Online learning of contexts for detecting suspicious behaviors in surveillance videos

作者：

Highlights：

• The context model allows to detect suspicious behaviors on surveillance videos.

• Contextual information to detect suspicious behaviors before criminal attack occur

• Capacity to start up the system operation with a reduced training dataset

• Performance improvements by using incremental learning during the online operation

摘要

•The context model allows to detect suspicious behaviors on surveillance videos.•Contextual information to detect suspicious behaviors before criminal attack occur•Capacity to start up the system operation with a reduced training dataset•Performance improvements by using incremental learning during the online operation

论文关键词：Incremental learning,Online learning,Context,Suspicious behavior,Surveillance

论文评审过程：Received 8 June 2017, Revised 2 January 2018, Accepted 22 July 2019, Available online 26 July 2019, Version of Record 15 August 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.07.006