 datasets across four environments.

Categorized six tasks and five approach types.

Identified key challenges and future research directions.

Abstract

The increasing popularity of compact and inexpensive cameras, e.g.~dash cameras, body cameras, and cameras equipped on robots, has sparked a growing interest in detecting anomalies within dynamic scenes recorded by moving cameras. However, existing reviews primarily concentrate on Video Anomaly Detection (VAD) methods assuming static cameras. The VAD literature with moving cameras remains fragmented, lacking comprehensive reviews to date. To address this gap, we endeavor to present the first comprehensive survey on Moving Camera Video Anomaly Detection (MC-VAD). We delve into the research papers related to MC-VAD, critically assessing their limitations and highlighting associated challenges. Our exploration encompasses three application domains: security, urban transportation, and marine environments, which in turn cover six specific tasks. We compile an extensive list of 25 publicly-available datasets spanning four distinct environments: underwater, water surface, ground, and aerial. We summarize the types of anomalies these datasets correspond to or contain, and present five main categories of approaches for detecting such anomalies. Lastly, we identify future research directions and discuss novel contributions that could advance the field of MC-VAD. With this survey, we aim to offer a valuable reference for researchers and practitioners striving to develop and advance state-of-the-art MC-VAD methods.