Robust infrared target tracking using discriminative and generative approaches

The process of designing an efficient tracker for thermal infrared imagery is one of the most challenging tasks in computer vision. Although a lot of advancement has been achieved in RGB videos over the decades, textureless and colorless properties of objects in thermal imagery pose hard constraints in the design of an efficient tracker. Tracking of an object using a single feature or a technique often fails to achieve greater accuracy. Here, we propose an effective method to track an object in infrared imagery based on a combination of discriminative and generative approaches. The discriminative technique makes use of two complementary methods such as kernelized correlation filter with spatial feature and AdaBoost classifier with pixel intesity features to operate in parallel. After obtaining optimized locations through discriminative approaches, the generative technique is applied to determine the best target location using a linear search method. Unlike the baseline algorithms, the proposed method estimates the scale of the target by Lucas-Kanade homography estimation. To evaluate the proposed method, extensive experiments are conducted on 17 challenging infrared image sequences obtained from LTIR dataset and a significant improvement of mean distance precision and mean overlap precision is accomplished as compared with the existing trackers. Further, a quantitative and qualitative assessment of the proposed approach with the state-of-the-art trackers is illustrated to clearly demonstrate an overall increase in performance.     

面向框架语义分析的目标词自动识别方法

提出了一种基于监督学习的目标词自动识别方法,分析并检验了多种区分目标词、框架元素和非实义词的分类特征,并在此基础上,联合使用监督学习与规则匹配方法,形成了兼顾扩展性和精确性的目标词识别系统。在FrameNet语料集的实验结果显示,融合方法的目标词识别获得了3.86%的性能提升。     

光电探测器组件光纤耦合移位特性分析

光电探测器组件响应度下降会造成光纤陀螺输出异常,响应度下降的主要原因为光纤耦合移位,分析光纤耦合移位的原因并采取有效措施可提高探测器组件的使用可靠性。通过对探测器尾纤出射高斯光斑在探测器管芯端面数学积分,计算出光纤耦合效率系数与光纤耦合间距及光纤偏转角度的关系,计算结果与实际封装探测器组件指标一致。根据计算结果,从光纤移位、探测器管芯移位和管壳形变三个方面分析了耦合移位的影响因素,提出避免探测器使用中发生耦合移位的措施,并通过试验验证了耦合焊接缺陷会造成探测器试验后响应度下降,采取耦合对准控制措施后封装的探测器试验后响应度保持稳定。     

面向内容的立体视频帧重要性区分模型研究

异构网络引起的视频传输失真是影响视频终端感知质量的重要因素,通常只能在解码端进行评估和补偿。因此在编码端建立一个面向内容的立体视频传输失真模型,考虑错误隐藏和错误扩散两种失真,通过近似估计视频中各帧对终端质量的贡献度,从而实现每帧重要性的区分。新模型综合考虑了视频帧编码位置以及表征内容的编码模式、运动矢量、视差矢量等关键信息,可以作为视频在异构网络中传输策略的重要依据。     

干扰泄漏最小的多小区MIMO干扰对齐算法

在3小区多输入多输出(MIMO)干扰对齐通信系统中, 提出一种基于系统总干扰泄漏最小的预编码矩阵组的选择算法.首先求出系统中所有变换矩阵,并基于干扰泄漏最小准则从中寻找出最优的变换矩阵;再依据干扰对齐的最大自由度选出一半的特征向量组成预编码矩阵.仿真结果表明:与现有干扰对齐预编码矩阵的设计方案相比,文中提出的算法在系统和速率性能上有明显的改善,而且该算法在统计信道状态信息下同样具有优势.     

三维战场态势显示标绘技术

 为提高三维战场态势显示标绘的图形效率和人机交互性,在总结分析战场态势信息基本理论概念的基础上,通过对显示与标绘两方面的军事需求和OSG/Qt 结合使用的软件架构模式进行分析,提出了程序框架的线程模式优化方法和基于帧缓存对象的离屏纹理烘焙技术的军标符号显示生成算法.设计和实现了三维战场态势显示标绘软件模块,并对模块进行了多种实现方法的比较测试,检查验证了相关技术方案和关键技术对于提高系统绘制效率和人机交互的有效性.     

基于粗对准与精对准信号分开探测的对准系统

提出了一种用于光刻装置的对准系统。该对准系统所用的标记包含多个相位子光栅。其中,标记±1级衍射光的光强信息用于产生粗对准信号。在粗对准信号上,通过峰值检测和信号拟合获得最大峰值点,该峰值点即为粗对准位置。同时,在另一光路中,精细子光栅的±1级衍射光的光强信息用于产生精对准信号。利用余弦或正弦曲线对该精对准信号进行拟合,得到一系列的波峰点。距离粗对准位置最近的波峰点即为精对准位置。当精细子光栅的周期足够小时,该对准系统可获得5nm级的重复精度。     

Alignment techniques for DRAGON-Ⅰ LIA

DRAGON-Ⅰ designed and manufactured by CAEP is a linear induction accelerator which can produce a 20 MeV-3 kA-60 us electron beam. The high performance required for the machine is determined by the beam quality and thus is greatly dependent on the accelerator alignment. In order to reduce the chromatic effect of the beam, the stretched wire technique has been developed to measure magnetic axes of the cells precisely, and the dipole steering magnets have been equipped into each cell to correct its magnetic axis misalignment. Finally, the laser tracker has been used to examine the installation error of the accelerator. In this paper, different alignment techniques and the primary results are presented and discussed.     

钢管混凝土刚构式柔性系杆拱桥的施工控制

针对钢管混凝土刚构式柔性系杆拱桥的特点,提出了动态有限元的概念和以仿真分析为基础,以准确控制系杆索力和墩顶位移为主要控制目标的施工监控总思路,给出了钢管混凝土拱桥拱肋混凝土收缩、徐变计算的系数取值范围及对温度影响处理的技巧．实测结果和实桥控制效果表明了本文方法的有效性．     

D-S理论在开放识别框架下的推广

针对无法获取完备识别框架的应用背景,把证据模型建立在一个随着证据组合而不断完善的开放识别框架上,提出一种推广的Dempster-Shafer(D-S)证据理论--开放框架D-S理论(OFDST).基于DFDST定义证据的支持函数与反对函数,对证据的信任函数模型进行全新诠释,揭示Dempster组合规则的线性实质.最后通过一个实例验证了该理论的合理性与有效性.