信息融合理论的基本方法与进展(Ⅱ)  

Basic methods and progress of information fusion (ⅡⅡ)

作　　者：潘泉[1] 王增福[1] 梁彦[1] 杨峰[1] 刘准钆[1] 

机构地区：[1]西北工业大学自动化学院,陕西西安710072

出　　处：《控制理论与应用》2012年第10期1233-1244,共12页Control Theory & Applications

基　　金：国家自然科学基金资助项目(61135001;61074179;61075029);西北工业大学博士论文创新基金资助项目(cx201014)

摘　　要：在军事技术、自动化、智能化等需求的牵引下,信息融合受到学术界和工业界的广泛关注,近年来取得了诸多新的理论与方法进展,因此有必要予以综述.本文首先分析了信息融合面临的问题与挑战,包括系统融合框架、信息不确定、多模态、高冲突、强相关、网络化以及非线性等;并以此为分类依据,在信息融合模型与系统设计、不确定信息融合、多模态信息融合、高冲突信息融合、相关信息融合及网络化信息融合等方面对近10年来的进展进行了综述.同时,探讨了信息一体化融合处理、以人为中心的信息融合、信息获取与融合的联合优化、复杂多传感器信息融合系统体系结构设计、信息融合系统仿真与性能评估、借助更多的数学理论方法等未来几个可能的研究发展方向.Because of the demands from military technology,automation and intelligence,information fusion has been broadly concerned in academia and industry.Since a number of methods and algorithms have been emerging in recent years,it is necessary to analyze and review their recent developments.We start by analyzing the inherent problems and challenges in information fusion,including fusion architecture,uncertainty of information,multimodal information,conflict information,correlative information,networked information and nonlinearity of information;and then,we review various methods and algorithms developed in the past ten years for implementing the fusion of the above types of information.In addition,several future directions of research are highlighted and described,including the joint processing for information,human-centered information fusion,joint optimization for information gathering and fusion,architecture design for complex multisensor information fusion systems,simulation and performance evaluation for information fusion and the application of more mathematical theories.

关 键 词：信息融合 数据融合 多传感器系统 联合指挥实验室(JDL)模型 

分 类 号：TP202[自动化与计算机技术—检测技术与自动化装置]