When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos

Abstract

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

23 pages, 11 figures, 6 tables

References in corpus (4)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• The Kinetics Human Action Video Dataset
• Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks

Cited by in corpus (5)

• Explanations in Autonomous Driving: A Survey
• BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation
• STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction
• Coupling Intent and Action for Pedestrian Crossing Behavior Prediction
• Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies