Hybrid Video Anomaly Detection for Anomalous Scenarios in Autonomous Driving
This work addresses the challenge of detecting rare and critical anomalies in autonomous driving, but it is incremental as it adapts an existing method to a new domain.
The paper tackles the problem of detecting anomalous scenarios in autonomous driving by adapting a surveillance video anomaly detection method to learn normality from a vehicle's ego perspective, resulting in pixel-wise anomaly detections in rare and critical scenarios.
In autonomous driving, the most challenging scenarios can only be detected within their temporal context. Most video anomaly detection approaches focus either on surveillance or traffic accidents, which are only a subfield of autonomous driving. We present HF$^2$-VAD$_{AD}$, a variation of the HF$^2$-VAD surveillance video anomaly detection method for autonomous driving. We learn a representation of normality from a vehicle's ego perspective and evaluate pixel-wise anomaly detections in rare and critical scenarios.