Street Scene: A new dataset and evaluation protocol for video anomaly detection

Bharathkumar Ramachandra, Michael Jones; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 2569-2578

Progress in video anomaly detection research is currently slowed by small datasets that lack a wide variety of activities as well as flawed evaluation criteria. This paper aims to help move this research effort forward by introducing a large and varied new dataset called Street Scene, as well as two new evaluation criteria that provide a better estimate of how an algorithm will perform in practice. In addition to the new dataset and evaluation criteria, we present two variations of a novel baseline video anomaly detection algorithm and show they are much more accurate on Street Scene than two well known algorithms from the literature.