Zhian Liu, Yongwei Nie, Chengjiang Long, Qing Zhang, Guiqing Li
In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors. More importantly, conditioned on the reconstructed flows, we then employ a Conditional Variational Autoencoder (CVAE), which captures the high correlation between video frame and optical flow, to predict the next frame given several previous frames. By CVAE, the quality of flow reconstruction essentially influences that of frame prediction. Therefore, poorly reconstructed optical flows of abnormal events further deteriorate the quality of the final predicted future frame, making the anomalies more detectable. Experimental results demonstrate the effectiveness of the proposed method. Code is available at \href{https://github.com/LiUzHiAn/hf2vad}{https://github.com/LiUzHiAn/hf2vad}.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Anomaly Detection | Ped2 | AUC | 0.993 | HF2-VAD |
| Anomaly Detection | ShanghaiTech Campus | AUC | 76.2 | HF2-VAD |
| 3D Anomaly Detection | Ped2 | AUC | 0.993 | HF2-VAD |
| 3D Anomaly Detection | ShanghaiTech Campus | AUC | 76.2 | HF2-VAD |
| Video Anomaly Detection | Ped2 | AUC | 0.993 | HF2-VAD |
| Video Anomaly Detection | ShanghaiTech Campus | AUC | 76.2 | HF2-VAD |