Review of techniques for motion capture data processing

In order to high reality and efficiency,the technique of motion capture (MoCap) has been widely used in the field of computer animation.With the development of motion capture,a large amount of motion capture databases are available and this is significant for the reuse of motion data.But due to the high degree of freedoms and high capture frequency,the dimension of the motion capture data is usually very high and this will lead to a low efficiency in data processing.So how to process the high dimension data and design an efficient and effective retrieval approach has become a challenge which we can’t ignore.In this paper,first we lay out some problems about the key techniques in motion capture data processing.Then the existing approaches are analyzed and summarized.At last,some future work is proposed.     

基于一般紧支撑小波的一类动态多尺度系统最优估计算法

This paper addresses the problem of dynamic multiscale system (DMS) estimation. Research achievements in the related area have been reported in the literature, but they either rely on the assumption of stationarity of the observed process or are difficult to be implemented. In this paper, a model of DMS that meets the requirements of the standard discrete time Kalman filtering is built and is realized by general compactly supported wavelet. The introduction of the state space projection equation and the augmentation of measurement equation are a major part of the novelty in our work. A theorem on the optimal filtering output at each scale is put forward. Experimental results are given to verify our methods0 superior performances.     

基于多传感器系统的光伏并网发电功率预测

针对耦合性较强的多维气象数据,在光伏(PV)多传感器系统中获取有效数据的基础上,提出了一种基于雾霾因素影响的数据挖掘光伏发电预测方法.利用多传感器采集大数据,利用逐步选择法对多维变量进行约减,有效降低了不同天气因素之间的耦合性.通过混合高斯聚类算法对样本进行聚类,并分别建立不同的径向基函数(RBF)神经网络模型,经过模糊推理的方法选择适当模型,实际预测结果验证了方法的高精度和实用性.     

Sensor fault diagnosis for a class of time delay uncertain nonlinear systems using neural network

In this paper, a sliding mode observer scheme of sensor fault diagnosis is proposed for a class of time delay nonlinear systems with input uncertainty based on neural network. The sensor fault and the system input uncertainty are assumed to be unknown but bounded. The radial basis function (RBF) neural network is used to approximate the sensor fault. Based on the output of the RBF neural network, the sliding mode observer is presented. Using the Lyapunov method, a criterion for stability is given in terms of matrix inequality. Finally, an example is given for illustrating the availability of the fault diagnosis based on the proposed sliding mode observer.     

Real-time control of human actions using inertial sensors

Our study proposes a new local model to accurately control an avatar using six inertial sensors in real-time.Creating such a system to assist interactive control of a full-body avatar is challenging because control signals from our performance interfaces are usually inadequate to completely determine the whole body movement of human actors.We use a pre-captured motion database to construct a group of local regression models,which are used along with the control signals to synthesize whole body human movement.By synthesizing a variety of human movements based on actors’control in real-time,this study verifies the effectiveness of the proposed system.Compared with the previous models,our proposed model can synthesize more accurate results.Our system is suitable for common use because it is much cheaper than commercial motion capture systems.     

Optimizing radial basis function neural network based on rough sets and affinity propagation clustering algorithm

A novel method based on rough sets (RS) and the affinity propagation (AP) clustering algorithm is developed to optimize a radial basis function neural network (RBFNN). First, attribute reduction (AR) based on RS theory, as a preprocessor of RBFNN, is presented to eliminate noise and redundant attributes of datasets while determining the number of neurons in the input layer of RBFNN. Second, an AP clustering algorithm is proposed to search for the centers and their widths without a priori knowledge about the number of clusters. These parameters are transferred to the RBF units of RBFNN as the centers and widths of the RBF function. Then the weights connecting the hidden layer and output layer are evaluated and adjusted using the least square method (LSM) according to the output of the RBF units and desired output. Experimental results show that the proposed method has a more powerful generalization capability than conventional methods for an RBFNN.     

适用于惯性动作捕捉与复现系统的轨迹捕捉算法及其实现

针对惯性动作捕捉与复现系统轨迹捕捉过程中由于零速检测不准确、姿态角误差发散造成捕捉到的轨迹不够平滑进而导致动画复现过程中人体模型发生严重抖动甚至位置跳变的问题,提出了一种基于改进零速检测的轨迹捕捉算法,可得到较高平滑度的轨迹.本文结合试验分析了零速检测误检源,并根据拉依达准则优化了检测算法,在此基础上构建了完整的轨迹捕捉Kalman滤波算法框架,其内嵌的姿态深度修正模块可有效抑制姿态角误差发散.最后通过实物试验,从精度和稳定性两方面验证了轨迹捕捉算法的可行性,试验表明,本文所述轨迹捕捉算法能得到较高平滑度的行走轨迹,因此能在一定程度上减小动画复现过程中人体模型的抖动,具有重要的工程意义.     

Dynamical pattern recognition for univariate time series and its application to an axial compressor

In this paper, a learning and recognition approach is proposed for univariate time series composed of output measurements of general nonlinear dynamical systems. Firstly, a class of dynamical systems in the canonical form is derived to describe the univariate time series by introducing coordinate transformation. An observer-based deterministic learning technique is then adopted to achieve dynamical modeling of the associated transformed systems of the training univariate time series, and the modeling results in the form of radial basis function network (RBFN) models are stored in a pattern library. Subsequently, multiple observer-based dynamical estimators containing the RBFN models in the pattern library are constructed for a test univariate time series, and a recognition decision scheme is proposed by the derived recognition indicator. On this basis, more concise recognition conditions are provided, which is beneficial for verifying the recognition results. Finally, simulation studies on the Rossler system and aero-engine stall warning verify the effectiveness of the proposed approach.     

基于改进GA-PSO的可重构测试资源匹配方法

为提高测点信号与可重构测试资源匹配效率,建立了基于STD标准的测点信号与可重构测试资源的数学描述模型.针对可重构测试资源的特点,结合工程实际提出了基于Sigmoid函数的匹配函数,以资源可靠性、配置文件大小及配置时间因子作为罚函数,利用匹配函数构造出遗传算法的适应度函数.为解决遗传算法搜索速度较慢的问题,改进了遗传算法的选择算子和交叉算子,将粒子群算法应用到遗传算法中,解决了遗传算法在算法后期迭代效率低下的问题,最后通过实例验证了算法的有效性.     

基于ARM与MPU6050的测姿系统设计

以ARM-LPC1788为核心的嵌入式芯片平台,采用9轴运动处理传感器MPU6050,通过对数字运动处理(DMP)数据库的成功移植,经由四元数解算得到准确、可靠的数据;采用广义延拓插值模型对数据进行优化处理以消除抖动误差,使最终姿态值更加稳定.测试结果表明:系统能够实时采集当前装置的准确姿态信息,测量偏差小于0.1°,且能够稳定可靠的工作,为需要姿态信息的嵌入式系统提供了更加稳定准确的参考标准.     

紧支径向基函数插值实现多维数据可视化

通过分析某城市空气质量数值预报数据的时空组织结构,构建出了多维空间数据的整体框架。论述了几种插值方法的优缺点,在比较的基础上,将新的紧支径向基函数局部径向点插值方法引入到多维数据处理中,在空间、时间维度上对数据进行局部插值,从而实现数据的重构。以新的基于封装回调函数的多线程方法实现了大规模空气质量预报数据的三维动态可视化。实验结果表明,以上方法应用于大规模数据可视化时,其质量和运算速度都能满足实际需要。     

联合紧支径向基函数和微分进化算法的电磁优化方法

针对工程电磁装置的优化设计问题,提出一种基于紧支径向基函数的近似模型和改进微分进化算法的组合优化方法。利用基于紧支径向基函数的近似模型得到多维设计空间中构造复杂目标函数和约束函数的显式函数关系。结合改进的微分进化算法获得精确度较高的全局最优解。实例分析和比较表明新方法的收敛速度和优化效率相对于其他的随机类优化算法和模型有明显的优势。     

一种径向基函数插值的ENO格式

将ENO格式和径向基函数插值相结合,提出了求解双曲型偏微分方程的径向基函数插值的ENO方法。该方法依据ENO思想建立自适应模板,在选定的模板上利用径向基函数进行逼近,能够很好地处理具有间断解的问题,消除间断点处数值振荡现象。以一维双曲型偏微分方程为例,对该方法进行了验证,并通过与多项式ENO格式比较,表明该方法更具有优势。     

基于径向基点插值的Chan-Vese模型图像分割算法

基于水平集方法的Chan-Vese模型是一种典型的几何活动轮廓模型,已成功应用于众多领域中的图像分割问题。为了提高该模型的演化速度和分割效果,提出了一种基于径向基点插值求解Chan-Vese模型的高效数值算法。通过用径向基点插值法逼近水平集函数,Chan-Vese模型被离散为常微分方程组初值问题并可用向前Euler法求解。该算法不需要网格单元,对水平集初始轮廓不敏感,不涉及复杂费时的重新初始化过程,并且有明确的演化终止条件,无需事先设置演化次数。实验表明该算法在没有初始轮廓时也能正确分割图像,具有很快的演化速度。     

基于Matlab的径向基函数数值计算软件包

为推动基于无网格方法的计算软件的发展,介绍基于Matlab自主开发的径向基函数（Radial Basis Function,RBF）数值计算软件包,阐述软件的理论基础、设计思路以及该软件包的功能和特点,并结合边界节点法（Boundary Knot Method,BKM）的数值实例给出软件的使用过程．该软件包可以根据不同的数学物理模型选择合适的数值算法来求解多种实际物理问题,也可对不同数值算法得到的结果进行比较．最后,总结应用Matlab进行数值计算软件开发的优缺点．     

基于径向基函数网络的SFS算法研究

分析了现有从明暗恢复形状(SFS)的几种方法普遍存在对恢复的形状的连续性和光滑性的缺点,提出了一种基于径向基函数网络模型进行从明暗恢复形状的新算法。该算法先采用网络构造一个曲面方程,再利用反射函数作为约束条件,通过调整权因子和径向基函数中心和宽度对网络进行自学习,得到一个满意的曲面方程。理论和实验证明,该算法在恢复形状的准确性和曲面的光滑性,连续性上有较大改进。     

基于径向基函数网络的浮游植物活体三维荧光光谱分类

将小波变换与神经网络相结合,对浮游植物活体的三维荧光光谱进行分类．首先利用小波变换对数据进行压缩,然后利用径向基函数（Radial Basis Function,RBF）神经网络对光谱曲线进行逼近,从而进行物种的识别,平均识别率高达95．8％．结果表明,该方法较传统的统计方法更方便、准确率更高．     

基于径向基函数网络的FBG传感光谱的重构

针对光纤Bragg光栅(FBG)解调系统中由于传感器部分脱粘、数据采集的量化误差引起的系统性能的非理想性,FBG反射回的光谱会发生失真。如果直接利用峰值检测法进行波长检测,存在较大的检测误差。于是便提出了用径向基函数网络(RBFN)拟合光纤光栅反射后的失真光谱的方法,此法与峰值检测法、高斯曲线拟合法相比,能够更大程度地减小波长检测的误差,提高解调的精度,并且,能够对多个光栅光谱进行重构。     

基于增强径向函数神经网络的错误定位方法

结合径向基函数神经网络与正交实验设计理论,提出了一种增强径向基函数神经网络错误定位算法.根据选择的测试用例执行得到源程序的语句覆盖信息和执行结果;通过神经网络计算出每条语句的可疑度值,并通过正交实验设计方法自适应调整神经网络中的参数值;最后按照可疑度值由高到低的顺序逐条检查程序的可疑语句进行错误定位.通过实验对所提出方法与径向基函数神经网络算法以及反向传播神经网络算法进行比较分析,结果表明,基于增强径向基函数神经网络算法具有更精确的错误定位效果和更显著的定位效率.     

基于离散余弦变换基函数迭代的人脸图像识别

使用非线性混沌方法处理与识别图像的研究工作逐渐增多,已有文献给出了一种 将正弦函数作为辅助函数与图像构造动力系统,迭代生成混沌吸引子作为图像特征。为进一步 探究图像吸引子作为图像的特性,改进识别效果,使用离散余弦变换(DCT)基函数矩阵代替正 弦函数,迭代生成近似混沌吸引子,用于人脸识别。首先,研究分析了DCT 基函数矩阵的多样 性与振荡特性;然后利用DCT 基函数矩阵与图像矩阵构造迭代表达式,通过给出的迭代算法使 其产生吸引子,再对吸引子进行快速傅里叶变换,计算相关系数,识别人脸图像。对于Yalefaces 图像库,每幅图像都参加训练,识别率可以达到100%,当使用每组前5 幅图像训练提取特征, 识别率可以超过85%;对于CMU PIE 数据库,每幅图像都参加训练,识别率可以超过99%。 该吸引子方法可以作为一种图像底层特征提取方法,有待于进一步深入研究。