战场环境下无人车辆战术机动路径规划方法

针对不同类型威胁体存在的战场环境中无人车辆战术机动路径规划问题,提出了一种基于威胁代价地图的粒子群优化（Particle Swarm Optimization,PSO）方法。借助极坐标系中关键点的极角进行路径描述,并使用分段3次Hermite插值方法形成光滑路径,将路径规划问题转化为关键点极角的参数优化问题。针对基本PSO（BPSO）算法存在的早熟收敛和后期迭代效率低的缺陷,借鉴以群集方式生活的物种按照不同任务对种群进行分工的机制,提出了一种基于多任务子群协同的改进粒子群优化（Particle Swarm Optimization based on the Multi—tasking Subpopu—lation Cooperation,PSO-MSC）算法。借助该算法的快速收敛和全局寻优特性实现了最优路径规划。实验结果表明：该算法可以快速有效地实现战场环境下无人车辆的战术机动路径规划,且规划路径安全、平滑。     

基于自适应变异粒子群算法的火力分配方法研究

针对最优火力分配的特点,分析了火力分配优化问题的数学模型,设计了一种求解该类问题的自适应变异粒子群算法（Adaptive Mutation Particle Swarm Optimization, AMPSO）。该算法采用十进制编码方法和基于数值运算的个体更新方法;为平衡算法的局部搜索能力和全局收敛性能,设计了一种关键参数自适应调整方法;为增强种群在进化后期的多样性,提出了一种变异策略。仿真结果表明,所提AMPSO算法具有良好的寻优性能,是优化火力分配的一种有效算法。     

Background dominant colors extraction method based on color image quick fuzzy c-means clustering algorithm

A quick and accurate extraction of dominant colors of background images is the basis of adaptive camouflage design. This paper proposes a Color Image Quick Fuzzy C-Means (CIQFCM) clustering algorithm based on clustering spatial mapping. First, the clustering sample space was mapped from the image pixels to the quantized color space, and several methods were adopted to compress the amount of clustering samples. Then, an improved pedigree clustering algorithm was applied to obtain the initial class centers. Finally, CIQFCM clustering algorithm was used for quick extraction of dominant colors of background image. After theoretical analysis of the effect and efficiency of the CIQFCM algorithm, several experiments were carried out to discuss the selection of proper quantization intervals and to verify the effect and efficiency of the CIQFCM algorithm. The results indicated that the value of quantization intervals should be set to 4, and the proposed algorithm could improve the clustering efficiency while maintaining the clustering effect. In addition, as the image size increased from 128 × 128 to 1024 × 1024, the efficiency improvement of CIQFCM algorithm was increased from 6.44 times to 36.42 times, which demonstrated the significant advantage of CIQFCM algorithm in dominant colors extraction of large-size images.     

Experimental and numerical investigations of interface properties of Ti6Al4V/CP-Ti/Copper composite plate prepared by explosive welding

Explosive welding technique is widely used in many industries. This technique is useful to weld different kinds of metal alloys that are not easily welded by any other welding methods. Interlayer plays an important role to improve the welding quality and control energy loss during the collision process. In this paper, the Ti6Al4V plate was welded with a copper plate in the presence of a commercially pure titanium interlayer. Microstructure details of welded composite plate were observed through optical and scanning electron microscope. Interlayer-base plate interface morphology showed a wavy structure with solid melted regions inside the vortices. Moreover, the energy dispersive spectroscopy analysis in the interlayer-base interface reveals that there are some identified regions of different kinds of chemical equilibrium phases of Cu–Ti, i.e. CuTi, Cu₂Ti, CuTi₂, Cu₄Ti, etc. To study the mechanical properties of composite plates, mechanical tests were conducted, including the tensile test, bending test, shear test and Vickers hardness test. Numerical simulation of explosive welding process was performed with coupled Smooth Particle Hydrodynamic method, Euler and Arbitrary Lagrangian-Eulerian method. The multi-physics process of explosive welding, including detonation, jetting and interface morphology, was observed with simulation. Moreover, simulated plastic strain, temperature and pressure profiles were analysed to understand the welding conditions. Simulated results show that the interlayer base plate interface was created due to the high plastic deformation and localized melting of the parent plates. At the collision point, both alloys behave like fluids, resulting in the formation of a wavy morphology with vortices, which is in good agreement with the experimental results.     

对流层散射无源监视系统最优布局方法

为提高对流层散射无源监视系统对辐射源的定位精度,利用改进粒子群优化算法对分布式监视节点进行最优布局设计。推导了基于电磁波方位到达角定位机制下的几何精度因子。在改进粒子群优化算法中,采用混沌理论初始化所有粒子的初始参数;通过自适应变化的惯性权重和学习因子来提高算法寻优能力;为防止粒子陷入局部最优,利用双子群机制进行寻优,并在两子群之间进行交叉变异操作,以增加粒子的多样性。仿真结果表明:相对于几种常规的布站方式,所提算法能够明显提高监视系统对辐射源的定位精度,运行时间较遍历寻优算法有所减少。     

折反射全景与遥感图像融合的建筑物高程自动提取方法

为了解决三维城市重建中的建筑物高程提取问题,提出一种折反射全景与遥感图像融合的建筑物高度自动提取方法.该方法分为三步,首先进行折反射全景与遥感图像的配准,然后利用配准结果提取折反射全景图像中建筑物的底部和顶部边界,最后基于边界信息,根据折反射全景成像光路跟踪模型计算建筑物的高度,整个提取过程自动完成.实验结果证明该方法...     

基于梯度直方图的交叉点检测方法

提出基于梯度直方图的交叉点检测方法:统计像素点邻域梯度信息生成特征描述子,通过判定准则筛选候选交叉点,基于欧氏距离对候选交叉点进行聚类后,利用灰度加权法定位图像交叉点坐标.仿真实验验证了算法的正确性与可行性,结果表明:该方法适用于交叉角为65°～90°范围内的交叉点检测,定位精度优于0.6像素,检测率大于90％;该方法...     

双处理器的图像跟踪系统硬件平台设计

通过分析装甲车车载图像跟踪系统的任务和应用环境,设计了以TMS320C6202数字信号处理器(DSP)为核心,结合PC104嵌入式计算机的双处理器并行处理硬件平台;详细介绍了利用大规模FPGA芯片实现系统总线仲裁和逻辑控制的设计思想;并给出了体现系统智能化程度的--DSP模块的程序智能加载技术以及其实现方法.实际系统测试表明该硬件平台能满足图像跟踪系统的实时性、可扩展性、稳定性的要求,为装甲战车的数字化改造提供了可靠的保障.     

基于层次方法和PCA特征变换的宫颈细胞识别

对宫颈细胞多分类,可以自动识别出不同状态的细胞,进而为宫颈癌诊断提供科学依据。在用6种多分类算法实验后,选取支持向量机（SVM）作为基分类器,先用一对一策略（one- versus -one）训练6个分类器进行3分类,然后再训练1个2分类器,这种二层4分类方法提高了识别准确率。又考虑不同层特征模式的差异性,在保证识别性能同时,每层分类前先采用主成分分析（PCA）法将原始154维特征变换到低维空间,去除冗余特征,加快识别速度。实验证明,所提层次PCA法在宫颈细胞分类中相比6种传统多分类方法有更高的识别准确率,可达90%以上;识别速度也较普通层次法提升了21.31%。     

基于仿射近似的摄像机标定

针对直接基于透视投影模型的标定算法计算量大、结果不稳定的事实,提出一种基于仿射投影矩阵的标定算法。算法首先线性解算仿射投影矩阵,然后分解出部分参数。在假定主点坐标等于图像中心的前提下,解算出其余参数,再以重投影图像点残差和为目标函数,对所有参数进行优化,获得精确的摄像机模型参数,达到精确、快速、稳定的标定目的。大量的仿真和真实图像实验证明算法比传统算法更稳定。