计算机科学
对手
可扩展性
利用
保险丝(电气)
传感器融合
模式
人机交互
实时计算
嵌入式系统
人工智能
计算机安全
数据库
社会科学
工程类
社会学
电气工程
作者
Shane J. Rouse,Robert I. Young,Barry D. McGrath
摘要
Recent experience has demonstrated that adversary activities are difficult to distinguish from background activity. In order to see hidden activities, it is proposed that a combination of new sensing modalities and better ways of processing existing modalities is required. We have applied a robust methodology to analyse the strengths and weaknesses of sensor types at detecting and characterising adversary activities. This has revealed both complementary and synergistic relationships between sensor types, supporting the hypothesis that judicious combining of data from multiple sensors will result in a sensing capability significantly greater than that achievable by individual sensors. The challenge to making this capability a reality is to develop and integrate automatic processing techniques to self-cue sensors and fuse their information, whilst avoiding additional burden on the users. To facilitate evolution and wide exploitation of this capability, we are developing an open, scalable architecture in which to integrate the sensors and processing. All of this work is now being taken forward in the UK's PWAS (Persistent Wide Area Surveillance) S2O demonstrator project which is working towards a rapid demonstration of the capability benefits of an integrated multiple sensor system. The immediate goal is to integrate mature equipment into a demonstrator system, as a test-bed for current and developing cueing/fusion processing algorithms. The near-term goal is to evolve the capability through technology updates which exploit new sensors and improved sensor processing.
科研通智能强力驱动
Strongly Powered by AbleSci AI