Anomaly detection in video with Bayesian nonparametrics

TL;DR

This paper introduces a dynamic Bayesian nonparametric model for detecting anomalies in video data, utilizing novel inference methods and abnormality measures, and demonstrates its effectiveness on synthetic and real datasets.

Contribution

It presents a new dynamic Bayesian nonparametric topic model with inference algorithms and abnormality measures for improved video anomaly detection.

Findings

Outperforms non-dynamic models in anomaly detection accuracy

Effective on both synthetic and real video datasets

Provides batch and online inference methods

Abstract

A novel dynamic Bayesian nonparametric topic model for anomaly detection in video is proposed in this paper. Batch and online Gibbs samplers are developed for inference. The paper introduces a new abnormality measure for decision making. The proposed method is evaluated on both synthetic and real data. The comparison with a non-dynamic model shows the superiority of the proposed dynamic one in terms of the classification performance for anomaly detection.