基于图论的参数曲线集目标区域识别方法

参数曲线集将平面划分为多个区域,区域的准确识别和提取是矢量图案填充的基础。目前,已经有多种光栅图形学区域识别的成熟算法,但准确、快速地识别任意复杂参数曲线集目标区域还比较困难,其关键问题是：如何利用计算机有效地描述参数曲线集划分的多个区域（内含孔、岛）以及准确地识别目标区域。从空间认知的需求出发,采用图论中的多叉树形式化表达区域的空间组织结构,在建立定向闭环的基础上,给出了目标区域的自动识别方法。实验结果表明：该方法准确、有效,具有普遍适用性,在Dimine数字矿山软件中得到了良好的应用。     

一种有效的复杂地质体剖面图自动生成方法*

提出了一种基于平面隐函数的实体切割思想和区域自动识别技术的地质体剖面图生成方法。其主要步骤包括：采用平面隐函数实现平面和地质实体的求交运算,生成离散的交线;采用基于KD树的空间索引方法,确定交线的邻接关系,生成地质体轮廓线;封闭的轮廓线将平面划分为多个复杂的区域(内含孔、岛),采用图论的多叉树形式化表达区域存储和组织;最后对多叉树表示的区域进行矢量图案的填充。实验结果表明,该算法有较好的计算效率,是一种比较实用的地质体剖切方法。     

凸形目标的快速区域修正与标记算法

为了解决常规区域标记算法难以消除凸形目标的内孔与凹陷对目标识别的影响,提出一种适用于凸形目标的快速区域修正与标记算法。通过扫描线端点搜索算法消除图像分割后产生的内孔,利用凸形目标的相关理论解决目标区域的凹陷,使修正后的区域更加接近于实际目标区域,能够获取包括轮廓在内的特征,实时性好,提高了目标识别的精度。将其应用到机器人足球竞赛中,取得了良好的效果。     

一种新的CpG岛的位置识别算法

随着多数生物基因组测序工作的完成,基因识别就显得尤为重要.CpG岛在基因组中有着重要的生物学意义,因此识别CpG岛将有助于基因的识别.目前已经构建的一些识别CpG岛的位置的模型大都存在标注偏差、需要独立假设等缺点,为此提出一种基于条件随机场(CRFs)模型的CpG岛的位置识别的新方法.该方法将识别CpG岛的位置的问题转化为序列标记问题,并根据CpG岛的位置的性质设计了相应的模型构建、训练以及解码的算法.利用本文算法可以对输入序列确定最有可能的标注序列,从而识别CpG岛的位置.通过对标准数据库的数据进行测试,其实验结果表明本文算法是可行的、高效的,比HMM方法有更高的准确率.     

异形转轴机械特性测试孔的机器视觉定位方法

针对智能塑壳断路器的异形主转轴机械特性测试孔难于定位加工的问题,提出一种基于机器视觉技术的平面三点圆心定位方法.对采集的图像进行概率面积直方图分析后,采用中值滤波、灰度拉伸和线性变换算法对图像进行预处理;然后使用圆模板匹配算法识别目标区域;最后使用开运算算法消除目标区域的毛刺和区域间小点后,采用改进Harris角点检测算法提取图像的兴趣点,对其经过分类和换算后确定钻孔位置坐标.对20个测试孔的定位加工结果显示,85%的孔同轴度在IT11的等级范围之内,90%的孔直线度在IT12等级范围之内,满足智能塑壳断路器主转轴机械特性测试孔定位精度要求.     

基于孔特征的弱纹理堆叠工件识别

针对目前工业现场弱纹理堆叠工件识别困难的问题,提出一种以工件表面孔洞为特征的改进几何模板匹配算法,以合页为例进行工件识别。首先采用加权平均法对彩色图像进行灰度化处理,再采用Canny算法进行边缘检测;其次采用旋转卡壳算法求取轮廓的最小面积外接矩形,进行几何约束后得到孔洞对应的孔轮廓,并采用随机增量法计算孔轮廓的最小外接圆得到孔特征圆心坐标。采用提出的改进几何模板匹配算法,即根据孔特征之间的几何约束进行工件识别,根据孔特征之间是否存在边缘剔除误识别工件。实验结果表明,提出的算法对带孔弱纹理堆叠工件具有良好的识别效果,工件识别查全率为98.3%,误检率为0.9%,为带孔弱纹理工件的识别提供方法。     

内容一致性行人重识别算法

行人重识别是指利用计算机视觉技术识别不同监控设备下的目标行人,该技术在公共安全与相册管理等方面应用较广。然而现有行人重识别算法在局部特征区域划分后出现离异值使该区域内容不一致,导致局部特征可区分性降低。提出一种基于局部区域特征选择的内容一致性行人重识别算法。将行人图像输入残差卷积神经网络取得张量,根据局部区域内容一致性从张量中选择基本单位特征向量,使用Softmax函数计算其局部区域概率重新生成局部区域,从而消除离异值,增加类间差异并减少类内差异。实验结果表明,与Spindel、PN-GAN等行人重识别算法相比,该算法的行人重识别准确率更高,其提取的行人特征可区分性和鲁棒性更好。     

基于数字图像处理技术的微小群孔快速检测系统

传统小孔检测方法适用于单个小孔的测量,检测微小群孔时效率低。针对微小群孔快速检测的需求,设计了一种基于数字图像处理技术的微小群孔快速检测系统,提取图像骨架,用模式匹配算法识别群孔,采用最小区域法逐个获取各个小孔的直径与圆度,引入真圆度信息判别各小孔的形状。实验表明：该系统精度满足生产要求,检测效率高,适用于微小群孔的快速检测。     

基于PCA-SVM准则改进区域生长的非结构化道路识别

针对智能车辆在非结构化道路识别中需要采用众多的特征参数,增加了特征融合识别难度与计算复杂度,并且部分背景与道路区域存在相似性会产生道路识别的误分、误判的问题,提出了一种基于主成分分析的支持向量机（PCA-SVM）准则改进区域生长的非结构化道路识别算法。首先,对非结构化道路颜色、纹理等复杂特征信息进行提取,采用PCA对提取的特征信息进行降维;然后,利用降维后的主元特征对SVM进行训练后作为复杂道路单元格的分类器。利用道路位置、起始单元格等先验知识以及道路边界单元格统计特征改进区域生长方法,在单元格生长时利用分类器判别,排除误判区域。实际道路检测结果表明,所提算法具有较好的鲁棒性,能够有效识别非结构化路面区域。对比结果表明,所提算法在保证准确率的同时,将10余维复杂特征信息压缩为3维主元特征,相比传统算法可缩短计算时间一半以上。针对背景与道路相似区域造成的传统算法10%左右的误判问题,所提算法能够有效排除。在野外环境下基于视觉的局部路径规划与导航方面,所提算法为缩短识别时间、排除背景干扰提供了可行途径。     

基于流形结构重建的启动子识别

启动子识别是生物信息学的一个重要研究方向,根据启动子本身的特点已经有基于信号、内容和CpG岛等多种识别算法。针对基因序列数据数据量大、维数高、非线性的特点,提出了基于流形结构重建的启动子识别算法,先利用非线性降维方法压缩数据,然后再进行启动子识别。实验结果表明,该方法能够取得较好的结果。     

Modelling parallel overhead from simple run-time records

A number of scientific applications run on current HPC systems would benefit from an approximate assessment of parallel overhead. In many instances a quick and simple method to obtain a general overview on the subject is regarded useful auxiliary information by the routine HPC user. Here we present such a method using just execution times for increasing numbers of parallel processing cores. We start out with several common scientific applications and measure the fraction of time spent in MPI communication. Forming the ratio of MPI time to overall execution time we obtain a smooth curve that can be parameterized by only two constants. We then use this two-parameter expression and extend Amdahl’s theorem with a new term representing parallel overhead in general. Fitting the original data set with this extended Amdahl expression yields an estimate for the parallel overhead closely matching the MPI time determined previously.     

Identification of linear systems with hard input nonlinearities of known structure

This paper studies identification of systems with input nonlinearities of known structure. For input nonlinearities parameterized by one parameter, a deterministic approach is proposed based on the idea of separable least squares. The identification problem is shown to be equivalent to an one-dimensional minimization problem. The method is very effective for several common static and nonstatic input nonlinearities. For a general input nonlinearity, a correlation analysis based identification algorithm is presented which is shown to be convergent.     

SVM‐based segmentation and classification of remotely sensed data

Support Vector Machines (SVM) is becoming a popular alternative to traditional image classification methods because it makes possible accurate classification from small training samples. Nevertheless, concerns regarding SVM parameterization and computational effort have arisen. This Letter is an evaluation of an automated SVM‐based method for image classification. The method is applied to a land‐cover classification experiment using a hyperspectral dataset. The results suggest that SVM can be parameterized to obtain accurate results while being computationally efficient. However, automation of parameter tuning does not solve all SVM problems. Interestingly, the method produces fuzzy image‐regions whose contextual properties may be potentially useful for improving the image classification process.     

参数曲线集最小闭环的提取算法

文章提出了自由曲线集最小闭环的概念,给出了最小闭环的两个性质。并根据这两个性质,设计了一种提取参数曲线集最小闭环的算法。该算法速度较快、应用范围广,能适用于任意复杂曲线集提取最小闭环的情况。     

New method for computing unstable equilibrium points of power systems with induction motors

The computation of the unstable equilibrium point(UEP) is a key step involved in stability region estimation of nonlinear dynamic systems.A new continuation-based method to compute the UEPs of a power system with induction motors is proposed.The mechanical torques of motors are changed to form a parameterized equation set.Then the solution curve of the equation set is traced by the continuation method from the stable equilibrium point to a UEP.The direction of mechanical torque change is varied to get multi...     

Relay-Based Identification of a Class of Nonminimum Phase SISO Processes

A set of general expressions is derived from a single symmetrical relay feedback test for identification of a class of process transfer functions. Using these expressions the parameters of open loop stable nonminimum phase transfer function models may be obtained from simple measurements made on the limit cycle. For comparison, the conventional describing function based identification formulae are presented. Fourier series based curve fitting with the options of nonlinear least squares method and trust-region algorithm is used to measure limit cycle parameters in the presence of measurement noise. Examples are given to illustrate the value of the proposed method     

Analysis of co‐articulation regions for performance‐driven facial animation

A facial gesture analysis procedure is presented for the control of animated faces. Facial images are partitioned into a set of local, independently actuated regions of appearance change termed co‐articulation regions (CRs). Each CR is parameterized by the activation level of a set of face gestures that affect the region. The activation of a CR is analyzed using independent component analysis (ICA) on a set of training images acquired from an actor. Gesture intensity classification is performed in ICA space by correlation to training samples. Correlation in ICA space proves to be an efficient and stable method for gesture intensity classification with limited training data. A discrete sample‐based synthesis method is also presented. An artist creates an actor‐independent reconstruction sample database that is indexed with CR state information analyzed in real time from video. Copyright © 2004 John Wiley & Sons, Ltd.     

A Recursive Subdivision Algorithm for Piecewise Circular Spline

We present an algorithm for generating a piecewise G ¹ circular spline curve from an arbitrary given control polygon. For every corner, a circular biarc is generated with each piece being parameterized by its arc length. This is the first subdivision scheme that produces a piecewise biarc curve that can interpolate an arbitrary set of points. It is easily adopted in a recursive subdivision surface scheme to generate surfaces with circular boundaries with pieces parameterized by arc length, a property not previously available. As an application, a modified version of Doo–Sabin subdivision algorithm is outlined making it possible to blend a subdivision surface with other surfaces having circular boundaries such as cylinders.     

基于Level Set算法的医学图像分割的研究与实现

提出了一种改进的结合基于阈值分割特点的Level Set方法.首先用滤波器对原始图像进行平滑,然后根据当前曲线找到区域的统计特性,最后根据区域之间的统计特性的相似度重新定义了Level Set方法的演化停止准则,从而提高了算法的准确性和自动性.实验结果表明,该方法具有较好的分割效果和较高的分割效率.