基于社区安全的人群甄别视频预警研究  

Research on Crowd Screening Video Warning System for Community Safety

作　　者：文贵华[1] 李辉辉[1] 李丹扬 江丽君[1] 郇二洋 

机构地区：[1]华南理工大学计算机科学与工程学院,广东广州510640

出　　处：《华南理工大学学报（社会科学版）》2016年第4期79-84,共6页Journal of South China University of Technology(Social Science Edition)

基　　金：广东省省级科技计划项目(2014A010103009;2015A020217002);国家自然科学基金项目(60973083;61273363)

摘　　要：视频监控系统已在社区、火车站、机场、地铁等公共场所安装应用,但主要依靠人工观察监控视频,发现人群甄别,工作强度大,刑侦能力要求高,容易误报和漏报。采用大数据和人工智能技术来实现监控视频中的人群甄别身份及其微表情识别,进而对可疑人群发出安全预警,其意义在于提高社区的安全程度,促进视频监控产业的发展,提升了系统的实用性,不会引起可疑人群的警觉。Video surveillance systems have been applied to the community, railway station, airport, subway and the other public places, where the crowd screening is now finished mainly through manually observing surveillance video. In such case, the larger working intensity and nice ability for criminal investigation are required, while the false positives and negative recognition easly happen. This paper applies the big data and artificial intelligence tech- nologies to perform crowd screening and micro expression recognition based on surveillance video, and then issues the safety warning for risk crowd. It has the significant value in improving the community safety degree, enhancing the video surveillance industry, and enhancing the practicability due to without interfering the suspect.

关 键 词：社区安全 人群甄别 微表情识别 视频监控 

分 类 号：X924[环境科学与工程—安全科学]