基于显著区域的行人检测算法

针对经典行人检测算法(HOG+SVM algorithm)因滑动窗口滑动次数过多引起的计算量过大问题,提出一种基于显著区域的行人检测算法。把提取的显著度和原图结合得出有效图,实现由整张图像行人检测到局部有效图行人检测的转变;用贝叶斯准则将有效区域和基于协方差的行人检测有机结合,达到在降低计算量的同时提高检测准确率的效果。在公开数据集INRIA上的实验结果表明,该算法降低了计算量,明显改善了误检率。     

多尺度级联行人检测算法的研究与实现

行人检测算法是利用行人的特征结合分类器对图片中是否有行人进行判断的方法。文中基于传统的HOG行人特征检测方法以及Adaboost分类器思想,改进了行人检测算法。使用多尺度的HOG特征对图片的检测区域进行特征提取,并采用级联的Adaboost分类器结合对应尺度的特征进行分类判断,将判断结果输入下一级分类器中继续进行分类判断,最终实现区域内有无人的检测。实验结果表明多尺度下的级联分类器能够更加有效地筛选出行人区域,在计算时间小幅增加的情况下,很大地提高了检测精度。     

基于区域特征的顶视运动行人快速检测

针对视频中运动行人遮挡问题,提出了一种基于区域特征的顶视运动行人检测算法.首先结合三帧差分和背景减除算法检测出所有可能的行人运动区域,然后找出运动区域的轮廓以及区域的外接矩形,并计算运动区域的面积,最后根据外接矩形的长宽比以及运动区域面积进行区域筛选,找出有效的运动区域,从而检测出行人.实验结果表明,该方法能够快速准确地检测出视频中的行人.     

基于HOG的快速行人计数算法

为解决智能监控中空间受限情景下的行人计数问题,设计了基于HOG的行人识别与计数算法. 通过限制HOG目标检测算法中图像的缩放范围,并设置感兴趣的检测区域,相比直接应用OpenCV函数实现的目标检测,其时间效率大幅提升;采用基于单计数线算法完成双向流量统计. 三个不同走廊环境的实验表明,本文算法具有不依赖帧间运动信息的特点,可快速稳定的对空间受限情景下的行人进行计数.     

基于似物性和空时协方差特征的行人检测算法

针对行人检测算法中缺少空时信息融合、检测区域过大等问题,提出了一种联合似物性检测和基于通道协方差信息的改进算法。该算法首先对图像进行二进制梯度归一化的似物性检测,并形成行人检测候选区域,缩小检测区域;然后提取待测目标的空间和时间特征;最后基于协方差信息构造一种融合空时特征的检测器,以提高检测精度。在公开的数据集INRIA和Caltech上的实验结果表明:该算法的性能优于目前主流的行人检测算法。     

基于HOG的行人快速检测

为了更好更快速地实现对行人的检测,提出一种基于空间梯度直方图的行人检测算法。该算法在分类识别时用Boosted Cascad算法级联结构的分类器,将那些对不包含行人信息的区域进行筛选排除,从而使信息量减少。实验结果表明,该算法在不降低检测效果的情况下明显提高了行人检测效率,具有较强的鲁棒性。     

利用腿部区域HOG特征的行人检测方法

为快速定位车辆前方的行人,提出一种基于腿部感兴趣区域梯度方向直方图（HOG）特征的行人检测方法。将可能存在行人腿部的区域作为感兴趣区域,采用Sobel算子增强腿部垂直边缘特征,并提取梯度方向直方图特征,有效地降低了特征向量的维数;在检测过程中仅扫描可能存在行人腿部的图像下半部分,并在整幅图像的块内计算HOG特征,减少了复杂背景对行人检测干扰,进一步简化了检测过程;基于垂直边缘对称性特征对检测结果进行融合。实验结果表明,该算法能在保持检测率的同时提高检测速度。     

结合网格密度聚类的行人检测候选域生成

目的 行人检测是计算机视觉领域中的重点研究问题。经典的可变形部件模型（DPM）算法在行人检测领域素有高检测精度的优点,但由于在构建特征金字塔前处理过多召回率低的候选区域,导致计算速度偏慢,严重影响系统的实时性。针对该问题,本文对模型中选取候选检测区域的流程进行了改进,提出一种结合网格密度聚类算法和选择性搜索算法的行人检测候选对象生成方法来改进DPM模型。方法 首先使用三帧差法和高斯混合模型收集固定数量的运动物体坐标点,然后结合基于网格密度的聚类算法构建网格坐标模型,生成目标频繁运动区域,同时进行动态掩层处理。随后引入改进的选择性搜索算法,结合支持向量机（SVM）训练得到的行人轮廓宽高比,提取该区域中高置信度的行人候选检测窗口,从而排除大量冗余的区域假设,完成对候选行人检测区域的精筛选,最后融合至DPM算法进行行人检测。结果 所提方法在PETS 2009 Bench-mark数据集上进行检测,实验结果表明,该方法对复杂背景下的检测有较强的稳定性,与传统DPM模型相比,精度提高了1.71%、平均对数漏检率降低2.2%、检测速度提高为3.7倍左右。结论 本文提出一种基于网格密度聚类的行人检测候选域生成算法,能够有效表达行人信息,与其他行人检测算法相比,有更好的精度和更快的速度,在检测率、检测时间方面均有提高,能够实现有效、快速的行人检测,具有实际意义。     

基于局部图块匹配的行人跟踪算法

针对传统行人跟踪算法计算复杂度高的问题,提出一种基于局部图块匹配（local block-graphs matching , LBGM ）的行人跟踪算法。利用摄像机采集视频流帧画面中含有行人的多幅视频图像,按照行人所在的图像区域进行分割;对图块进行数据关联匹配,通过匹配结果完成对行人的检测过程,得到检测的行人集合;针对行人集合,利用损失最小化进行最小偏差的路径预测,实现行人的跟踪过程。选取多相机行人视频（multi-camera pedestrians video ）进行对比实验,实验结果表明,该算法可以有效地跟踪行人,较传统算法有更好的行人检测率和跟踪准确率。     

煤矿井下行人检测算法

针对井下光照不均匀、行人特征与背景的相似度高等导致基于计算机视觉的行人检测技术在井下应用面临很大挑战的问题,提出采用Faster区域卷积神经网络(RCNN)进行煤矿井下行人检测。Faster RCNN行人检测算法采用区域建议网络(RPN)生成候选区域,RPN与Fast RCNN共享卷积层,以提高网络训练和检测速度;在图像特征提取过程中采用动态自适应池化方法对不同池化域进行自适应池化操作,提高了检测准确性。实验结果表明,该算法对于不同环境下图像中的行人均具有较好的检测效果。     

A bottom-up approach for delineating urban areas minimizing the connection cost of built clusters: Comparison with top-down-based densely inhabited districts

The main purpose of my research is to propose a consistent and bottom-up-based approach for delineating present and future urban areas on the foundation of investigating the relationship between delineating urban areas and the connection cost of built clusters. In my approach, optimal urban built clusters are defined as the delineation of urban areas by grouping buildings that satisfy the following rules based on the head/tail division rule: (1) the nearest neighbour distance from a building centroid is shorter than the criterion that can minimize the average total cost to provide public infrastructure (road networks); and (2) the size of grouped buildings (called an urban built cluster) is equal to or more than the mean of urban built cluster sizes. In the literature, the difference between optimal urban built clusters and densely inhabited districts (DIDs), a top-down-based approach, has not been analysed in detail. In replacing a top-down approach (DIDs) with a bottom-up one (e.g., the method proposed in this article), this difference needs to be evaluated. Therefore, the difference between DIDs and optimal urban built clusters was investigated. For the empirical study, I have selected Chiba prefecture, in the east of the Tokyo metropolitan region. Results show that (1) the overlapping relations of urban built clusters and DIDs can be distinguished based on their hierarchical levels; and (2) 55% of DIDs are optimal urban built clusters. However, the size of optimal urban built clusters that are not intersected by DIDs is the same as that of those intersected by DIDs. This poses to urban planners the important question of how to deal with two types of zones: zones overlapping not DIDs but optimal urban built clusters, and zones overlapping not optimal urban built clusters but DIDs.     

基于Vega的阀门虚拟仿真技术研究

阀门的虚拟仿真是系统虚拟仿真的一部分.通过对如何利用Creator对阀门进行建模的实现方法的讨论,建立了阀门虚拟仿真所需的三维模型.阀门的数学模型是阀门动态虚拟仿真的核心部分.通过对阀门运动和流体性质的分析,建立了其数学仿真模型.在阀门的虚拟仿真技术研究的基础上,利用Visual C＋＋和Vega程序建立了其仿真模块.同时为了展现阀门的结构原理,对阀门的虚拟拆分技术也进行了研究.阀门虚拟仿真所讨论的技术同样适用于系统其它部件的虚拟仿真,它和管道系统的其它组成部件的虚拟仿真一起构成了整个系统的虚拟仿真.     

面向业务的E-维护知识供应模型

为使E-维护中的知识支持维护任务,提出面向业务的知识供应模型。采用维护知识概念本体规范任务描述、维护对象和知识功能,通过知识对象本体集成知识资源。将知识供应的需求和权限集成到业务过程中,构建维护知识供应信息模型,建立知识匹配方法控制知识供应。在某石化企业E-维护平台上的应用结果表明,该模型能提升企业的维护水平。     

Automated concurrent engineering in Designworld

Designworld, an automated engineering system for digital circuits built from standard parts, is described. The system has integrated support for various phases in a product's life cycle, from design, through manufacture, to maintenance. The design for a product is entered into the system through a multimedia design workstation. The product is automatically built by a dedicated robotic cell. If necessary, the product, once built, can be returned to the system for automatic diagnosis and repair. Designworld's agent-based framework, implementation, and support of concurrent engineering are described     

Performance of RAID5 disk arrays with read and write caching

In this paper, we develop analytical models and evaluate the performance of RAID5 disk arrays in normal mode (all disks operational), in degraded mode (one disk broken, rebuild not started) and in rebuild mode (one disk broken, rebuild started but not finished). Models for estimating rebuild time under the assumption that user requests get priority over rebuild activity have also been developed. Separate models were developed for cached and uncached disk controllers. Particular emphasis is on the performance of cached arrays, where the caches are built of Non-Volatile memory and support write caching in addition to read caching. Using these models, we evaluate the performance of arrayed and unarrayed disk subsystems when driven by a database workload such as those seen on systems running any of several popular database managers. In particular, we assume single-block accesses, flat device skew and little seek affinity.With the above assumptions, we find six significant results. First, in normal mode, we find there is no difference in performance between subsystems built out of either small arrays or large arrays as long as the total number of disks used is the same. Second, we find that if our goal is to minimize the average response time of a subsystem in degraded and rebuild modes, it is better to use small arrays rather than large arrays in the subsystem. Third, we find the counter-intuitive result that if our goal is to minimize the average response time of requests to any one array in the subsystem, it is better to use large arrays than small arrays in the subsystem. We call this the best worst-case phenomenon.Fourth, we find that when no caching is used in the disk controller, subsystems built out of arrays have a normal mode performance that is significantly worse than an equivalent unarrayed subsystem built of the same drives. For the specific drive, controller, workload and system parameters we used for our calculations, we find that, without a cache in the controller and operating at typical I/O rates, the normal mode response time of a subsystem built out of arrays is 50% higher than that of an unarrayed subsystem. In rebuild mode, we find that a subsystem built out of arrays can have anywhere from 100% to 200% higher average response time than an equivalent unarrayed subsystem.Out fifth result is that, with cached controllers, the performance differences between arrayed and equivalent unarrayed subsystems shrink considerably. We find that the normal mode response time in a subsystem built out of arrays is only 4.1% higher than that of an equivalent unarrayed system. In degraded (rebuild) mode, a subsystem built out of small arrays has a response time 11% (13%) higher and a subsystem built out of large arrays has a response time 15% (19%) higher than an unarrayed subsystem.Our sixth and last result is that cached arrays have significantly better response times and throughputs than equivalent uncached arrays. For one workload, a cached array with good hit ratios had 5 times the throughout and 10 to 40 times lower response times than the equivalent uncached array. With poor hit ratios, the cached array is still a factor of 2 better in throughput and a factor of 4 to 10 better in response time for this same workload.We conclude that 3 design decisions are important when designing disk subsystems built out of RAID level 5 arrays. First, it is important that disk subsystems built out of arrays have disk controllers with caches, in particular Non-Volatile caches that cache writes in addition to reads. Second, if one were trying to minimize the worst response time seen by any user, one would choose disk array subsystems built out of large RAID level 5 arrays because of the best worst-case phenomenon. Third, if average subsystem response time is the most important design metric, the subsystem should be built out of small RAID level 5 arrays.     

基于贝叶斯网络的分层网络故障诊断

本文以SNMP网络管理模型的管理信息库（MIB）为基础,在不同层次上构建了用于故障判别与定位的贝叶斯网络。对MIB变量采用自适应自回归（AAR）模型建模分析,构建与其相关协议之间的贝叶斯网络,推断协议功能是否发生异常。分析各个协议之间的功能依赖关系,构建协议间的贝叶斯网络,定位协议间的故障根源。考虑网络中故障传播构建了基于网络拓扑的贝叶斯网,定位故障根源节点。最后,对构建的模型进行了实验仿真,并分析了模型的优点和缺点。     

嵌入式计算机应用于相控阵雷达机内测试设备的设计

介绍了嵌入式计算机应用于相控阵雷达机内测试设备的设计。叙述了机内测试设备和专用电子模块的组成 ,工作原理以及设计特点     

无线传感器网络单跳扩展增强树型路由协议研究

增强树型路由协议是最近提出的无线传感器网络路由协议,除了使用父子链路,当前路由决策节点通过和其一跳邻居节点之间建立增强链路形成比树型路由更短的路由捷径。为了尽可能多地发掘出潜在的路由捷径,提出了单跳扩展增强树型路由协议,该协议在增强树型路由协议的基础上把当前路由决策节点的单跳父亲节点和儿子节点及它们的邻居节点也考虑进路由决策过程中,可选路由捷径范围不再局限于当前路由决策节点及其一跳邻居之间的增强链路,而是向上扩展到其父亲节点及其一跳部居以及向下扩展到其儿子节点及其一跳邻居之间所形成的增强链路。该协议选择最短的路由捷径发送数据包。给出了单跳扩展增强树型路由协议的判定过程,并将该协议应用到ZigBee网络中。仿真结果显示,该协议在路由跳数和能量消耗这两项网络性能上比树型路由和增强树型路由均有提高。     

Sliding mode learning control for T-S fuzzy system and an application to hypersonic flight vehicle

Sliding mode-based learning control is presented for T-S fuzzy system. A T-S fuzzy model with both uncertainties and unmodeled dynamics is proposed firstly, in which the information of uncertainties and unmodeled dynamics are assumed to be unknown. Then, according to a given reference model, state-tracking error system is built. Respecting facts, the input matrices of the built T-S fuzzy model are different from each other. An extended state observer is built for estimating the unknown uncertainties and unmodeled dynamics, and a corresponding sliding surface is proposed. A learning controller is then presented for the closed loop system. Moreover, a numerical simulation result on hypersonic flight vehicles is considered to testify the controller's availability.     

IBI and CA Model based Extraction of Urban Built\|up Areaand Its Application：A Case Study in Shanghai

At present,the automatic extraction of urban built\|up area is still a problem.Taking Shanghai city as an example,this research uses the binary image,which was derived from an IBI(index\|based built\|up index)image,as the geographical cellular automaton initial input data.This was then imported to the extended cellular automata model for further processing.After a series of processing such as thresholding,corrosion and connectivity test,the urban built\|up area was simulated and can be extracted.Based on this method,the urban built\|up area of Shanghai in five different years between 1987 and 2015 was extracted using multi\|temporal Landsat images of Shanghai.In addition,the urban growth intensity index,the concentric buffers analysis and radar chart analysis were calculated and used to analysis spatiotemporal pattern of Shanghai urban expansion in the 28 study years.The result shows that the built\|up area of Shanghai was expanded from 195 km² in 1987 to 1759 km² in 2015,which is eight times as large as that in 1987.In the period between 1987 and 2002,the urban built\|up area expanded mainly along the North\|South axis of the Huangpu River.However,after 2002 the expansion rate was increased more quickly,and the direction of the expansion was shifted to an east to west direction.Generally speaking,Shanghai has experienced a rapid urban expansion in the recent three decades.