Reasonable Anomaly Detection in Long Sequences

TL;DR

This paper introduces a novel approach for video anomaly detection by modeling long-term motion patterns with a Stacked State Machine, improving detection accuracy over existing short-term methods.

Contribution

The paper proposes a new long-sequence representation method using a Stacked State Machine to better capture temporal dependencies for anomaly detection.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively models long-term motion dependencies

Demonstrates significant improvement in anomaly detection accuracy

Abstract

Video anomaly detection is a challenging task due to the lack in approaches for representing samples. The visual representations of most existing approaches are limited by short-term sequences of observations which cannot provide enough clues for achieving reasonable detections. In this paper, we propose to completely represent the motion patterns of objects by learning from long-term sequences. Firstly, a Stacked State Machine (SSM) model is proposed to represent the temporal dependencies which are consistent across long-range observations. Then SSM model functions in predicting future states based on past ones, the divergence between the predictions with inherent normal patterns and observed ones determines anomalies which violate normal motion patterns. Extensive experiments are carried out to evaluate the proposed approach on the dataset and existing ones. Improvements over state-of-the-art methods can be observed. Our code is available at https://github.com/AllenYLJiang/Anomaly-Detection-in-Sequences.