# What goes around comes around: Cycle-Consistency-based Short-Term Motion Prediction for Anomaly Detection using Generative Adversarial Networks

## TL;DR

This paper explores GAN-based methods for anomaly detection in surveillance videos, emphasizing cycle-consistency and short-term motion prediction to improve detection accuracy in static camera setups.

## Contribution

It introduces a cycle-consistency approach for short-term motion prediction using GANs, enhancing anomaly detection performance in surveillance scenarios.

## Key findings

- Up to 2.4% performance improvement with morphological operations.
- Reduced anomaly detection error by approximately 42.8%.
- Evaluated influence of optical flow and network configurations.

## Abstract

Anomaly detection plays in many fields of research, along with the strongly related task of outlier detection, a very important role. Especially within the context of the automated analysis of video material recorded by surveillance cameras, abnormal situations can be of very different nature. For this purpose this work investigates Generative-Adversarial-Network-based methods (GAN) for anomaly detection related to surveillance applications. The focus is on the usage of static camera setups, since this kind of camera is one of the most often used and belongs to the lower price segment. In order to address this task, multiple subtasks are evaluated, including the influence of existing optical flow methods for the incorporation of short-term temporal information, different forms of network setups and losses for GANs, and the use of morphological operations for further performance improvement. With these extension we achieved up to 2.4% better results. Furthermore, the final method reduced the anomaly detection error for GAN-based methods by about 42.8%.