Motion-Aware Feature for Improved Video Anomaly Detection
This work addresses video anomaly detection for surveillance and security applications, offering incremental improvements through enhanced motion features and temporal modeling.
The authors tackled video anomaly detection by proposing a motion-aware feature and a temporal Multiple Instance Learning ranking model, achieving significant performance improvements and outperforming previous approaches by a large margin on the UCF Crime dataset.
Motivated by our observation that motion information is the key to good anomaly detection performance in video, we propose a temporal augmented network to learn a motion-aware feature. This feature alone can achieve competitive performance with previous state-of-the-art methods, and when combined with them, can achieve significant performance improvements. Furthermore, we incorporate temporal context into the Multiple Instance Learning (MIL) ranking model by using an attention block. The learned attention weights can help to differentiate between anomalous and normal video segments better. With the proposed motion-aware feature and the temporal MIL ranking model, we outperform previous approaches by a large margin on both anomaly detection and anomalous action recognition tasks in the UCF Crime dataset.