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

中文翻译：

---

何时、何地、什么？用于驾驶视频异常检测的新数据集

视频异常检测（VAD）已被广泛研究。然而，对具有动态场景的以自我为中心的交通视频的研究缺乏大规模的基准数据集以及有效的评估指标。本文提出了使用 \textit{when-where-what} 管道检测、定位和识别以自我为中心的视频中的异常事件的交通异常检测。我们引入了一个名为检测交通异常 (DoTA) 的新数据集，其中包含 4,677 个带有时间、空间和分类注释的视频。提出了一种新的曲线下时空面积 (STAUC) 评估指标并与 DoTA 一起使用。最先进的方法针对两个 VAD 相关任务进行了基准测试。实验结果表明 STAUC 是一种有效的 VAD 指标。据我们所知，DoTA 是迄今为止最大的流量异常数据集，并且是第一个支持跨时间、地点、内容视角的流量异常研究。我们的代码和数据集可以在：https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly