基于虚拟手的人机交互关键技术

基于虚拟手的人机交互技术是虚拟现实中的研究热点。对其中的关键技术进行了研究,采用多边形网格建模方法,建立了虚拟手的逼真几何模型;基于Virtools平台开发了数据手套的数据采集模块,提出使用基于初始值的数据转换方法,解决了开始运动时的跳变问题,同时对手指的外展运动,使用约束值方法进行处理,提高了虚拟手与真实人手匹配一致性;最后,针对虚拟手与虚拟物体的操作交互,提出了一种基于有效阈值角度的抓取算法。通过Virtools平台进行验证,实验结果表明:虚拟手模型逼真度高,手型变化自然;同时实现了虚拟手对虚拟物体的操作交互,具有很强的实用性。     

A three-dimensional anthropometric solid model of the hand based on landmark measurements

Hand anthropometry data are largely based on measurements of the hand in an outstretched hand posture and are, therefore, difficult to apply to tool gripping hand postures. The purpose of this project was to develop a representative, scalable hand model to be used with 3-D software drawing packages to aid in the ergonomic design of hand tools. Landmarks (66) on the palmar surface of the right hand of 100 subjects were digitised in four functional hand postures and, from these, 3-D surface models of a mean, 25th and 75th% hand were developed. The root mean square differences in hand length between the hand model and the digitised data for the 25th, 50th and 75th percentile hand were 11.4, 3.2 and 8.9 mm, respectively. The corresponding values for hand breadth were 2.0, 0.4 and 1.4 mm. There was good agreement between distances on the digitised hand and the hand model. The application of this research includes improved ergonomic hand tool design through the use of hand anthropometry reference values developed from the general population using grasping hand postures.     

A three-dimensional anthropometric solid model of the hand based on landmark measurements

Hand anthropometry data are largely based on measurements of the hand in an outstretched hand posture and are, therefore, difficult to apply to tool gripping hand postures. The purpose of this project was to develop a representative, scalable hand model to be used with 3-D software drawing packages to aid in the ergonomic design of hand tools. Landmarks (66) on the palmar surface of the right hand of 100 subjects were digitised in four functional hand postures and, from these, 3-D surface models of a mean, 25th and 75th% hand were developed. The root mean square differences in hand length between the hand model and the digitised data for the 25th, 50th and 75th percentile hand were 11.4, 3.2 and 8.9 mm, respectively. The corresponding values for hand breadth were 2.0, 0.4 and 1.4 mm. There was good agreement between distances on the digitised hand and the hand model. The application of this research includes improved ergonomic hand tool design through the use of hand anthropometry reference values developed from the general population using grasping hand postures.     

Exploratory spatio-temporal visualization: an analytical review

Current software tools for visualization of spatio-temporal data, on the one hand, utilize the opportunities provided by modern computer technologies, on the other hand, incorporate the legacy from the conventional cartography. We have considered existing visualization-based techniques for exploratory analysis of spatio-temporal data from two perspectives: (1) what types of spatio-temporal data they are applicable to; (2) what exploratory tasks they can potentially support.The technique investigation has been based on an operational typology of spatio-temporal data and analytical tasks we specially devised for this purpose. The result of the study is a structured inventory of existing exploratory techniques related to the types of data and tasks they are appropriate for. This result is potentially helpful for data analysts—users of geovisualization tools: it provides guidelines for selection of proper exploratory techniques depending on the characteristics of data to analyze and the goals of analysis. At the same time the inventory as well as the suggested typology of tasks could be useful for tool designers and developers of various domain-specific geovisualization applications. The designers can, on the one hand, see what task types are insufficiently supported by the existing tools and direct their creative activities towards filling the gaps, on the other hand, use the techniques described as basic elements for building new, more sophisticated ones. The application developers can, on the one hand, use the task and data typology in the analysis of potential user needs, on the other hand, appropriately select and combine existing tools in order to satisfy these needs.     

虚拟手的远程控制实现

针对远程控制虚拟手传输数据量大,容易丢包和出现时延的情况,提出了一种基于行为数据库的参数传递方法。利用3DS MAX软件对虚拟手建模并用OpenGL在PC机上显示;将手势数据测量装置采集的手势原始数据转化成虚拟手的运动角度参数后,以一定的结构形式储存并编号,建立对应的手势行为数据库;通过传输参数编号代替直接传输手势数据降低传输数据量;通过在传输协议中加入打包序号的方式解决由于传输路径不同带来的虚拟手显示时出现的“帧倒序”现象。真实手和虚拟手的匹配实验结果表明数据传输准确、时延低。     

基于Kinect深度信息与骨骼信息的手指尖识别方法

针对基于视频的手势识别技术对手掌轮廓和指尖信息要求较高的问题,提出了一种基于图像深度信息和人体骨骼信息的手指指尖识别方法和手掌轮廓检测算法。采用微软Kinect摄像头获取深度信息和人体骨骼信息,并将每个骨骼点的三维信息转换成深度图上的二维信息。根据人体骨骼信息快速找到手掌的位置,并利用基于深度阈值的轮廓检测算法将手掌轮廓和弯曲手指轮廓从背景图像中分割出来。利用k曲率算法检测到手指指尖的位置。实验结果证明,该方法可以高效地检测出伸直和弯曲手指的轮廓,识别出人体的手指,并且该方法可在黑暗的环境下进行。     

基于SURF特征跟踪的动态手势识别算法

提出了一种基于加速鲁棒特征(SURF)跟踪的动态手势识别算法.其特征在于算法无需预先检测分割人手区域,仅通过跟踪统计相邻帧间匹配SURF特征点的移动主方向来刻画手势运动轨迹.提出采用经时间规整的轨迹方向数据流来建立动态手势模型,利用基于相关分析的数据流聚类方法实现动态手势的识别,大大提高动态手势识别速度.实验使用26个英文字母作为动态手势训练和识别,手势训练集和测试集的识别率分别为87.1%和84.6%,并成功用于实验室自主研制的侦察移动机器人Hunter的运动控制中,证实了该方法的有效性.     

五指形仿人机械手的设计与实现及示教

设计和实现了一个具有五个手指和手掌的仿人机械手（以下简称仿人机械手）,并利用数据手套对其进行了示教,使其能有效地完成复杂的作业。首先,以现有的仿人机械手研究成果为基础,对仿人机械手进行了优化设计和实现;然后,以数据手套为示教源,对仿人机械手示教模型进行了研究,采用D-H变换矩阵建立了仿人机械手的逆向运动学,解决了示教运动映射问题。最后,利用仿人机械手进行了若干作业实验,实验结果证明了仿人机械手及其示教模型的正确性。     

基于神经网络的手势识别

本文在对手结构和关节运动作了深入分析的基础上, 建立了对其施加约束的手模型．根据所定义的约束及运动类型,建立了适合于手势合成的手 数据结构．并采用神经网络理论进行手势识别,取得了较好的效果．     

Intelligent Biometric Group Hand Tracking (IBGHT) database for visual hand tracking research and development

With the increase of innovations in vision-based hand gesture interaction system, new techniques and algorithms are being developed by researchers. However, less attention has been paid on the scope of dismantling hand tracking problems. There is also limited publicly available database developed as benchmark data to standardize the research on hand tracking area. For this purpose, we develop a versatile hand gesture tracking database. This database consists of 60 video sequences containing a total of 15,554 RGB color images. The tracking sequences are captured in different situations ranging from an easy indoor scene to extremely high challenging outdoor scenes. Complete with annotated ground truth data, this database is made available on the web for the sake of assisting other researchers in the related fields to test and evaluate their algorithms based on standard benchmark data.     

分布式仿真系统中的数据传输研究

为提高分布式仿真系统内部有效数据传输效率,满足系统实时性要求,以车辆定位监控仿真系统为问题原型,提出一种基于运行时间支撑系统数据分发管理(RTI-DDM)和套接字(Socket)的双层数据传输模型.该模型一方面利用RTI-DDM来限定传输数据的范围,有效降低系统内部冗余数据的传输;另一方面,利用Socket技术在仿真实体之间建立点对点的直接传输,从而提高系统的运行效率.对比实验结果表明,在相同仿真交互数据量下,该模型相对于传统RTI数据传输模型,数据传输延时平均缩短50%.     

Hand number gesture recognition using recognized hand parts in depth images

In this paper, we present a novel approach of recognizing hand number gestures using the recognized hand parts in a depth image. Our proposed approach is divided into two stages: (i) hand parts recognition by random forests (RFs) and (ii) rule-based hand number gestures recognition. In the first stage, we create a database (DB) of synthetic hand depth silhouettes and their corresponding hand parts-labeled maps and then train RFs with the DB. Via the trained RFs, we recognize or label the hand parts in a depth silhouette. In the second stage, based on the information of the recognized or labeled hand parts, hand number gestures are recognized according to our derived rules. In our experiments, we quantitatively and qualitatively evaluated our hand parts recognition system with synthetic and real data. Then, we tested our hand number gesture recognition system with real data. Our results show the average recognition rate of 97.80 % over the ten hand number gestures from five different subjects.     

基于局部和全局的特征提取算法及在人脸识别中的应用

提出了一种基于局部和全局特征的特征提取算法.该算法不仅能保持数据集的局部性,同时也考虑了数据集的全局性,使得降维后的数据既能保持邻近关系,又能从整体上较好地重构和展现.PCAO能较好地展现原数据集,LPP能保持局部邻近关系,算法结合了这两个算法的思想,但由于LPP没有考虑类别信息,故先对LPP进行改进,给出了一种有监督的局部保持投影算法,使得提出的算法能更加有利于分类问题.通过人脸识别实验,验证了算法的正确性和有效性.     

基于卷积神经网络的Leap Motion运动数据优化网络

为提高Leap Motion设备的采集精准度,解决自遮挡、采样频率不稳定等设备固有问题,首先,设计了使用Leap Motion和动作捕捉设备的手部多模态同步运动采集方案,采集了日常动作数据集;其次,提出了基于卷积神经网络(convolutional neural network,CNN)的Leap Motion手部运动数据优化方法,使用日常动作数据集训练Leap Motion数据到动作捕捉数据的映射网络;最后,提出手指平面约束,确保网络输出数据保持稳定的手部骨骼结构.通过15名志愿者采集了6类动作共967550帧的同步运动数据集,进行了手指平面约束有效性、动作一致性实验,并与双向循环自编码器(bidirectional recurrent autoencoder,BRA)、双向编解码器(encoder-bidirectional-decoder,EBD)方法进行了精度对比.结果表明,文中方法支持使用Leap Motion获取固定采样频率且近似动捕设备精度的手部运动数据,效果较BRA和EBD更加稳定平滑.将文中方法应用于康复游戏中,明显减少了交互动作识别的错误次数.     

基于RGBD数据的静态手势识别

提出一种基于RGBD数据的手势识别方法,首先采用融合深度信息和彩色信息的手势分割算法分割出手势区域;其次提取静态手势轮廓的圆形度、凸包点及凸缺陷点、7Hu矩特征组成特征向量;最后采用SVM进行静态手势识别。实验结果表明,该方法能有效地识别预定义的5种静态手势,且对环境的适应性比较强。     

上海市资源与环境数据共享平台的实现

提出一种基于元数据和Web services的分布式异构数据共享技术方案,通过元数据实现对分布式数据的集中描述和管理,利用Web services标准化处理并获取异构数据。该方案已成功应用于上海市资源与环境数据共享平台,有效解决了分布式异构数据的共享问题,提高了数据的利用效率。     

Large-scale multiview 3D hand pose dataset

Accurate visual hand pose estimation at joint level has several applications for human-robot interaction, natural user interfaces and virtual/augmented reality applications. However, it is still an open problem being addressed by the computer vision community. Recent novel deep learning techniques may help circumvent the limitations of standard approaches. However, they require large amounts of accurate annotated data.Hand pose datasets that have been released so far present issues such as limited number of samples, inaccurate data or high-level annotations. Moreover, most of them are focused on depth-based approaches, providing only depth information (missing RGB data).In this work, we present a novel multiview hand pose dataset in which we provide hand color images and different kind of annotations for each sample, i.e. the bounding box and the 2D and 3D location on the joints in the hand. Furthermore, we introduce a simple yet accurate deep learning architecture for real-time robust 2D hand pose estimation. Then, we conduct experiments that show how the use of the proposed dataset in the training stage produces accurate results for 2D hand pose estimation using a single color camera.     

一种区间型数据的自适应模糊c均值聚类算法

针对区间型数据的聚类问题,提出一种自适应模糊c均值聚类算法。该算法一方面基于区间数的中点和半宽度,通过引入区间宽度的影响因子以控制区间大小对聚类结果的影响;另一方面通过引入一个自适应系数,以减少区间型数据的数据结构对聚类效果的影响。通过仿真数据和Fish真实数据验证了该算法的有效性,并对聚类结果进行比较和分析。     

一种基于平行坐标的度量模型及其应用

分析了数据挖掘中可视化技术应用的特点与方法,给出了数据挖掘中可视对象与参数的确定及算法分解的方法,提出了一种基于平行坐标技术的度量指标体系,证明了其中的相关性质与结论,并给出基于平行坐标技术的度量模型以及在实验数据上的应用例.结果表明这种方法对于数据挖掘中的数据可视化表示是有效的.基于度量指标的可视化技术在对可视对象的分析处理上可以借助适用的数学方法建模与评测,这有助于数据挖掘可视化的研究与应用.     

基于LeapMotion的个体化手部建模与实时交互

虚拟人手的实时建模是以人机交互为核心的VR/AR系统中的重要技术难点，传统的基于LeapMotion的手部跟踪视觉反馈仅展示骨架动画信息，缺少应用演示的真实感。由此，提出了一个快速高效的个体化手部建模与实时交互系统，重点阐述了该系统的的工作原理以及算法。以含有骨架信息的静止手模型为模板，使用LeapMotion跟踪用户手的骨架数据作为输入，提出了基于骨骼尺寸的手部模型自动个体化建模算法。提供了一种基于不完整骨骼运动数据的线性蒙皮技术的改进算法，可快速计算不同手部姿势下骨架之间的变换矩阵，动态更新虚拟手的姿势。实验结果表明，此系统在实验的硬件平台上运行速度可以达到60 f/s，误差稳定在4 mm以内，能为人机交互任务实时提供真实可靠的视觉反馈。