When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
This provides a new dataset and metric for researchers in video anomaly detection, specifically for traffic scenarios, but is incremental as it builds on existing VAD work.
The paper tackles the lack of large-scale benchmark datasets and effective evaluation metrics for video anomaly detection in egocentric traffic videos by introducing the DoTA dataset with 4,677 videos and a new STAUC metric, showing that STAUC is effective and DoTA is the largest such dataset to date.
Video anomaly detection (VAD) has been extensively studied. However, research on egocentric traffic videos with dynamic scenes lacks large-scale benchmark datasets as well as effective evaluation metrics. This paper proposes traffic anomaly detection with a \textit{when-where-what} pipeline to detect, localize, and recognize anomalous events from egocentric videos. We introduce a new dataset called Detection of Traffic Anomaly (DoTA) containing 4,677 videos with temporal, spatial, and categorical annotations. A new spatial-temporal area under curve (STAUC) evaluation metric is proposed and used with DoTA. State-of-the-art methods are benchmarked for two VAD-related tasks.Experimental results show STAUC is an effective VAD metric. To our knowledge, DoTA is the largest traffic anomaly dataset to-date and is the first supporting traffic anomaly studies across when-where-what perspectives. Our code and dataset can be found in: https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly