期刊
IEEE ACCESS
卷 9, 期 -, 页码 123977-123986出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3109102
关键词
Image reconstruction; Anomaly detection; Computational modeling; Predictive models; Feature extraction; Task analysis; Optical imaging; Anomaly detection; generative adversarial network; self attention
In this study, a prediction-based video anomaly detection approach named TransAnomaly is proposed, which combines U-Net and ViViT to improve anomaly detection performance. By modifying ViViT for video prediction, richer temporal information and more global contexts are captured. Experimental results demonstrate that adding the transformer module enhances anomaly detection performance, and the model outperforms other state-of-the-art prediction-based video anomaly detection methods with proper settings and regularity score calculations.
Video anomaly detection is challenging because abnormal events are unbounded, rare, equivocal, irregular in real scenes. In recent years, transformers have demonstrated powerful modelling abilities for sequence data. Thus, we attempt to apply transformers to video anomaly detection. In this paper, we propose a prediction-based video anomaly detection approach named TransAnomaly. Our model combines the U-Net and the Video Vision Transformer (ViViT) to capture richer temporal information and more global contexts. To make full use of the ViViT for the prediction, we modified the ViViT to make it capable of video prediction. Experiments on benchmark datasets show that the addition of the transformer module improves the anomaly detection performance. In addition, we calculate regularity scores with sliding windows and evaluate the impact of different window sizes and strides. With proper settings, our model outperforms other state-of-the-art prediction-based video anomaly detection approaches. Furthermore, our model can perform anomaly localization by tracking the location of patches with lower regularity scores.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据