用灭点－边缘线性内插算法提取立体图象物体的中心线

本文提出了提取立体图象物体中心线的灭点一边缘线性内插算法。以光带图象为实例,阐明了它的实现原理。它与灰色加权线性内插算法相比,不仅具有计算速度快的优点,而且具有相同的精度。      

IP MULTICAST GROUP MANAGEMENT FOR BROADCAST LANS DISTRIBUTION

IntroductionThere are two traditional types of communica-tion in computer networks:unicastand broadcast.A unicast address (one to one) is designed to sendmessages to a single destination in a network.Abroadcast (one to all) address is used to send datato the entire network(all hosts) .Multicast(oneor many to many) can be viewed either as an inter-mediate case,or as a generalized mode encompass-ing both unicast and broadcast as special cases.Inmulticast mode,messages are sent to an arbitraryse…     

基于激光雷达的自动驾驶同步定位与建图方法综述

同步定位与建图（Simultaneous Localization and Mapping,SLAM）技术可使自动驾驶车辆在未知环境中根据车载传感器采集到的数据估计自身位姿,建立环境地图,为车辆的规划、决策提供定位信息,是近年来自动驾驶技术研究的热点之一。基于车载激光雷达的点云数据,聚焦SLAM技术在自动驾驶领域的应用,围绕前端里程计、后端优化和回环检测技术,对国内外相关研究进行综述。考虑到单一传感器的局限性,结合目前多传感器融合研究的热点与难点,展望了自动驾驶多传感器融合SLAM技术在自动驾驶领域的机遇与挑战。     

基于小波变换的数字水印算法研究

基于小波变换的数字水印技术是当前的一个研究热点,本文系统分析和总结了基于小波域的数字水印算法,并根据水印算法的特点对其进行了分类,详细分析了各类水印算法的各种嵌入和检测技术以及各自的优缺点,最后给出了图像水印算法的测试结果.     

基于径向基神经网络的大连站客运量预测

针对铁路客运量在时序上的复杂非线性特征,采用径向基函数(RBF)神经网络对铁路客运量时间序列进行预测.用自相关分析技术分析时间序列的延迟特性,据此确定RBF神经网络的输入、输出向量,建立了基于MATLAB7.0环境下的RBF神经网络客运量预测模型,并用大连站实际客运量数据进行了验证.结果表明,该模型拟合精度和预测精度较高、计算速度较快.     

Method for improving RLS algorithms

The recursive least-square (RLS) algorithm has been extensively used in adaptive identification, prediction, filtering, and many other fields. This paper proposes adding a second-difference term to the standard recurrent formula to create a novel method for improving tracing capabilities. Test results show that this can greatly improve the convergence capability of RLS algorithms.     

遗传算法在动车组运用计划编制中的应用

本文建立了动车组运用计划编制中相应的数学模型;在求解模型部分把动车组的运用计划分为交路段的生成和交路的生成两部分来求解,在生成交路段的过程中采用遗传算法使生成的交路段数最少,在交路的生成过程中采用交路段互换的方法使得各个基地的动车组使用均衡。     

Design of ANFIS networks using hybrid genetic and SVD methods for modeling and prediction of rubber engine mount stiffness

Genetic Algorithm (GA) and Singular Value Decomposition (SVD) are deployed for optimal design of both the Gaussian membership functions of antecedents and the vector of linear coefficients of consequents, respectively, of ANFIS networks. These networks are used for stiffness modelling and prediction of rubber engine mounts. The aim of such modelling is to show how the stiffness of an engine mount changes with variations in geometric parameters. It is demonstrated that SVD can be optimally used to find the vector of linear coefficients of conclusion parts using ANFIS (Adaptive Neuro-Fuzzy Inference Systems) models. In addition, the Gaussian membership functions in premise parts can be determined using a GA. In this study, the stiffness training data of 36 different bush type engine mounts were obtained using the finite element analysis (FEA).     

Applicability of highway alignment optimization models

This paper presents an intelligent optimization tool that assists planners and designers in finding preferable highway alignments, connecting specified endpoints or zones. It integrates genetic algorithms with a geographic information system (GIS) for optimizing highway alignments and processes massive amounts of relevant data associated with highway design and alternative evaluation. To show the applicability of the proposed model to a real-world problem, two actual highway projects in the state of Maryland have been analyzed using the model. An extensive analysis of sensitivity to key model parameters is also conducted to describe the model capabilities. The analysis results show that the model can effectively optimize highway alignments in an area combining complex terrain and various types of natural and cultural land-use patterns, and provide detailed information of optimized alignments as a model output. It is also found that the alignments optimized by the model are quite similar to those obtained through conventional manual methods by a state agency, but the model can greatly reduce the time required for highway planning and design as well as produce lower cost solutions. Finally, the results confirm that all dominating and alignment-sensitive costs should be simultaneously evaluated in the alignment optimization process because many trade-off opportunities exist among those costs. The proposed model can greatly contribute to the productivity of highway planners as well as to the quality of the resulting infrastructure.