作者
Yu Yao, Mingze Xu, Yuchen Wang, David J Crandall, Ella M Atkins
发表日期
2019/11/3
研讨会论文
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
页码范围
273-280
出版商
IEEE
简介
Recognizing abnormal events such as traffic violations and accidents in natural driving scenes is essential for successful autonomous driving and advanced driver assistance systems. However, most work on video anomaly detection suffers from two crucial drawbacks. First, they assume cameras are fixed and videos have static backgrounds, which is reasonable for surveillance applications but not for vehicle-mounted cameras. Second, they pose the problem as one-class classification, relying on arduously hand-labeled training datasets that limit recognition to anomaly categories that have been explicitly trained. This paper proposes an unsupervised approach for traffic accident detection in first-person (dashboard-mounted camera) videos. Our major novelty is to detect anomalies by predicting the future locations of traffic participants and then monitoring the prediction accuracy and consistency metrics with three …
学术搜索中的文章
Y Yao, M Xu, Y Wang, DJ Crandall, EM Atkins - 2019 IEEE/RSJ International Conference on Intelligent …, 2019