Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks

Abstract

Automating the detection of anomalous events within long video sequences is challenging due to the ambiguity of how such events are defined. We approach the problem by learning generative models that can identify anomalies in videos using limited supervision. We propose end-to-end trainable composite Convolutional Long Short-Term Memory (Conv-LSTM) networks that are able to predict the evolution of a video sequence from a small number of input frames. Regularity scores are derived from the reconstruction errors of a set of predictions with abnormal video sequences yielding lower regularity scores as they diverge further from the actual sequence over time. The models utilize a composite structure and examine the effects of conditioning in learning more meaningful representations. The best model is chosen based on the reconstruction and prediction accuracy. The Conv-LSTM models are evaluated both qualitatively and quantitatively, demonstrating competitive results on anomaly detection datasets. Conv-LSTM units are shown to be an effective tool for modeling and predicting video sequences.

Cited by in corpus (8)

• Deep Learning for Anomaly Detection: A Survey
• When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
• Anomaly Locality in Video Surveillance
• Future Frame Prediction Using Convolutional VRNN for Anomaly Detection
• VizADS-B: Analyzing Sequences of ADS-B Images Using Explainable Convolutional LSTM Encoder-Decoder to Detect Cyber Attacks
• Anomaly Detection using Deep Reconstruction and Forecasting for Autonomous Systems
• Few-shot Scene-adaptive Anomaly Detection
• EvAn: Neuromorphic Event-based Anomaly Detection