多传感器目标识别的图像数据融合技术研究

军事和空间技术的要求促进了微光技术的发展。微光图像实时处理技术是夜技术今后发展的重要方向，本文针对微光图像与脉冲激光测距仪的数据信息实时融合与显示的方法及其实现进行了研究。给出了系统框图及工作原理，为实现探测识别、跟踪的实时性、智能化和微型化，从而为研制新一代战术侦察与火控系统提供了具体有效的技术基础。     

3D Motion Estimation and Motion Fusion by Affine Region Matching

In this paper,a new method is presented for 3D motion estimation by image region correspondences using stereo cameras.Under the weak perspectivity assumption.we first employ the moment tensor theory (Cyganski and Orr^[11]) to compute the monocular affine transformations relating images taken by the same camera at different time instants and the binocular affine transformations relating images taken by different cameras at the same time instant.We then show that 3D motion can be recovered from these 2D transformations.A space-time fusion strategy is proposed to aim at robust results.No knowledge of point correspondences if requred in the above processes and the computations involved are linear.To find corresponding image regions,new affine invariants,which show stronger invariance,are derived in term of tensor contraction theory.Experiments on real motion images are conducted to verify the proposed method.     

The Role of Plasma Science in Graduate Education

In many academic institutions plasma science is currently viewed as a basic physics discipline encompassing a broad range of applications including fusion, astrophysics, space physics, low temperature plasma physics for the semiconductor industry, and environmental remediation of nuclear and chemical waste. Although the applications are broad, it is accurate to state that the major development of the field has been driven by the scientific needs of a single program, fusion. As such, plasma science and engineering has played an important role in graduate education since the early days of the fusion program, late 50's, early 60's.     

Can Fusion and Fission Breeding Help Civilization Survive?

As apparent from the title, this author feels that civilization faces a real threat, one which will become obvious and serious within the lifetimes of many readers of this article. This threat is not global warming, but lack of affordable energy. We take for granted turning on a light, or adjusting our thermostats in winter or summer, or filling our cars gas tank; and lose sight of the fact that there are huge and complicated industrial systems which make this possible. But as we run out of petroleum and natural gas, and worry about the environmental and climatic effects of burning coal on the required scale, how can this continue? This paper makes the case that breeding nuclear fuel, by both fusion and fission, is the only way our civilization as we know it, can continue beyond the next half century or so.     

一种基于Hough变换的声呐对目标航迹检测算法研究

为提高声呐对目标航迹的检测性能,从单部声呐时间融合的角度出发,提出了一种基于Hough变换的声呐信号检测算法。该算法把航迹上的观测点变换为参数空间的对应曲线,充分利用一段时间内的目标观测数据,在低信噪比下也能从背景噪声中提取目标的航迹特征,提高了声呐的检测概率,且对部分信息和数据的缺失不敏感。仿真试验证明了该算法的有效性。     

The Year 2015 Fusion Power Conversations

Assuming significant technical success in the ITER project by the year 2015, it is likely that governments will want to develop a more comprehensive plan for DT tokamak fusion power commercialization. To provide a glimpse into many of the related issues, we construct conversations between the director of the U.S. fusion program and three specialists key to commercial fusion success: an environment and safety regulator, an environmentalist, and an electric generation investor. The insights from these imagined conversations will hopefully be of value as tokamak fusion power proponents plan beyond ITER.     

Merging uncertain information with semantic heterogeneity in XML

Semistructured information can be merged in a logic-based framework [6, 7]. This framework has been extended to deal with uncertainty, in the form of probability values, degrees of beliefs, or necessity measures, associated with leaves (i.e. textentries) in the XML documents [3]. In this paper we further extend this approach to modelling and merging uncertain information that is defined at different levels of granularity of XML textentries, and to modelling and reasoning with XML documents that contain semantically heterogeneous uncertain information on more complex elements in XML subtrees. We present the formal definitions for modelling, propagating and merging semantically heterogeneous uncertain information and explain how they can be handled using logic-based fusion techniques. Anthony Hunter received a B.Sc. (1984) from the University of Bristol and an M.Sc. (1987) and Ph.D. (1992) from Imperial College, London. He is currently a reader in the Department of Computer Science at University College London. His main research interests are: Knowledge representation and reasoning, Analysing inconsistency, Argumentation, Default reasoning and Knowledge Fusion. Weiru Liu is a senior lecturer at the School of Computer Science, Queen's University Belfast. She received her B.Sc. and M.Sc. degrees in Computer Science from Jilin University, P.R China, and her Ph.D. degree in Artificial Intelligence from the University of Edinburgh. Her main research interests include reasoning under uncertainty, knowledge representation and reasoning, uncertain knowledge and information fusion, and knowledge discovery in databases. She has published over 50 journal and conference papers in these areas.     

基于多代理技术的传感器管理系统

针对分布式对空监视网中混合式传感器管理结构存在的问题，提出了基于多代理技术的混合式传感器管理结构。该结构较好地克服了混合式管理结构中在融合中心存在的瓶颈问题，通过多个传感器代理、融合中心代理之间的相互协商来实现传感器任务的分配。传感器代理与传感器相结合使传感器的工作模式实现高度的自动化和模块化，便于传感器的灵活组网。     

信息融合的飞机识别方法

以信息融合的理论为基础，利用从可见光图像序列和8-12μm长波红外图像序列中提取的信息对不同种类飞机进行识别。采用矩特征并结合BP神经网络的方法，分别在特征级和决策级两个不同层次上实现了信息融合。实验结果表明，通过信息融合进行飞机识别的准确率可达到90％以上。     

Vote counting measures for ensemble classifiers

Various measures, such as Margin and Bias/Variance, have been proposed with the aim of gaining a better understanding of why Multiple Classifier Systems (MCS) perform as well as they do. While these measures provide different perspectives for MCS analysis, it is not clear how to use them for MCS design. In this paper a different measure based on a spectral representation is proposed for two-class problems. It incorporates terms representing positive and negative correlation of pairs of training patterns with respect to class labels. Experiments employing MLP base classifiers, in which parameters are fixed but systematically varied, demonstrate the sensitivity of the proposed measure to base classifier complexity.