关键词: 大数据, 公共安全, 视频监控系统, 视频结构化描述, 数据检索

Abstract:

Video surveillance has become an important tool due to its rich, intuitive and accurate information. However, with the large-scale construction of video surveillance systems all over the world, useful information and clues cannot be found immediately from the huge video data. The problem affects detection efficiency in crime prediction and public security governance. A great variety of public security information systems have been built for management of traffic accidents, and prediction of criminal events and terrorist attacks. However, large redundant construction of systems leads to great waste of IT resource and
information overload. Technologies such as big data, cloud computing and virtualization have been applied in the public security industry to solve these problems. This paper describes a novel architecture for the next generation public security system in which a front-plus-back pattern is used. In the architecture, cloud technologies such as distributed storage and computing, data retrieval of huge and heterogeneous data are introduced. Multiple optimized strategies are proposed to enhance resources utilization and efficiency of tasks.

Key words: big data, date retrieval, public security, video structurized description, video surveillance system