光照变化条件下结合图像纹理与改进census变换的鲁棒光流算法

针对传统光流算法只能对某种特定光照变化有效的问题,提出一种能改善不同光照变化条件下的光流鲁棒求解方法.所提出的方法利用改进census变换和图像纹理信息加权和构建光流模型中数据项.数据项中不同分量的权重根据两帧图像SIFT点对应灰度差动态选择,以满足不同亮度变化的图像,自适应地选择相应的数据项.改进census变换包含了变换窗口内完整的相对灰度大小信息;对两个不同的窗口,较传统census变换有更高的区分度.以Middlebury和KITTI数据库对所控算法进行测试,实验结果证实了所提出方法对不同仿真光照变化和野外真实光照环境下图像鲁棒光流求解的有效性.     

基于灰度分布特征的层次掌纹识别方法

目前掌纹识别算法主要集中在对掌纹图像所切取的ROI区域的研究,而对原始手部图像的灰度分布特征则讨论较少。在一定光照条件下,掌部不同位置的主线、皱纹和表层皮肤颜色的深浅在灰度图像上各自对应了不同的灰度级。该文提出一种利用手部尺寸和角度信息完成粗分类,借助单元信息熵的概念来分析手部图像的灰度分布特征从而完成细分类的层次掌纹识别方法。该方法不同于传统的对ROI区域进行特征提取的方法,直接利用整幅人手图像完成分类识别。在99类共990幅手部图像的数据库上进行的实验结果与PCA和LDA算法的对比表明,该算法具有比传统算法更高的鲁棒性,识别率也得到了较大幅度的提高。     

基于改进的BP神经网络模型的遥感图像分类方法研究

遥感图像通过像元灰度值的高低差异和空间变化来表示不同属性的地物目标及其分布情况。随着人工神经网络理论的发展,神经网络技术日益成为遥感图像分类处理的有效手段,并有逐渐取代传统遥感图像分类方法的趋势。重点分析了BP神经网络模型的遥感图像分类方法,并针对BP算法的学习速率慢做了改进,利用M atlab 7.0作为实验平台,对北京市海淀区遥感影像进行分类实验。实验结果表明,与基本BP算法相比较,改进的BP算法网络训练收敛速度快,分类方法是有效的。     

基于多重分形谱的木材高光谱图像纹理分类算法

为了过滤木材高光谱图像中大量的冗余信息,提升应用图像纹理进行分类的准确率,本文采用基于多重分形理论的木材高光谱图像分类算法。首先利用不同的特征选择算法选取最具代表性的10个波段;随后根据不同的函数密度图像对所选取波段的图像求解其多重分形曲线,将选择出的多个波段所对应的多重分形曲线取平均,得到表示样本纹理特征的多重分形曲线;最后使用支持向量机和BP神经网络分类器对多重分形曲线进行分类。实验表明,相对熵(K-L散度)要好于自适应波段选择(ABS)提取的波段,多重分形算法提取的高光谱图像纹理特征要好于灰度共生矩阵,支持向量机算法的分类准确率和速度要优于BP神经网络,融合K-L散度、多重分形和支持向量机算法能够有效地提高木材高光谱图像的识别准确率,最高识别准确率达到了97.91%。     

同质背景预测用于红外弱小目标检测

背景预测是红外弱小目标检测中抑制背景的主要方法之一.提出了一种同质背景预测算法,在分析空背景下不同背景成分图像灰度特征模型的基础上,首先对图像进行边缘检测,将图像划分为不同灰度性质的区域,然后使用边缘检测结果调制预测权值矩阵.仿真结果表明,该算法对背景杂波具有很好的抑制效果,能够有效保护图像细节,明显降低异质区域像素灰度对预测的不利影响,显著改善低信噪比条件下弱小目标的检测性能.     

一种采用高斯隐马尔可夫随机场模型的遥感图像分类算法

该文研究了无监督遥感图像分类问题。文中构造了图像的隐马尔可夫随机场模型(HiddenMarkov Random Fleid,HMRF),并且提出了基于该模型的图像分类算法。该文采用有限高斯混合模型(Finite Gaussian Mixture,FGM)描述图像像素灰度的条件概率分布,使用EM(Expectation-Maximization)算法解决从不完整数据中估计概率模型参数问题。针对遥感图像分布的不均匀特性,该文提出的算法没有采用固定的马尔可夫随机场模型参数,而是在递归分类算法中分级地调整模型参数以适应区域的变化。实验结果表明了该文算法的有效性,分类算法处理精度高于C-Means聚类算法.。     

一种改进的一维Otsu快速算法

阈值分割是众多图像分割方法中使用最普遍的一种方法,阈值的求解也是图像处理的重心。传统Otsu算法属于穷举式的阈值求解方法,需遍历每个灰度值并计算以其为阈值的类间方差,在此进行了大量不必要的计算,可能无法应用于某些实时性要求较高的环境中。对此提出一种快速的Otsu改进算法,在引入图像复杂度及其相关性质缩小了灰度的搜索范围,同时在搜索范围内使用了一种快速计算方法,较传统Otsu算法进行了二次加速。实验结果证明,该算法较传统Otsu算法提高了计算速度,且两种算法的图像分割结果相同。     

基于最大后验概率的SAR图像目标分割算法

文中使用最大后验概率(MAP)分类方法实现合成孔径雷达(SAR)图像目标分割,并与基于偏微分方程(PDE)的各向异性扩散(AD)过程结合起来,使MAP分类准则得到更好的分割结果。AD过程是作用在后验概率上的空域滤波器,具有高效、精确和简洁的优点,并对图像数据的分布特性具有很强的适应性。这种方法需要先将图像从灰度域转化到后验概率域,因此需要对像素灰度分布进行条件概率分布建模,并进行参数估计。文中巧妙的使用有限混合高斯分布模型来逼近条件概率分布,并用期望最大化(EM)方法用来实现参数估计。在引入这种新奇的混合高斯分布模型后,基于MAP-AD的分割算法对地面SAR图像获得了很好的分割结果并对图像灰度分布具有很强的鲁棒性。     

基于特征提取与机器学习的文档区块图像分类算法

文档区块图像分类对于文档版面图像的理解和分析至关重要。在传统机器学习分类模型中,直接使用图像作为输入会导致模型参数量过大因此无法进行训练。为了克服这个困难,我们在本文中针对文档区块图像设计了一组有效的特征,并提出了基于这些特征和机器学习的文档区块分类算法。在特征设计上,我们提取了几何、灰度、区域、纹理和内容五方面在内的32维特征,以增强特征针对区块类别的分辨能力。在分类器方面,我们在所提出的特征上对传统机器学习分类模型、自动机器学习方法以及深度学习均进行了实验。在公开数据集上的实验结果表明,我们提出的文档版面区块分类算法具有很高的分类准确率,并且十分高效。另外我们实现了一个简单的分步文档版面分析算法,以展示所提出的区块分类算法的推广能力。      

超像素优化Snake模型的乳腺X线图像胸肌分割

提出基于超像素优化Snake模型的乳腺X线图 像胸肌 分割方法。首先采用融合灰度和纹理特征的超像素分割算法将图像分割为多个具有准确边界 、同质的 超像素区域;再根据胸肌的解剖学特征和灰度特征将超像素分类,识别胸肌区域,完成胸肌 的粗分割; 最后使用超像素分类结果优化Snake模型初始轮廓,通过Snake模型演化实现胸肌的细分割 。实验结果表明,本文方法对不同大小、形状和亮 度的胸肌 能够准确地逼近到目标边界,并具有较强的抗噪性和鲁棒性;与其他胸肌分割算法相比,本 文算法准确性较高,稳定性较好。     

基于广义UT变换的交互式多模型粒子滤波算法

 针对粒子滤波中重采样过程与优化提议分布的处理方式导致的粒子溃退和算法实时性下降问题,通过广义UT变换原理和卡尔曼滤波预测更新机制的引入,实现当前量测信息对于状态估计结果的直接优化,给出了一种基于广义UT变换的粒子滤波算法。另外,将改进后算法与交互式多模型相结合,进而提出了一种基于广义UT变换的交互式多模型粒子滤波算法．理论分析和仿真结果表明：新算法在计算复杂度方面与标准粒子滤波相近,在滤波精度方面优于标准粒子滤波及其改进算法．     

A geometric approach to chip-scale TSV shield placement for the reduction of TSV coupling in 3D-ICs

In 3D ICs, through-silicon-vias (TSVs) can suffer from cross coupling if signal integrity is not considered during the design process. In this paper, coupling between TSVs is modeled, and a chip-scale TSV shielding scheme is presented. A geometric model is developed to estimate TSV coupling. The low complexity of the geometric model makes it practical for chip-scale shield placement optimization. Two shield placement algorithms are presented and compared to standard shield placement techniques that use a high complexity circuit model of coupling. Results show that our algorithms are able to reduce the total cross coupling in a layout on average 111%/129% more than standard methods.     

Beam pattern design of circular antenna array via efficient biogeography-based optimization

In this paper, an efficient biogeography-based optimization (EBBO) method is proposed to synthesize the circular antenna arrays (CAA) for specific radiation beam pattern properties and null controls. The proposed method achieves the desired beam patterns by jointly optimizing the excitation currents as well as the spaces between the array elements. Three improved components, including chaotic search theory, model learning method and a new random perturbation operator, are introduced into the standard biogeography-based optimization (BBO) to improve the performance of the algorithm. Simulation results show that the maximum sidelobe level obtained by EBBO can be suppressed effectively compared with other algorithms. Moreover, the null controlling performance of EBBO is the best among the algorithms.     

Research on equipment fault diagnosis method based on random stochastic adaptive particle swarm optimization

The traditional fault diagnosis method of industrial equipment has low accuracy and poor applicability. This paper proposes a equipment fault diagnosis method based on random stochastic adaptive particle swarm optimization (RSAPSO). The entire model is validated by using the data of healthy bearings collected by Case Western Reserve University. Different gradient descent algorithms and standard particle swarm optimization (PSO) algorithms in a back propagation (BP) network are compared experimentally. The results show that the RSAPSO algorithm has a higher accuracy of weight threshold updating than the gradient descent algorithm and does not easily fall into a local optimum. Compared with PSO, it has a faster optimization speed and higher accuracy. Finally, the RSAPSO algorithm is validated with the data of bearings collected from the laboratory rotating machinery test bench and motor data collected from the tower reflux pump. The average recognition rate of the four kinds of bearing data constructed is 97.5% , and the average recognition rate of the two kinds of motor data reaches 100% , which prove the universality of the method.     

基于改进鲸鱼算法的多无人机协同欺骗干扰技术

多机协同对组网雷达系统进行航迹欺骗干扰属于大规模优化问题,往往需要利用群体智能算法优化无人机的飞行任务,然而采用传统群体智能算法优化时往往会出现收敛速度慢、求解精度低等问题。针对这一问题,对标准鲸鱼优化算法进行了改进,提出了一种基于改进鲸鱼优化算法的多无人机协同欺骗干扰技术。首先建立了多无人机协同欺骗干扰组网雷达的数学模型以及对应的优化函数,然后在标准鲸鱼优化算法的基础上引入了自适应惯性权值,提高了算法的全局搜索能力和收敛速度。仿真实验表明,固定无人机数量为9架时,利用改进鲸鱼、标准鲸鱼、粒子群、蚁群4种算法分别优化多机协同欺骗干扰模型,得出改进鲸鱼优化算法平均运行时间最短,迭代次数最少,同时优化产生的实际航迹与理论值误差最小;逐步增加无人机数量至20架,利用上述四种算法进行模型求解时得出改进鲸鱼优化算法在不同无人机架数的条件下产生的假目标航迹条数均优于其他3种算法。     

Evolutionary computation applied to the reconstruction of 3-D surface topography in the SEM

A genetic algorithm has been applied to the line profile reconstruction from the signals of the standard secondary electron (SE) and/or backscattered electron detectors in a scanning electron microscope. This method solves the topographical surface reconstruction problem as one of combinatorial optimization. To extend this optimization approach for three-dimensional (3-D) surface topography, this paper considers the use of a string coding where a 3-D surface topography is represented by a set of coordinates of vertices. We introduce the Delaunay triangulation, which attains the minimum roughness for any set of height data to capture the fundamental features of the surface being probed by an electron beam. With this coding, the strings are processed with a class of hybrid optimization algorithms that combine genetic algorithms and simulated annealing algorithms. Experimental results on SE images are presented.     

通信卫星星座优化设计综述

通信卫星星座优化设计是构建通信星座系统的关键环节。对通信卫星星座设计中的优化模型和优化算法进行了综述和展望。首先,建立了通信卫星星座设计的一般优化模型;然后,从覆盖性能、星间链路和系统成本三个方面对优化模型中优化变量、目标函数和约束条件的构建进行了综述;之后,介绍了卫星星座设计中常用的三大类多目标优化算法,归纳总结了4种主流算法的主要特征,并比较分析了它们应用于卫星星座设计的优缺点;最后,指出了现有通信卫星星座优化设计中存在的问题及发展趋势。     

A robust phase-only Direct Data Domain algorithm based on generalized rayleigh quotient optimization using hybrid Genetic Algorithm

A robust phase-only Direct Data Domain Least Squares （D3LS） algorithm based on generalized Rayleigh quotient optimization using hybrid Genetic Algorithm （GA） is presented in this letter. The optimization efficiency and computational speed are improved via the hybrid GA composed of standard GA and Nelder-Mead simplex algorithms. First, the objective function, with a form of generalized Rayleigh quotient, is derived via the standard D3LS algorithm. It is then taken as a fitness function and the unknown phases of all adaptive weights are taken as decision variables Then, the nonlinear optimization is performed via the hybrid GA to obtain the optimized solution of phase-only adaptive weights. As a phase-only adaptive algorithm, the proposed algorithm is simpler than conventional algorithms when it comes to hardware implementation. Moreover, it proc- esses only a single snapshot data as opposed to forming sample covariance matrix and operating matrix inversion. Simulation results show that the proposed algorithm has a good signal recovery and interferences nulling performance, which are superior to that of the phase-only D3LS algorithm based on standard GA.     

Rate distortion optimal bit allocation methods for volumetric data using JPEG 2000.

Computer modeling programs that generate three-dimensional (3-D) data on fine grids are capable of generating very large amounts of information. These data sets, as well as 3-D sensor/measured data sets, are prime candidates for the application of data compression algorithms. A very flexible and powerful compression algorithm for imagery data is the newly released JPEG 2000 standard. JPEG 2000 also has the capability to compress volumetric data, as described in Part 2 of the standard, by treating the 3-D data as separate slices. As a decoder standard, JPEG 2000 does not describe any specific method to allocate bits among the separate slices. This paper proposes two new bit allocation algorithms for accomplishing this task. The first procedure is rate distortion optimal (for mean squared error), and is conceptually similar to postcompression rate distortion optimization used for coding codeblocks within JPEG 2000. The disadvantage of this approach is its high computational complexity. The second bit allocation algorithm, here called the mixed model (MM) approach, mathematically models each slice's rate distortion curve using two distinct regions to get more accurate modeling at low bit rates. These two bit allocation algorithms are applied to a 3-D Meteorological data set. Test results show that the MM approach gives distortion results that are nearly identical to the optimal approach, while significantly reducing computational complexity.     

A modular approach for simulation-based optimization of MEMS

The importance of MEMS optimization concerning performance, power consumption, and reliability is increasing. A variety of specialized tools is available in the MEMS design flow. FEM tools (ANSYS, CFD-ACE+) are widely used on component level. System level simulations are carried out using simplified models and simulators like Saber or ELDO. There is a lack of simulator-independent optimization support. Only a few simulators offer optimization capabilities.Our approach aims at a flexible combination of simulators and optimization algorithms by partitioning the optimization cycle into simulation, error calculation, optimization and model generation. This new method is translated into a modular optimization system named Moscito implemented in Java. Several optimization algorithms are available: methods without derivatives, methods using derivatives and stochastic approaches. Interfaces to simulators like ANSYS, Saber, MATLAB are implemented. Thus the optimization problem can be handled on different levels of model abstraction (FEM, ordinary differential equations, generalized networks, block diagrams, etc.). A graphical user interface supports control and visualization of the optimization. The modules of the optimization system are able to communicate via the Internet to allow a distributed, web-based optimization.