Prior Knowledge Guided Network for Video Anomaly Detection

TL;DR

This paper introduces PKG-Net, a novel video anomaly detection model that leverages prior knowledge and a teacher-student architecture to improve detection accuracy and generalization on unseen data.

Contribution

The paper proposes a prior knowledge guided network with a teacher-student auto-encoder architecture and multi-scale feature knowledge distillation for enhanced video anomaly detection.

Findings

Outperforms recent state-of-the-art methods on three benchmarks.

Effectively combines prediction error and feature inconsistency for anomaly scoring.

Demonstrates improved generalization to unknown anomalies.

Abstract

Video Anomaly Detection (VAD) involves detecting anomalous events in videos, presenting a significant and intricate task within intelligent video surveillance. Existing studies often concentrate solely on features acquired from limited normal data, disregarding the latent prior knowledge present in extensive natural image datasets. To address this constraint, we propose a Prior Knowledge Guided Network(PKG-Net) for the VAD task. First, an auto-encoder network is incorporated into a teacher-student architecture to learn two designated proxy tasks: future frame prediction and teacher network imitation, which can provide better generalization ability on unknown samples. Second, knowledge distillation on proper feature blocks is also proposed to increase the multi-scale detection ability of the model. In addition, prediction error and teacher-student feature inconsistency are combined to evaluate anomaly scores of inference samples more comprehensively. Experimental results on three public benchmarks validate the effectiveness and accuracy of our method, which surpasses recent state-of-the-arts.