基于能量增强的运动车辆车标的“四阶段法”定位技术研究

基于视频图像的运动车辆识别系统主要是由汽车牌照识别和汽车类型识别两大核心技术构成,它在智能交通领域中有着广泛的应用,同时也是计算机视觉、图像处理和模式识别等交叉学科研究的热门课题,运动车辆车标定位是车辆类型识别的核心技术之一,提出了基于能量增强的运动车辆车标定位的"四阶段法"的概念,介绍了运动车辆车标定位的方法和关键技术,对不同天气状况下不同类型的运动车辆进行了车标定位实验,实验结果表明该方法具有较强的科学依据和实用价值.     

车牌识别机器学习方法的数学建模与实现

首先,针对不同光照、复杂背景和投影失真的车牌图像建立基于Adaboost算法和改进Haar特征的车牌检测模型;然后,运用Radon变换进行车牌校正,并结合3次B样条小波变换和识别反馈模型对字符进行粗和精分割;最后,根据汉字和数字字母的不同结构特征,采用不同的算法提取特征,特别是针对车牌字符特点,训练汉字、字母和数字字母3种神经网络模型用于建立字符识别模型.实验结果表明该模型是实用的.     

基于DCT变换的车牌定位算法

车牌定位技术是车牌识别技术中最重要的部分,利用车牌图像在DCT域的水平和竖直能量值对图像进行进一步二值化处理,通过中值滤波和小区去除定位车牌.实验结果表明这种车牌定位方法具有算法实现简单、速度快、适应性强的特点.     

一种快速有效的混合倾斜车牌校正方法

车牌倾斜校正是车牌识别系统中的一关键技术,校正效果将直接影响到后续字符分割和识别的效果.为此,提出了一种快速有效的混合倾斜车牌校正方法.水平倾斜校正时,先进行Sobel垂直边缘检测算子提取字符的有效数据点,构造有效数据点矩阵,然后进行矩阵奇异值分解,利用特征向量矩阵导出车牌水平倾斜角度的表达式;垂直倾斜校正时,首先通过Sobel垂直和水平边缘检测有效去除边框及上下左右噪声干扰区域,然后通过形态学腐蚀提取有效反映字符水平错位的有效数据点,其次将这些有效数据点水平投影分成七个字符区域,求取每个区域错切变换后的最佳列坐标质心对应其区域垂直倾斜角,最后取区域垂直倾斜角的均值作为车牌的最佳垂直倾斜角.对大量复杂背景下的倾斜车牌进行实验,并做了精确度、运行时间、抗干扰性分析,实验结果表明:提出的混合倾斜校正方法精确度高、运行时间短、抗干扰性强.     

基于模板匹配的车牌数字与字母识别

车牌的字符识别是车牌识别的重要组成部分.我国的车牌由7个字符组成,除第一位为汉字外,其余均为字母和数字字符,所以提高数字与字母识别率在车牌字符识别中占很重要的地位.通过模板匹配的方法对车牌的数字与字母字符进行识别.选择了两个判别函数,一个是求取模板、待识别字符与运算结果的标准差的最小值,另一个是求取运算结果与模板比值的最大值.并对两个判别函数的识别结果进行了比较,求标准差最小值在总体识别结果上比求比值最大值的识别结果要好,但在个别字符的识别上,求取比值最大值的识别结果要高于求取标准差最小值的识别结果.     

基于SVM的车牌数字识别方法

运用支持向量机对车牌字符进行识别,解决了由于图像受客观条件的影响、样本数量不是很大等原因导致的识别率不高的问题.主要针对车牌字符中的数字进行实验,选取了15组数字样本,8组进行训练,7组进行测试,采用交叉验证的思想对SVM进行参数C与g的寻优,并选择合适的核函数,对样本进行训练和预测,对于某些数字的识别率可达到100%,并在相同的训练集和测试集下与BP网络的识别效果进行对比.实验结果表明,SVM在训练样本较少且无字符特征提取的情况下具有很好的识别率,并且有很好的分类推广能力.     

基于跟车思想的一维元胞自动机交通流模型

提出一个改进的一维元胞自动机模型来模拟周期性边界条件下高速公路上车流运动.基于跟车模型的思想,根据所研究车辆与其前方紧邻车辆之间的间距和相对速度来确定该车的运动,间接地反映了次近邻车辆的影响.通过引入安全间距来描述高速运动车辆接近前方缓行车辆时的减速行为,并利用随机减速概率来反映减速行为中的随机因素.由于安全间距的引入,当减速概率大于零时在较高密度下就出现完全的阻塞相.同时在本模型中采用的是有条件减速,因而可以较好描述交通实测中观察到的现象.在临界密度附近,车流运动处于亚稳态并呈现出滞后现象.由于本模型对于车辆微观运动的合理描述,可以直接用以研究在交通灯控制下城市道路交通中的各种现象.     

自动驾驶测试评价研究综述

随着自动驾驶技术研究的兴起,对自动驾驶车辆建立一个科学完善的测试评价体系也逐渐受到重视.自动驾驶车辆的测试评价体系主要包括测试方法,以及评价方案与指标的选取.各个国家也为自动驾驶车辆的技术发展和应用制定了标准和法规,对于评价体系的建立有所帮助.因此,文章针对于自动驾驶车辆的测评研究进行了相关的调研工作,从现状背景、测试...     

基于视网膜大细胞通路计算模型和深度学习的无人机目标检测

在复杂背景下的小型无人机红外目标检测是计算机视觉领域的挑战性课题.传统目标检测算法利用深度卷积神经网络提取无人机的静态外观特征并进行模式判别,但在复杂背景下且目标外观不清晰时的性能会显著下降.本文借鉴生物视网膜机制,通过视网膜大细胞通路模型提取无人机目标的时空运动信息,同时借助深度卷积神经网络获得基于静态表观特征的目标置信度图,进而将视网膜时空运动信息与深度卷积网络的目标置信度图进行融合获得目标检测结果.在Anti-UAV2020公开数据集上的评估结果表明,所提出算法的检测精确率达到86.90%,超过了业内主流的YOLO-v3算法.     

基于逐步回归分析和BP_Adaboost算法的危险驾驶行为辨识

为准确辨识车辆在行驶过程中可能出现的异常加减速,压线行驶,右侧超车驾驶行为,以便于及时给予驾驶员信息反馈和安全预警,使车辆保持安全的运行状态.首先通过虚拟驾驶仿真实验平台,采集驾驶行为的48种车辆运行数据对实验数据进行预处理,获得实验样本1492组;其次利用逐步回归分析对原始数据进行降维处理,并选取其中的最优回归模型获得特征参数;将提取的特征参数数据输入到BP_Adaboost多分类网络中,训练BP_Adaboost多分类网络,对上述驾驶行为进行识别;最后该模型与BP神经网络进行识别结果对比分析.结果表明模型识别率相较于BP神经网络提高了8.81%,达到92.93%,能进行更加有效的安全预警.     

Polygon Recognition and Symmetry Detection

We introduce an approach based on moving frames for polygon recognition and symmetry detection. We present detailed algorithms for the recognition of polygons in R² modulo the special Euclidean, Euclidean, equi-affine, skewed-affine, and similarity Lie groups. We also solve the case of polygons in the Poincar\'e half-plane under the action of SL(2) and explain a method applicable to Lie group actions in general. The time complexity of our algorithms is linear in the number of vertices and they are noise resistant. The signatures used allow the detection of partial, as well as approximate, equivalences.     

Finite Element Simulations with Adaptively Moving Mesh for the Reaction Diffusion System

A moving mesh method is proposed for solving reaction-diffusion equations. The finite element method is used to solving the partial different equation system, and an efficient scheme is applied to implement mesh moving. In the practical calculations, the moving mesh step and the problem equation solver are performed alternatively. Serveral numerical examples are presented, including the Gray-Scott, the Activator-Inhibitor and a case with a growing domain. It is illustrated numerically that the moving mesh method costs much lower, compared with the numerical schemes on a fixed mesh. Even in the case of complex pattern dynamics described by the reaction-diffusion systems, the adapted meshes can capture the details successfully.     

A witness version of the Cops and Robber game

The games considered are mixtures of Searching and Cops and Robber. The cops have partial information provided via witnesses who report “sightings” of the robber. The witnesses are able to provide information about the robber’s position but not the direction in which he is moving. The robber has perfect information. In the case when sightings occur at regular intervals, we present a recognition theorem for graphs on which a single cop suffices to guarantee a win. In a special case, this recognition theorem provides a characterization.     

某类带参数4n－阶微分算子的一个同胚与线性同胚定理

本文对某类由考察一些物体的运动性状而引出的４ｎ－阶线性非对称或非线性微分算子给出了一个正则性定理。这个定理包含在实（非线性）情形下２个同胚与扩张同胚类，或者在复（线性）情形下３个线性同胚与扩张线性同胚类。这对于揭示某些物体（例如，某些飞行器）在它们运动过程中的双向平稳性是有用的。     

Does the chalkboard still hold its own against modern technology in teaching mathematics? A case study

The purpose of this case study is to explore the integration of technology into teaching at a mathematics department at a large South African University. Both quantitative and qualitative data were collected from staff teaching undergraduate mathematics. The study shows that many staff members feel that chalkboards are still more suitable than technology for teaching mathematics. This finding supports the idea of a strong subject culture. Age does not emerge as a determinant for preference of either technology or the chalkboard, although gender and academic qualifications do. Subject culture is strongly rooted under the male members of staff, while female staff members feel more positive towards the use of technology in teaching. Use of chalkboards has decreased significantly over the past 10 years, while the use of modern technologies has increased accordingly. Teaching of large groups has necessitated the use of technology in the classroom. Despite the strong subject culture, a shift in attitude towards technology use in teaching is noticed and there is a definite trend of moving towards using new technologies.     

Vibrations of a beam-string complex system under a moving force

In this paper, the dynamic response of an Euler-Bernoulli beam and string system traversed by a constant moving force is considered. The force is moving with a constant velocity on the top beam. The complex system is finite, simply supported, parallel one upon the other and continuously coupled by a linear Winkler elastic element. The classical solution of the response of a beam-string system subjected to a force moving with a constant velocity has a form of an infinite series. The main goal of this paper is to show that in the considered case the aperiodic part of the solution can be presented in a closed, analytical form instead of an infinite series. The presented method of finding the solution in a closed, analytical form is based on the observation that the solution of the system of partial differential equations in the form of an infinite series is also a solution of an appropriate system of ordinary differential equations. The dynamic influence lines of complex systems may be used for the analysis the complex models of moving load. (© 2016 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Asymptotic solutions of a magnetohydrodynamic system which describe smoothed discontinuities

Asymptotic solutions of a nonlinear magnetohydrodynamic system rapidly varying near moving surfaces are described. It is shown that the motion of jump surfaces is determined from a free boundary problem, while the main part of the asymptotics satisfies a system of equations on the moving surface. In the “nondegenerate” case, this system turns out to be linear, while, under the additional condition that the normal component of the magnetic field vanishes, it becomes nonlinear. In the latter case, the small magnetic field instantaneously increases to a value of order 1.     

A higher‐order PDE‐based image registration approach

This paper addresses the problem of image registration with higher‐order partial differential equation (PDE) methods. From the study of existing affine‐linear and non‐linear methods, a new framework is proposed that unifies common image registration methods within a generic formulation. Currently image registration strategies are classified into either affine‐linear or non‐linear methods subject to the underlying transformations. The new approach combines both strategies to obtain proper approximations which are invariant under global geometrical distortion (shearing), anisotropic resolution (scale changes), as well as rotation and translation. To achieve this favourable property, a modified gradient flow approach is proposed which uses an operator with a kernel consisting of affine‐linear transformations. An approximation with finite differences leads to a large singular linear system. The pseudo‐inverse solution of this system can be computed efficiently by augmenting the singular system to a regular system. Numerical experiments show the improvements compared to unmodified gradient flow approaches. Copyright © 2005 John Wiley & Sons, Ltd.     

Dynamic behavior of a moving frictional punch over the surface of anisotropic materials

This paper investigates dynamic, frictional contact of a moving punch over the surface of anisotropic materials. An eigenvalue analysis of the governing equations is performed. The application of the complex function theory produces a singular integral equation exhibiting a non-square-root or unconventional singularity. Numerical tests demonstrate that both the friction coefficient and the moving velocity contribute to the contact behaviors under a moving punch with a flat or cylindrical profile. Furthermore, the present results illustrate that the surface in-plane stress possesses singularity and discontinuation at both edges of the flat punch and has a tensile spike at one edge of the cylindrical punch, which may account for the fatigue and fracture under the contact loading.