论文标题
何时，哪里，什么？一个用于驱动视频异常检测的新数据集
When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
论文作者
论文摘要
视频异常检测（VAD）已被广泛研究。但是，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。本文建议使用\ textit {wher-where-what-what-what}管道检测，本地化和识别以自我为中心视频的异常事件的流量异常检测。我们介绍了一个新的数据集，称为流量异常检测（DOTA），其中包含4,677个带有时间，空间和分类注释的视频。提出了一个新的时空区域（Stauc）评估度量标准，并与DOTA一起使用。针对两个与VAD相关的任务进行了最新方法。经验结果表明，Stauc是有效的VAD度量。据我们所知，DOTA是迄今为止最大的流量异常数据集，并且是跨越一些观点的首次支持交通异常研究。我们的代码和数据集可在以下方式找到：https：//github.com/moonblvd/detection-of-traffic-anomaly
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
