Monocular head pose estimation using generalized adaptive view-based appearance model

Accurately estimating the person’s head position and orientation is an important task for a wide range of applications such as driver awareness, meeting analysis and human-robot interaction. Over the past two decades, many approaches have been suggested to solve this problem, each with its own advantages and disadvantages. In this paper, we present a probabilistic framework called Generalized Adaptive View-based Appearance Model (GAVAM) which integrates the advantages from three of these approaches: (1) the automatic initialization and stability of static head pose estimation, (2) the relative precision and user-independence of differential registration, and (3) the robustness and bounded drift of keyframe tracking. In our experiments, we show how the GAVAM model can be used to estimate head position and orientation in real-time using a simple monocular camera. Our experiments on two previously published datasets show that the GAVAM framework can accurately track for a long period of time with an average accuracy of 3.5° and 0.75 in. when compared with an inertial sensor and a 3D magnetic sensor.     

基于矩阵李群表示及容积卡尔曼滤波的视觉惯导里程计新方法

针对滤波方法实现的视觉-惯导里程计(VIO)问题,为更准确传递旋转运动的不确定性并降低系统线性化误差,提高位姿估计的精度,设计并实现了一种高维矩阵李群表示的采用容积卡尔曼滤波框架实现的VIO算法.算法将状态变量构建为一个高维李群矩阵,并定义了李群变量在容积点采样过程中的‘加法’运算,将容积点和状态均值、方差等概念由欧氏空间扩展到流形空间;采用容积变换传递状态均值及方差,避免了旋转运动复杂的雅克比矩阵计算过程,降低了模型线性化误差.最后,使用EuRoc MAV数据集进行算法验证,结果表明所提出算法在提高位姿估计精度方面是有效的.     

基于波浪式矩阵置换的稀疏度均衡分块压缩感知算法

基于矩阵置换的分块压缩感知（BCS）引入矩阵置换的策略,使复杂子块和稀疏子块向介于两者中间的稀疏度水平变化,用单一采样率采样时可以减少块效应,但仍存在块间稀疏度均衡效果较差的问题。为了得到更好的重构效果,提出基于波浪式矩阵置换的稀疏度均衡BCS（BCS-RMP）算法。首先,在采样前对图像进行矩阵置换的预处理,通过波浪式置换矩阵对图像各子块的稀疏度进行均衡;然后,采用相同的测量矩阵对子块进行采样,在解码侧进行重构;最后,通过波浪式置换逆矩阵对重构结果进行逆变换得到最终的重构图像。仿真结果表明,与现有矩阵置换算法相比,当选择合适的子块大小和采样率时,所提波浪式矩阵置换算法可有效提高图像的重构质量,且能更准确地体现细节信息。     

Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Tracking

In this article we present the integration of 3-D shape knowledge into a variational model for level set based image segmentation and contour based 3-D pose tracking. Given the surface model of an object that is visible in the image of one or multiple cameras calibrated to the same world coordinate system, the object contour extracted by the segmentation method is applied to estimate the 3-D pose parameters of the object. Vice-versa, the surface model projected to the image plane helps in a top-down manner to improve the extraction of the contour. While common alternative segmentation approaches, which integrate 2-D shape knowledge, face the problem that an object can look very differently from various viewpoints, a 3-D free form model ensures that for each view the model can fit the data in the image very well. Moreover, one additionally solves the problem of determining the object’s pose in 3-D space. The performance is demonstrated by numerous experiments with a monocular and a stereo camera system.     

一种鲁棒高效的人脸特征点跟踪方法

人脸特征点跟踪能获取除粗略的人脸位置和运动轨迹以外的人脸部件的精确信息,对计算机视觉研究有重要作用.主动表象模型(Active appearance model, AAM)是描述人脸特征点位置的最有效的方法之一,但是其高维参数空间和梯度下降优化策略使得AAM对初始参数敏感,且易陷入局部极值. 因此,基于传统AAM的人脸特征点跟踪方法不能同时较好地解决大姿态、光照和表情的问题.本文在多视角AAM的框架下,提出一种结合随机森林和线性判别分析(Linear discriminate analysis, LDA)的实时姿态估计算法对跟踪的人脸进行姿态预估计和更新,从而有效地解决了视频人脸大姿态变化的问题.提出了一种改进的在线表象模型(Online appearance model, OAM)方法来评估跟踪的准确性,并自适应地通过增量主成分分析(Principle component analysis, PCA) 学习来更新AAM的纹理模型,极大地提高了跟踪的稳定性和模型应对光照和表情变化的能力.实验结果表明,本文算法在视频人脸特征点跟踪的准确性、鲁棒性和实时性方面都有良好的性能.     

Prediction error identification of linear systems: A nonparametric Gaussian regression approach

A novel Bayesian paradigm for the identification of output error models has recently been proposed in which, in place of postulating finite-dimensional models of the system transfer function, the system impulse response is searched for within an infinite-dimensional space. In this paper, such a nonparametric approach is applied to the design of optimal predictors and discrete-time models based on prediction error minimization by interpreting the predictor impulse responses as realizations of Gaussian processes. The proposed scheme describes the predictor impulse responses as the convolution of an infinite-dimensional response with a low-dimensional parametric response that captures possible high-frequency dynamics. Overparameterization is avoided because the model involves only a few hyperparameters that are tuned via marginal likelihood maximization. Numerical experiments, with data generated by ARMAX and infinite-dimensional models, show the definite advantages of the new approach over standard parametric prediction error techniques and subspace methods both in terms of predictive capability on new data and accuracy in reconstruction of system impulse responses.     

Revisiting parallel cyclic reduction and parallel prefix-based algorithms for block tridiagonal systems of equations

Direct solvers based on prefix computation and cyclic reduction algorithms exploit the special structure of tridiagonal systems of equations to deliver better parallel performance compared to those designed for more general systems of equations. This performance advantage is even more pronounced for block tridiagonal systems. In this paper, we re-examine the performances of these two algorithms taking the effects of block size into account. Depending on the block size, the parameter space spanned by the number of block rows, size of the blocks and the processor count is shown to favor one or the other of the two algorithms. A critical block size that separates these two regions is shown to emerge and its dependence both on problem dependent parameters and on machine-specific constants is established. Empirical verification of these analytical findings is carried out on up to 2048 cores of a Cray XT4 system.     

利用结构化SVM结合CNN的层次化目标检测与人体姿态估计方法

针对现有姿态估计方法不能准确提取特征参数的问题,提出了一种基于结构化支持向量机(SSVM)与卷积神经网络(CNN)的层次化模型。首先,展示了一个基于PS部件模型的SSVM如何实现为一个两层的神经网络,其中第一层是卷积层,另一层是损失增强推理层;通过将模型的结构化形式转换为模型中的一个神经网络,提出方法可以同时学习结构模型和外观模型,同时反向传播误差以学习底层的可学习参数,这些参数可从外观模型特征中提取出来;最后,将SSVM模型转换为神经网络模型,将误差反向传播到较低层,并计算确切的SSVM损失,同时通过基于次梯度的方法来学习原始SSVM。将该模型与当前较为先进的识别模型进行了对比,结果证明提出的层次化模型的识别成功率比对比方法平均高6%,具有更强的识别性能。     

分布式目标位姿跟踪的序列无关融合估计方法

针对传统目标位姿跟踪在处理旋转运动时导致估计精度低和稳定性差的问题, 提出一种分布式目标位姿跟踪的序列无关融合估计方法. 首先, 在矩阵李群上构建状态和不变误差的动态方程, 并将系统误差状态转移矩阵与估计状态解耦, 更精确地描述和处理旋转运动中的不确定性, 以提高滤波器的鲁棒性; 然后, 考虑到融合序列的随机性, 设计基于李群的序列无关融合策略, 使得在任意融合序列条件下均可在李群上进行有效地数据融合, 确保全局估计的一致性; 最后, 通过仿真和实验验证所提出方法的有效性和优越性.     

Identification methods in a unified framework

The paper derives a framework suitable to discuss the classical Koopmans-Levin (KL) and maximum likelihood (ML) algorithms to estimate parameters of errors-in-variables linear models in a unified way. Using the capability of the unified approach a new parameter estimation algorithm is presented offering flexibility to ensure acceptable variance in the estimated parameters. The developed algorithm is based on the application of Hankel matrices of variable size and can equally be considered as a generalized version of the KL method (GKL) or as a reduced version of the ML estimation. The methodology applied to derive the GKL algorithm is used to present a straightforward derivation of the subspace identification algorithm.     

融合HOG和颜色特征的人体姿态估计新算法

为解决现有人体姿态估计算法在处理光照条件很差或颜色对比度很低的待处理图像时估计准确度较低的问题,利用梯度方向直方图（HOG）和颜色特征建立了一种的基于可能性C（PCM）聚类算法部位外观模型,提出了一种新的融合HOG特征和颜色特征的人体姿态估计算法。算法根据待处理图像自动选择部位外观模型,若图像的光照条件和颜色对比度都较好则选择现有的基于HOG和颜色特征融合的部位外观模型,否则选择基于PCM聚类算法的部位外观模型。仿真实验表明所建立的部位外观模型能更准确地描述光照条件很差或颜色对比度很低的图像中下真实人体部位的外观,提出的人体姿态估计算法对各种类型的待处理图像均能得到准确度更高的估计结果。     

基于三维模型的人脸姿态估计方法

提出一种三维人脸姿态估计方法。该方法通过估计三维平面人脸模型到图像平面的单应矩阵来获得人脸相对于摄像机坐标系的旋转矩阵,并利用M-估计优化方法迭代求精。其主要特点是：实施简单,不需要对透视摄像机参数预先进行标定,能够在较大范围内较精确地估计人脸姿态。对模拟数据及真实人脸图像的实验均验证了该方法的有效性。     

基于R-SVM与SVDD的部位外观模型

为克服现有基于HOG特征的部位外观模型未考虑不同细胞单元的不同作用以及不能准确表征相似度的缺陷,提出了一种基于递归支持向量机(R-SVM)和支持向量数据描述(SVDD)算法的人体部位外观模型.所提外观模型由两个分类器构成,利用R-SVM进行特征选择并建立的分类器用于判断图像某区域是否属于人体部位类,利用SVDD建立的相似度分类器用于计算属于人体部位类的图像区域与外观模型的相似度.将所提部位外观模型用于人体上半身姿态的估计,仿真实验结果显示其比现有部位外观模型的估计准确度更高,表明所提部位外观模型可以更准确地描述真实人体部位.     

Learning a Mahalanobis distance metric for data clustering and classification

Distance metric is a key issue in many machine learning algorithms. This paper considers a general problem of learning from pairwise constraints in the form of must-links and cannot-links. As one kind of side information, a must-link indicates the pair of the two data points must be in a same class, while a cannot-link indicates that the two data points must be in two different classes. Given must-link and cannot-link information, our goal is to learn a Mahalanobis distance metric. Under this metric, we hope the distances of point pairs in must-links are as small as possible and those of point pairs in cannot-links are as large as possible. This task is formulated as a constrained optimization problem, in which the global optimum can be obtained effectively and efficiently. Finally, some applications in data clustering, interactive natural image segmentation and face pose estimation are given in this paper. Experimental results illustrate the effectiveness of our algorithm.     

融合注意力特征的遮挡物体6D姿态估计

在机械臂视觉抓取过程中,现有的算法在复杂背景、光照不足、遮挡等条件下,难以对目标物体进行实时、准确、鲁棒的姿态估计。针对以上问题,提出一种基于关键点方法的融合注意力特征的物体6D姿态网络。首先,在跳跃连接（Skip Connection）阶段引入能够聚焦通道空间信息的卷积注意力模块（CBAM）,使编码阶段的浅层特征与解码阶段的深层特征进行有效融合,增强特征图的空间域信息和精确位置通道信息;其次,采用归一化损失函数以弱监督的方式回归每个关键点的注意力图,将注意力图作为对应像素位置上关键点偏移量的权重分数;最后,累加求和得到关键点坐标。实验结果证明,所提网络在LINEMOD数据集和Occlusion LINEMOD数据集上ADD(-S)指标分别达到了91.3%和46.3%。与基于关键点的逐像素投票网络（PVNet）相比ADD(-S)指标分别提升了5.0个百分点和5.5个百分点,验证了所提网络在遮挡场景下有更好的鲁棒性。     

基于BIBD和循环置换矩阵的LDPC码

提出一种基于平衡不完全区组设计(BIBD)和循环置换矩阵的准循环低密度校验码(LDPC)构造方法。根据实际需求,利用BIBD构造相应的模板矩阵,用适合的循环置换矩阵进行扩展。采用该方法构造的LDPC码具有良好的结构和灵活性,该方法在一定范围内可快速方便构造出某一特定码长或码率的准循环LDPC码。仿真结果证明,准循环LDPC码在高斯白噪声信道上采用迭代译码时,具有较优的纠错性能及较低的错误平层。     

加权SVDD算法在人体姿态估计中的研究与应用

支持向量数据描述（SVDD）算法是解决单类分类问题的最好方法之一,在人体姿态估计问题中获得了成功的应用,在建立部位外观模型方面取得了良好的效果,但现有利用SVDD算法建立的部位外观模型将所有训练样本和样本不同特征都平等对待。为克服存在的这两个缺陷,提出了一种样本和特征加权的SVDD算法,并用其建立了一种基于样本和特征加权SVDD算法的部位外观模型。样本的权重系数根据样本到样本中心的距离远近来确定,样本特征的权重系数根据特征对应图像区域被训练图像中真实人体部位包含次数的多少来确定。仿真实验结果表明所建立的部位外观模型比利用标准SVDD算法建立的部位外观模型能更准确地描述真实人体部位的外观,能得到更高的人体姿态估计准确度。     

ARGP-Pose:基于关键点间关系分析与分组预测的3D人体姿态估计

尽管3D人体姿态估计已经相对成功,但现存方法在复杂场景下的性能依然差强人意。为了提高在无约束场景下3D人体姿态估计的准确性以及鲁棒性,提出了ARGP-Pose,一种基于探索关键点间关系的单目视频3D人体姿态估计框架。该框架包含一种关键点信息预处理方式以及3D姿态估计网络结构。关键点预处理能够强化结构特征,抽取出关键点之间联系信息,并作为网络输入。3D姿态估计网络能够融合各个关键点的局部信息以及整体姿态的全局信息。此外,利用自注意力模块来提取有效时序信息,以进一步提高预测准确度。而对于复杂姿态,采用了分组预测的方式将复杂动作的预测分解为各个点的预测,从而使网络对复杂姿态的估计能力有了明显的提高。在Human3.6M和HumanEva-I这两个著名数据集上的实验结果证明了所提出的方法的优越性。