A Discriminative Framework for Anomaly Detection in Large Videos

Abstract

We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach of learning high-dimensional models and finding low-probability events. These algorithms are sensitive to the order in which anomalies appear and require either training data or early context assumptions that do not hold for longer, more complex videos. By defining anomalies as examples that can be distinguished from other examples in the same video, our definition inspires a shift in approaches from classical density estimation to simple discriminative learning. Our contributions include a novel framework for anomaly detection that is (1) independent of temporal ordering of anomalies, and (2) unsupervised, requiring no separate training sequences. We show that our algorithm can achieve state-of-the-art results even when we adjust the setting by removing training sequences from standard datasets.

arXiv comment14 pages without references, 16 pages with. 7 figures. Accepted to ECCV 2016

Cited by in corpus (4)

• Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
• Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
• Detecting abnormal events in video using Narrowed Normality Clusters
• Ignoring Distractors in the Absence of Labels: Optimal Linear Projection to Remove False Positives During Anomaly Detection