Abnormal Event Detection in Videos using Spatiotemporal Autoencoder

TL;DR

This paper introduces a spatiotemporal autoencoder architecture for efficient anomaly detection in videos, capable of real-time processing and effective in crowded scenes, with performance comparable to state-of-the-art methods.

Contribution

The paper proposes a novel unsupervised spatiotemporal autoencoder architecture specifically designed for anomaly detection in videos, including crowded scenes.

Findings

Achieves detection accuracy comparable to state-of-the-art methods.

Operates at speeds up to 140 frames per second.

Effective in crowded scene scenarios.

Abstract

We present an efficient method for detecting anomalies in videos. Recent applications of convolutional neural networks have shown promises of convolutional layers for object detection and recognition, especially in images. However, convolutional neural networks are supervised and require labels as learning signals. We propose a spatiotemporal architecture for anomaly detection in videos including crowded scenes. Our architecture includes two main components, one for spatial feature representation, and one for learning the temporal evolution of the spatial features. Experimental results on Avenue, Subway and UCSD benchmarks confirm that the detection accuracy of our method is comparable to state-of-the-art methods at a considerable speed of up to 140 fps.