Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM

2022/05/18 by Hanh Thi Minh Tran, David W. Hogg, Tran, Hanh Thi Minh +1
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Artificial Immune Systems Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.2205.08812

openalex publication_date 2022/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a novel method for video anomaly detection motivated by an existing architecture for sequence-to-sequence prediction and reconstruction using a spatio-temporal convolutional Long Short-Term Memory (convLSTM). As in previous work on anomaly detection, anomalies arise as spatially localised failures in reconstruction or prediction. In experiments with five benchmark datasets, we show that using prediction gives superior performance to using reconstruction. We also compare performance with different length input/output sequences. Overall, our results using prediction are comparable with the state of the art on the benchmark datasets.

Related

• Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks
• Exploiting Spatial-temporal Correlations for Video Anomaly Detection
• Abnormal Event Detection in Videos using Spatiotemporal Autoencoder
• Reasonable Anomaly Detection in Long Sequences
• Predicting Next Local Appearance for Video Anomaly Detection