基于图嵌入线性拓展方法的人体动作识别研究

采用图嵌入降维的方法对人侧影轮廓数据进行降维处理并用来识别人的行为动作.给定一个动作的图像序列,提取序列中每帧中人的侧影轮廓信号并用之表征人体运动,利用两种图嵌入法将提取的时变轮廓信号投影到低维空间,采用Hausdroff距离测量运动的相似性并在最近邻框架下识别人的动作.为验证算法的有效性,采用留一法和统计方法两种测试方法对五类人体常见动作(走、跑、拍手、挥手和拳击)进行测试.实验结果表明,方法不仅有很好的分类性能,而且能有效的降低了计算量.     

基于动作串的人体行为识别

提出了一种以运动人体侧影为特征的基于模板匹配的人体行为识别方法.首先,利用背景差分法和阴影消除技术提取运动人体侧影.利用缓变换对人体侧影进行特征提取,将时变的2D区域形状转换为对应的1D距离向量.然后,利用谱系聚类方法提取动作序列的关键姿态,将关键姿态编码为称为动作串的模板.最后,利用动态时间规整算法度量测试序列与标准模板之间的相似性.实验结果表明,本方法对人的6种日常行为进行识别的正确识别率达到85％以上,具有简单实用的特点.     

基于改进动态纹理模型的人体运动分析

人体运动分析是计算机视觉领域最活跃的研究课题之一。文中提出2种描述人体运动序列的改进动态纹理模型:二值动态纹理模型和张量子空间动态纹理模型。假设二值图像服从Bernoulli分布,二值动态纹理模型使用二值主成分分析来学习训练模型的参数。张量子空间动态纹理模型将图像看作张量, 引入张量子空间分析的方法分别对其行向量和列向量进行降维,将其转化为低维灰度图像,然后用动态纹理模型描述灰度图像序列。在人体行为和步态数据库上的实验结果验证2种改进动态纹理模型的有效性。     

QPSO算法和Powell法结合的多分辨率医学图像配准

图像配准一直是图像研究领域的热点话题,互信息的配准方法由于其精度高、鲁棒性强等特点,成为图像配准中的常用方法。但其目标函数存在局部极值问题。针对这个问题,提出一种量子行为的粒子群优化算法(QPSO)和Powell法相结合的多分辨率搜索优化算法。QPSO参数个数少,其每一个迭代步的取样空间能覆盖整个解空间,能保证算法的全局收敛,因此可以有效地解决Powell算法的缺点。该算法将量子行为的粒子群优化算法(QPSO)与Powell法结合起来对二维的MRI图像进行配准。实验结果表明,该方法能够有效地克服互信息函数的局部极值问题,并提高了配准精度和速度。     

基于量子理论及蚁群算法的多Agent Q学习

针对多Agent协作强化学习中存在的行为和状态维数灾问题,以及行为选择上存在多个均衡解,为了收敛到最佳均衡解需要搜索策略空间和协调策略选择问题,提出了一种新颖的基于量子理论和蚁群算法的多Agent协作学习算法。新算法首先借签了量子计算理论,将多Agent的行为和状态空间通过量子叠加态表示,利用量子纠缠态来协调策略选择,利用概率振幅进行动作探索,加快学习速度。其次,根据蚁群算法,提出“脚印”思想来间接增强Agent之间的交互。最后,对新算法的理论分析和实验结果都证明了改进的Q学习是可行的,并且可以有效地提高学习效率。     

面向行为识别的拉普拉斯特征映射算法的改进

提出了一种面向行为识别的拉普拉斯特征映射算法的改进方法.首先,将Kinect提供的关节点数据作为姿态特征,采用Levenstein距离改进流形学习算法中的拉普拉斯特征映射算法,并映射到二维空间得到待识别行为的嵌入空间;其次,结合待识别行为的嵌入空间和训练数据建立先验模型;最后,通过重新设计的粒子动态模型和观察模型,采用粒子滤波算法进行行为识别.实验结果表明,该方法可以对重复动作、遮挡,以及动作幅度和速度都有明显差异的行为进行较好的识别,总体识别率达到92.4％.     

基于深度数据的人体动作识别方法

本文提出了一个基于流形学习的动作识别框架,用来识别深度图像序列中的人体行为。本文从Kinect设备获得的深度信息中评估出人体的关节点信息,并用相对关节点位置差作为人体特征表达。在训练阶段,本文利用Lapacian eigenmaps(LE)流形学习对高维空间下的训练集进行降维,得到低维隐空间下的运动模型。在识别阶段,本文用最近邻差值方法将测试序列映射到低维流形空间中去,然后进行匹配计算。在匹配过程中,通过使用改进的Hausdorff距离对低维空间下测试序列和训练运动集的吻合度和相似度进行度量。本文用Kinect设备捕获的数据进行了实验,取得了良好的效果;同时本文也在MSR Action3D数据库上进行了测试,结果表明在训练样本较多情况下,本文识别效果优于以往方法。实验结果表明本文所提的方法适用于基于深度图像序列的人体动作识别。     

Hausdorff距离和量子粒子群的二维图像匹配

提出了一种基于Hausdorff距离和量子粒子群算法的二维图像匹配算法。为了实现二维图像的搜索,首先利用Canny算子提取图像的边缘,再利用Hausdorff距离作为图像搜索的目标函数,然后引入了带量子行为的粒子群的优化算法来求解搜索所需的空间变化参数,实验结果表明,带量子行为的粒子群的优化算法（QPSO）能够迅速地在全局范围内找到最优解,因此应用于二维图像搜索是可行的。     

基于光流特征与序列比对的实时行为识别*

提出一种基于光流特征与序列比对的行为识别算法.首先利用分层光流提取视频序列中的运动信息;然后用光流场的方向直方图构造相应行为的模板库和索引序列库;最后用序列比对方法实现行为识别.实验结果表明,该算法可在线进行人的典型行为识别,对目标尺度变化、小角度倾斜和旋转具有一定程度的鲁棒性.目前以该算法为核心的行为识别实验系统对图像尺寸为320×240的序列平均处理速度达到10 fps.     

基于改进的等距离映射算法的人脸识别

针对等距离映射(Isomap)算法在处理扰动图像时拓扑结构不稳定的缺点,提出了一种改进算法。改进算法将图像欧氏距离(IMED)嵌入到等距离映射算法之中。首先引入坐标度量系数计算图像的坐标度量矩阵,通过线性变换将原始图像从欧氏距离(ED)空间转换到图像欧氏距离空间;然后计算变换空间中样本的欧氏距离矩阵,并在此基础上构建样本邻域图,得到近似测地距离矩阵;最后采用多维标度(MDS)分析算法构造样本的低维表示。对ORL和Yale人脸数据库降维并结合最近邻分类器进行实验,基于改进算法的识别率平均分别提高了5.57%和3.95%,表明与原算法相比,改进算法在人脸识别中对图像扰动具有较好的鲁棒性。     

线性动态系统反演模型在人体行为识别的应用

目的 人体行为识别在视频监控、环境辅助生活、人机交互和智能驾驶等领域展现出了极其广泛的应用前景。由于目标物体遮挡、视频背景阴影、光照变化、视角变化、多尺度变化、人的衣服和外观变化等问题,使得对视频的处理与分析变得非常困难。为此,本文利用时间序列正反演构造基于张量的线性动态模型,估计模型的参数作为动作序列描述符,构造更加完备的观测矩阵。方法 首先从深度图像提取人体关节点,建立张量形式的人体骨骼正反向序列。然后利用基于张量的线性动态系统和Tucker分解学习参数元组（A_F,A_I,C）,其中C表示人体骨架信息的空间信息,A_F和A_I分别描述正向和反向时间序列的动态性。通过参数元组构造观测矩阵,一个动作就可以表示为观测矩阵的子空间,对应着格拉斯曼流形上的一点。最后通过在格拉斯曼流形上进行字典学习和稀疏编码完成动作识别。结果 实验结果表明,在MSR-Action 3D数据集上,该算法比Eigenjoints算法高13.55%,比局部切从支持向量机（LTBSVM）算法高2.79%,比基于张量的线性动态系统（tLDS）算法高1%。在UT-Kinect数据集上,该算法的行为识别率比LTBSVM算法高5.8%,比tLDS算法高1.3%。结论 通过大量实验评估,验证了基于时间序列正反演构造出来的tLDS模型很好地解决了上述问题,提高了人体动作识别率。     

Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking

Appearance modeling is very important for background modeling and object tracking. Subspace learning-based algorithms have been used to model the appearances of objects or scenes. Current vector subspace-based algorithms cannot effectively represent spatial correlations between pixel values. Current tensor subspace-based algorithms construct an offline representation of image ensembles, and current online tensor subspace learning algorithms cannot be applied to background modeling and object tracking. In this paper, we propose an online tensor subspace learning algorithm which models appearance changes by incrementally learning a tensor subspace representation through adaptively updating the sample mean and an eigenbasis for each unfolding matrix of the tensor. The proposed incremental tensor subspace learning algorithm is applied to foreground segmentation and object tracking for grayscale and color image sequences. The new background models capture the intrinsic spatiotemporal characteristics of scenes. The new tracking algorithm captures the appearance characteristics of an object during tracking and uses a particle filter to estimate the optimal object state. Experimental evaluations against state-of-the-art algorithms demonstrate the promise and effectiveness of the proposed incremental tensor subspace learning algorithm, and its applications to foreground segmentation and object tracking.     

Face Recognition and Micro-expression Recognition Based on Discriminant Tensor Subspace Analysis Plus Extreme Learning Machine

In this paper, a novel recognition algorithm based on discriminant tensor subspace analysis (DTSA) and extreme learning machine (ELM) is introduced. DTSA treats a gray facial image as a second order tensor and adopts two-sided transformations to reduce dimensionality. One of the many advantages of DTSA is its ability to preserve the spatial structure information of the images. In order to deal with micro-expression video clips, we extend DTSA to a high-order tensor. Discriminative features are generated using DTSA to further enhance the classification performance of ELM classifier. Another notable contribution of the proposed method includes significant improvements in face and micro-expression recognition accuracy. The experimental results on the ORL, Yale, YaleB facial databases and CASME micro-expression database show the effectiveness of the proposed method.     

Tensor linear Laplacian discrimination (TLLD) for feature extraction

Discriminant feature extraction plays a central role in pattern recognition and classification. In this paper, we propose the tensor linear Laplacian discrimination (TLLD) algorithm for extracting discriminant features from tensor data. TLLD is an extension of linear discriminant analysis (LDA) and linear Laplacian discrimination (LLD) in directions of both nonlinear subspace learning and tensor representation. Based on the contextual distance, the weights for the within-class scatters and the between-class scatter can be determined to capture the principal structure of data clusters. This makes TLLD free from the metric of the sample space, which may not be known. Moreover, unlike LLD, the parameter tuning of TLLD is very easy. Experimental results on face recognition, texture classification and handwritten digit recognition show that TLLD is effective in extracting discriminative features.     

基于张量分析的表情特征提取

表情识别的性能依赖于所提取表情特征的有效性,现有方法提取的表情基本上是人脸与表情的融合体,然而不同个体的人脸差异是表情识别的主要干扰因素。在表情识别时,理想情况是将个体相关的人脸特征和与个体无关的表情特征相分离。针对此问题,在三维空间建立人脸张量;然后用张量分析的方法将人脸特征与表情特征进行分离,使获取的表情参数与人脸无关。从而排除不同个体的人脸差异对表情识别的干扰。最后,在JAFFE表情数据库上验证了该方法的有效性。     

基于张量的半监督判别分析算法

边界Fisher判别分析算法因采用一维向量表示而无法很好保持图像的空间几何结构,且无法利用大量未标记样本信息.为此,提出一种基于张量的半监督判别分析算法.采用二维张量表示人脸空间中的样本图像,揭示流形的内在几何结构,利用有判别信息的标记样本和大量未标记样本,使数据在投影空间的类间分离度最大,同时保证高维空间中不相邻的点在低维空间中也不相邻.在PIE和FERET人脸库上的实验结果表明,该算法能够获得较高的识别率.     

Human action recognition based on graph-embedded spatio-temporal subspace

Human action recognition is an important issue in the pattern recognition field, with applications ranging from remote surveillance to the indexing of commercial video content. However, human actions are characterized by non-linear dynamics and are therefore not easily learned and recognized. Accordingly, this study proposes a silhouette-based human action recognition system in which a three-step procedure is used to construct an efficient discriminant spatio-temporal subspace for k-NN classification purposes. In the first step, an Adaptive Locality Preserving Projection (ALPP) method is proposed to obtain a low-dimensional spatial subspace in which the linearity in the local data structure is preserved. To resolve the problem of overlaps in the spatial subspace resulting from the ambiguity of the human body shape among different action classes, temporal data are extracted using a Non-base Central-Difference Action Vector (NCDAV) method. Finally, the Large Margin Nearest Neighbor (LMNN) metric learning method is applied to construct an efficient spatio-temporal subspace for classification purposes. The experimental results show that the proposed system accurately recognizes a variety of human actions in real time and outperforms most existing methods. In addition, a robustness test with noisy data indicates that our system is remarkably robust toward noise in the input images.     

Orthogonal Tensor Neighborhood Preserving Embedding for facial expression recognition

In this paper a generalized tensor subspace model is concluded from the existing tensor dimensionality reduction algorithms. With this model, we investigate the orthogonality of the bases of the high-order tensor subspace, and propose the Orthogonal Tensor Neighborhood Preserving Embedding (OTNPE) algorithm. We evaluate the algorithm by applying it to facial expression recognition, where both the 2nd-order gray-level raw pixels and the encoded 3rd-order tensor-formed Gabor features of facial expression images are utilized. The experiments show the excellent performance of our algorithm for the dimensionality reduction of the tensor-formed data especially when they lie on some smooth and compact manifold embedded in the high dimensional tensor space.     

张量局部Fisher判别分析的人脸识别

子空间特征提取是人脸识别中的关键技术之一,结合局部Fisher判别分析技术和张量子空间分析技术的优点, 本文提出了一种新的张量局部Fisher判别分析(Tensor local Fisher discriminant analysis, TLFDA)子空间降维技术. 首先,通过对局部Fisher判别技术进行分析,调整了其类间散度目标泛函, 使算法的识别性能更高且时间复杂度更低;其次,引入张量型降维技术对输入数据进行双边投影变换而非单边投影, 获得了更高的数据压缩率;最后,采用迭代更新的方法计算最优的变换矩阵.通过ORL和PIE两个人脸库验证了所提算法的有效性.     

Feature Fusion Using Multiple Component Analysis

Canonical correlation analysis (CCA) and partial least squares (PLS) are always used as fusing two feature sets. How to extend them to fuse multiple features in a generalized way is still an unsolved problem. In this paper, we propose a novel feature fusion method called multiple component analysis (MCA). By constructing a higher-order tensor, all kinds of information are fused into the covariance tensor. Then orthogonal subspaces corresponding to each feature set are learned through tensor singular value decomposition (SVD), that couples dimension reduction and feature fusion together. Compared with multiple feature fusion by subspace learning (MFFSL), our method has the ability to represent fused data more efficiently and discriminatively in very few components. And it is shown that principle component analysis (PCA) and PLS are special cases of our method when there are only one set and two sets of features respectively. Extensive experiments on both handwritten numerals classification and face recognition demonstrate the effectiveness and robustness of the proposed method.