Video Anomaly Detection By The Duality Of Normality-Granted Optical Flow
This work addresses the problem of detecting diverse abnormal events in videos for surveillance and security applications, representing an incremental improvement over existing reconstruction and prediction methods.
The paper tackles video anomaly detection by using a duality of normality-granted optical flow to predict normal frames while hindering abnormal ones, achieving impressive performance on standard benchmarks.
Video anomaly detection is a challenging task because of diverse abnormal events. To this task, methods based on reconstruction and prediction are wildly used in recent works, which are built on the assumption that learning on normal data, anomalies cannot be reconstructed or predicated as good as normal patterns, namely the anomaly result with more errors. In this paper, we propose to discriminate anomalies from normal ones by the duality of normality-granted optical flow, which is conducive to predict normal frames but adverse to abnormal frames. The normality-granted optical flow is predicted from a single frame, to keep the motion knowledge focused on normal patterns. Meanwhile, We extend the appearance-motion correspondence scheme from frame reconstruction to prediction, which not only helps to learn the knowledge about object appearances and correlated motion, but also meets the fact that motion is the transformation between appearances. We also introduce a margin loss to enhance the learning of frame prediction. Experiments on standard benchmark datasets demonstrate the impressive performance of our approach.