Surveillance scene representation and trajectory abnormality detection using aggregation of multiple concepts

作者：

Highlights：

• An expert sysytem for monitoring surveillance environment is proposed.

• A graph-based knowledge accusation tool is used to learn multiple features of target.

• Fuzzy aggregation methods are applied to combine multiple features of target.

• A suitable reweighting method is proposed to reduce missed alarm.

摘要

•An expert sysytem for monitoring surveillance environment is proposed.•A graph-based knowledge accusation tool is used to learn multiple features of target.•Fuzzy aggregation methods are applied to combine multiple features of target.•A suitable reweighting method is proposed to reduce missed alarm.

论文关键词：Visual surveillance,Trajectory analysis,Trajectory abnormalities detection,Multi parameter fusion,Aggregation of concepts

论文评审过程：Received 14 October 2017, Revised 17 January 2018, Accepted 8 February 2018, Available online 9 February 2018, Version of Record 15 February 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.02.013