概述了信息融合的发展历程与信息融合模型分类,重点分析了美国国防部实验室联合理事会(JDL)数据融合过程模型的演变过程及其各阶段特点.最后,给出了信息融合领域的当前技术发展动态.

分布式信息融合与网络中心战密不可分,网络中心战的概念与内涵对分布式信息融合的概念与实现起着主导性作用.首先,概述了网络中心战的概念、特征、价值链、自组织和自同步的内涵;然后,分析了网络中心战对分布式信息融合的架构、算法和应用等需求;最后,给出了分布式信息融合面临的5方面挑战性问题.

针对目标综合识别系统中如何实现系统与人的紧密结合和有效协作的技术难题,探讨了人参与和主导的信息融合技术的主要特征,阐述了人所承担的重要作用和人在环中的信息融合实现方式,提出了一种目标综合识别模型,并详细设计了该人机协作模型中的预处理、数据关联、证据综合、融合推理、识别判定等子模型;仿真验证结果表明,该模型可行有效,能够充分结合人的认知思维与机器高速精确计算的优势,为解决相关实际问题提供了一种可行的技术途径。

在未来海军一体化联合作战的背景下,海战场作战效能越来越依赖于作战资源的整体效能.根据任务对资源的能力需求和作战资源的能力匹配以及资源约束条件,建立合同作战资源的多目标规划模型.基于模糊逻辑理论量化决策者的决策偏好信息,提出了一种基于模糊偏好的多目标量子行为粒子群优化(FPMOQPSO)算法.仿真结果表明,基于FPMOQPSO算法的作战资源规划方案更具针对性,能够减轻决策者的决策负担.

A system architecture for assistant operation decision-making system of command and control system is designed based on the idea of Service-Oriented Architecture ( SOA) .Then the key technologies for the service-oriented,assistant operation decision-making are analyzed,including five aspects as the serviced description of assistant operation decision making course ,service running management ,assistant operation calculation modeling ,cooperative operation mission planning and real-time surveillance of combat process. This purpose is to supply a technical reference for developing a command and control system with aided intelligent decision-making in the future .

Visual saliency maps of the source images are extracted with various image features.A novel fusion rule for the low-frequency subbands of multi-scale image fusion algorithms is proposed,and a new multi-scale image fusion method is developed based on the visual saliency maps.trous wavelet is integrated with Nonsubsampled Contourlet Transform,and is applied to the experiment of multisensor and multi-focus image fusion.It is demonstrated that the proposed approach yields better results both in visual inspection and objective evaluation than the methods choosing low frequency coefficients based on average or neural network.

描述了信息融合理论与技术当前研究动态,提出了第三代信息融合概念、模型、特征和功能模式,强调了人在感知观测—判断—决策—行动(OODA)环中的主导作用,为情报战博弈和按我方意图塑造战场态势以及先敌感知提供理论依据.最后介绍了当前信息融合6个挑战性问题和信息融合学科中的一些奥秘.

The target track quality classification standard in U.S.military Link-16 terminal unit,joint tactical information distribution system(JTIDS) is analyzed.Some concepts about the track quality classification system based on the moving target state information are elaborated,and mathematical models of the multi-dimensional error radius are constructed based on the degree of confidence and the ordinal sample clustering.Then,the constructing method for moving target track quality classification system,procedure and application cases are given.The theoretical and methodological supports for constructing the track quality system of air,maritime and ground moving target according with the equipment system are provided.

With the knowledge that the locally maximum of the dim target gray value usually shows a sudden change of the spectrum in frequency domain,a two-stage infrared dim target enhancement approach based on spectral analysis and image fusion is proposed.The algorithm extractes the spectral residual according to the spectral difference between the dim target and the image background,constructed the saliency map of the potential targets,and applies different fusion rules to potential targets and background respectively with the information redundancy of continuous frames to obtain the fused image.Experimental results showe that the method can enhance the size and the total energy of the infrared dim target effectively and efficiently.

An image fusion method based on nonsubsampled contourlet transform(NSCT)is presented,which uses the nonsubsampled pyramids(NSP)and the nonsubsampled directional filter banks(NSDFBs)to decompose the source images in a multi-scale and multi-direction way.Like the contourlet transform method,the presented method can obtain multi-scale and multi-direction images with good multi-resolutions,and it is also shift-invariant.In the fusion process,an improved consistency check strategy is used.The high frequency coefficients are checked not only in their own level but also in all high frequency levels.The experimental results show that the presented fusion method is effective,and it can obtain better fused images than such methods as Laplacian pyramid transform,wavelet transform and contourlet transform with respect to several indicators.

<正>内容简介:面向工业部门应用领域,系统地阐述了信息融合的概念、结构和主要方法等。在跟踪国际技术前沿的同时,归纳和总结了该领域几十年来的研究成果、应用效果和经验。全书包括10个章节:信息融合基础概念与内涵;信息融合系统结构/模型;信息源空间配准方法与技术;多传感器多目标探测与跟踪;态势与

Multi-sensor image fusion has attracted much attention recently. Although it is relatively simple to obtain a fused image, evaluating the performance of fusion algorithms is much harder in practice. This paper presents a novel non-reference objective quality metric for night vision image fusion. The metric takes human perception and the imaging characteristics of the infrared and visible images into account, divides the source images into different local regions, and the quality of fused image is evaluated by regional information similarity, instead of computed pixel by pixel as traditional methods. Experimental results show that this metric is consistent with human visual inspection and can be applied to compare image fusion schemes that are not performed at the same level.

The occurrence causes and features of diversity information are described by fusion structures.The concept and the connotation of flexible fusion of multi-class diversity information are explained.Effects of the communication delay and the process noise on the the fusion performances are analyzed.Finally,the selection scheme for fusion structures under conditions of different communication delay and the process noise is proposed.The fusion methods for diversity information with different characteristics are provided.Finally,differences between the flexible fusion and the traditional fusion are analyzed.

Aimed at solving problems of recommended and revised data fusion model of Joint Directors′ Laboratories(JDL) 2004,the battlefield awareness is divided into two parts: resource management(RM) and information fusion(IF).The relations of concepts,functions and multi-level control between RM and IF are described,and a functional structure of the battlefield awareness system is established.Dasarathy data fusion input/output model is illustrated from the aspects of RM and IF.Finally,the guidance role of the model in the domain of battlefield awareness is given.

Based on the region partition and association of source images,two regional features of source images are defined according to the imaging characteristics of infrared and visible images and the requirements of fusion tasks.A regional similarity assessment index with the regional features and the information entropy and mutual information of fused images and source images is constructed.A novel non-reference quality evaluation metric for infrared and visible image fusion is proposed.Experimental results show that this metric fits the results of human visual inspection better than the recent state of the art image fusion evaluation metrics.

The concept of Context and its function in the process that the human recognizes the world are described, Context-sensitive period loop is established, the effect of Context in the process of knowledge acquirement is introduced; the division of human cognition phase and the effect of Context in every phase are described. The specific connotation of Context and the effect exerted by Context in the phases of information fusion, which correspond the phases of human cognition, are described emphatically.

Rao-Blackwellised Particle Filtering(RBPF) is a class of particle filter.A particular nonlinear radar target tracking problem is analyzed in detail,this kind of problem is often dealt with linearization and it is failed when correlation between measurement noise is too big.In this simulation test,multi-weight of RBPF is discussed and a doable way is proposed,the performance of RBPF under much correlation of noise is analyzed,relative estimate error of RBPF is also discussed when time processes.

The optimization of an observer trajectory when the observer tracks a constant acceleration target is taken into account.First,optimal control theory is applied to establish the optimal trajectory model of an observer.Second,at the global range accuracy criterion,necessary conditions for the optimal observer course are resolved by analytical means.Finally,the influences of speed of the observer,acceleration of targets,relative target initialization range,and target course on the optimal observer trajectory are discussed by simulation.Simulation results show that the optimal observer trajectory is almost smooth when near targets approach the observer at small acceleration and the observer should maneuver at high speed along the optimal trajectory for the sake of tracking constant acceleration targets accurately.

The concepts of Battlefield Situation and Situation Assessment are presented,with illumination of the level division of Battlefield Situation and the relation between the level division and the three level COP of USA military,focusing on the historical evolution of concepts of Battlefield Situation and Situation Assessment.Our work is helpful for clarifying some confusion in concepts and congnition in the field of situation assessment,and serves some basis for further investigations.