FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation

TL;DR

FastAno introduces a novel training-only patch transformation method that enhances normal feature learning and enables rapid anomaly detection in videos, outperforming previous methods in speed while maintaining competitive accuracy.

Contribution

The paper proposes spatial rotation and temporal mixing transformations applied during training to improve anomaly detection speed and effectiveness without relying on computationally expensive optical flow networks.

Findings

Achieved state-of-the-art speed in anomaly detection.

Maintained competitive accuracy on benchmark datasets.

Eliminated the need for pre-trained optical flow networks.

Abstract

Video anomaly detection has gained significant attention due to the increasing requirements of automatic monitoring for surveillance videos. Especially, the prediction based approach is one of the most studied methods to detect anomalies by predicting frames that include abnormal events in the test set after learning with the normal frames of the training set. However, a lot of prediction networks are computationally expensive owing to the use of pre-trained optical flow networks, or fail to detect abnormal situations because of their strong generative ability to predict even the anomalies. To address these shortcomings, we propose spatial rotation transformation (SRT) and temporal mixing transformation (TMT) to generate irregular patch cuboids within normal frame cuboids in order to enhance the learning of normal features. Additionally, the proposed patch transformation is used only during the training phase, allowing our model to detect abnormal frames at fast speed during inference. Our model is evaluated on three anomaly detection benchmarks, achieving competitive accuracy and surpassing all the previous works in terms of speed.