As an important part in the security and protection system of cities, smart monitoring cameras which are equipped with intelligent video analytics ability can monitor in different scenes and pre-alarm abnormal behaviors or events. Nevertheless, with the growing number of smart monitoring cameras, the challenges to analytics, storage and retrieval of massive surveillance video data need to be solved in the big data era. This paper proposes an intelligent processing method which makes full use of smart cameras to big surveillance video data. The method consists of three parts: the intelligent pre-alarming for abnormal events, smart storage for surveillance video and rapid retrieval for evidence videos, which aim to improve the utilization efficiency of surveillance video data. Experimental results prove that the proposed approach can reliably pre-alarm abnormal events, efficiently reduce storage space of recorded video and significantly improve the evidence video retrieval rates associated with specific suspects.%视频监控是安防的重要组成部分,智能监控摄像头以其丰富的异常行为识别功能,极大地增强了监控场所的安全.随着部署的智能摄像头日渐增多以及视频监控网规模的不断扩大,海量的视频数据给存储、检索及分析带来了巨大挑战.该文提出智能摄像头异常报警事件驱动的监控视频大数据智能处理方法,具体包括:多点关联分析的异常事件自动预警、事件驱动的监控视频选择性存储以及异常行为事件约束的关联检索,以期提高大数据时代监控视频数据的深度利用效率.实践案例证实,所提方法能够实现异常事件的可信预警,录像视频选择性的高效保存和破案线索的快速发现.
展开▼
