This paper describes the evolution of our research from video analytics to a global security system with focus on the video surveillance component. Indeed video surveillance has evolved from a commodity security tool up to the most efficient way of tracking perpetrators when terrorism hits our modern urban centers. As number of cameras soars, one could expect the system to leverage the huge amount of data carried through the video streams to provide fast access to video evidences, actionable intelligence for monitoring real-time events and enabling predictive capacities to assist operators in their surveillance tasks. This research explores a hybrid platform for video intelligence capture, automated data extraction, supervised Machine Learning for intelligently assisted urban video surveillance; Extension to other components of a global security system are discussed. Applying Knowledge Management principles in this research helps with deep problem understanding and facilitates the implementation of efficient information and experience sharing decision support systems providing assistance to people on the field as well as in operations centers. The originality of this work is also the creation of "common" human-machine and machine to machine language and a security ontology.
翻译:本文描述了我们从视频分析到全球安全系统研究的演变过程,重点是视频监控部分。事实上,视频监控已经从商品安全工具发展到在恐怖主义袭击现代城市中心时以最有效的方式追踪实施者。随着摄影机的数量猛增,人们可以期望该系统利用通过视频流传送的大量数据,提供视频证据的快速访问,监测实时事件的可操作情报,并使预测能力能够帮助操作者完成监控任务。这项研究探索了视频情报捕捉、自动数据提取、监督机器学习的混合平台,用于智能辅助城市视频监控;讨论了全球安全系统其他组成部分的扩展。在这项研究中应用知识管理原则有助于深刻理解问题,并促进高效的信息和经验共享支持系统的实施,为外地和业务中心的人们提供援助。这项工作的初衷还在于创建“通用”的人类机器和机器,用于机器语言和安全本体学。