基于轮廓线特征的三维人脸识别改进算法

研究基于面部轮廓曲线特征的三维人脸识别。为提取最优面部曲线特征,提出一种基于模糊聚类方法的人脸曲线特征优选算法。该算法从三维人脸深度图中选取最具代表性的8条轮廓曲线,作为主要识别特征,这在很大程度上降低了计算复杂度,克服表情和光照对人脸识别的消极影响,同时它用最少的轮廓线包含了所需要的人脸识别信息。基于这些人脸轮廓线特征,利用改进的Manhattan距离分类器来提高人脸识别的分类效果。实验结果表明,所提出的算法明显提高了人脸识别率,并且具有很强的鲁棒性。     

大连金州线城轨车辆动态限界计算分析

城市轨道车辆交通限界计算是保证车辆安全的基本要素,为了提高车辆的安全性舒适性,降低轨道交通建设费用,本文以大连市金州线B2型车为例,介绍了城轨车辆限界和设备限界的计算方法,以期确定更为安全适用、经济合理的车辆轮廓线和车辆限界。     

自行车流视频识别判断方法研究

考虑算法的实时性,交通流个体识别往往采用轮廓特征来描述。由于自行车与行人的很多轮廓特征值相近,在复杂城市交通环境中,从慢行交通流中准确地识别出自行车是目前采用视频检测交通流的难点之一。通过现场视频检测获取足够的样本外轮廓数据,分析检测目标轮廓的高、宽、高宽比、面积等典型轮廓特征,发现目标轮廓高宽比特征能较好地识别出行人、自行车等慢行交通,并给出合适的取值范围。研究表明自行车高宽比能够较好地成为视频识别的依据,为自行车视频识别提供数据。     

时速160km以下双层集装箱运输铁路有砟轨道隧道内轮廓研究

目前运营时速160 km以下(双箱运输)有砟轨道隧道内轮廓难以满足大型养护机械(特别是大型清筛机)作业空间需求,通过对新建时速160 km以下电气化铁路(双箱运输)有砟轨道隧道的建筑限界、接触网悬挂方式及布置、大型养护机械空间需求、轨道结构形式、侧沟及电缆槽设置等内轮廓影响因素进行综合分析,确定单双线铁路有砟轨道隧道内轮廓控制性尺寸、拟定内轮廓方案,通过对各型内轮廓方案的结构安全性、经济性及施工便利性比较,给出推荐方案,为通用图编制和纳入规范奠定基础。     

图像边界检测区域对比度模糊增强算法在轮廓提取中的运用

分析了图像边界检测的区域对比度模糊增强算法的特点，通过实验验证了该算法的正确性和可行性，并指出了算法的一些不足之处和待改进的地方，提出了一种适用轮廓提取的新广义算子。     

利用ICCP的水下地磁修正惯导方法研究

迭代最近等值线算法（ICCP）是一种重要的地磁匹配导航算法。首先,为了获取相对精度较高的位置信息,又在一定程度上达到弥补实测数据精度不足的目的,将二次插值技术应用到地磁匹配算法中;然后,仿真计算得到了最佳匹配位置;最后,针对目前水下航行器通过航位推算等传统方法实现惯导重调的弊端,提出将地磁匹配位置误差作为观测量,用卡尔曼滤波对惯导系统的速度、位置和姿态误差进行最优估计。由最后仿真结果表明,以磁场匹配位置误差作为观测量来估计惯导误差是可行的。     

岩土介质中不良地质体轮廓探测技术研究

为解决埋深较大或地面条件复杂的地下工程开挖前方不良地质体轮廓探测不易从地面展开的难题,利用地震波"角度+位置"偏移的联合体系探测隧道施工前方不良地质体的形状,通过对地面地震波位置偏移法探测三维形状体的研究分析,论述地震波角度偏移在探测地下三维形状体的理论与重要作用,并借用人眼仿生学的原理进一步阐述角度偏移在地下工程前方探测的合理性与可行性。得出以下结论:角度偏移技术不需占用较大空间,非常适合地下工程开挖掌子面有限空间的前方不良地质体轮廓探测,利用"角度+位置"偏移的联合体系探测软弱岩体取得了很好的实际效果。     

A bintree energy approach for colour image segmentation using adaptive channel selection

A new hierarchical approach called bintree energy segmentation was presented for color image segmentation. The image features are extracted by adaptive clustering on multi-channel data at each level and used as the criteria to dynamically select the best chromatic channel, where the segmentation is carried out. In this approach, an extended direct energy computation method based on the Chan-Vese model was proposed to segment the selected channel, and the segmentation outputs are then fused with other channels into new images, from which a new channel with better features is selected for the second round segmentation. This procedure is repeated until the preset condition is met. Finally, a binary segmentation tree is formed, in which each leaf represents a class of objects with a distinctive color. To facilitate the data organization, image background is employed in segmentation and channels fusion. The bintree energy segmentation exploits color information involved in all channels data and tries to optimize the global segmentation result by choosing the ＂best＂ channel for segmentation at each level. The experiments show that the method is effective in speed, accuracy and flexibility.     

单洞4车道隧道内轮廓关键指标统计分析与启迪

现行公路隧道设计规范对单洞4车道隧道的构造和设计尚无明确规定。基于其内轮廓设计角度,并参考相关研究成果,提出应将扁平率作为其关键指标。同时,结合对已建成类似隧道工程内轮廓扁平率的统计分析结果,指出对于分离式双洞8车道或单洞4车道隧道,其内轮廓设计时,扁平率（不含仰拱）取0.485,扁平率（含仰拱）取0.605,矢跨比取0.406,具有较好的技术经济性,可为4车道公路隧道设计提供借鉴。     

Environmental lumping for efficient fatigue assessment of large-diameter monopile wind turbines

Fatigue damage is one of the governing factors for the design of offshore wind turbines. However, the full fatigue assessment is a time-consuming task. During the design process, the site-specific environmental parameters are usually condensed by a lumping process to reduce the computational effort. Preservation of fatigue damage during lumping requires an accurate consideration of the met-ocean climate and the dynamic response of the structure. Two lumping methods (time-domain and frequency-domain) have been evaluated for a monopile-based 10 MW offshore wind turbine, both based on damage-equivalent contour lines. Fatigue damage from lumped load cases was compared to full long-term fatigue assessment. The lumping methods had an accuracy of 94–98% for the total long-term fatigue damage and 90% for individual wind speed classes, for aligned wind and waves. Fatigue damage was preserved with the same accuracy levels for the whole support structure. A significant reduction of computational time (93%) was achieved compared to a full long-term fatigue assessment. For the cases with 30° and 60° wind-wave misalignment, there was a mean underestimation of approximately 10%. Variations in penetration depth did not affect the selection of the lumped sea-state parameters. This work presents a straightforward method for the selection of damage-equivalent lumped load cases, which can adequately preserve long-term fatigue damage throughout the support structure, providing considerable reduction of computational effort.