基于隐含多项式曲线的物体描述与对称性检测

物体的对称性检测是图像分析，计算视觉中一个重要研究课题，在形状匹配，基于模型的目标匹配，三维物体的重建，图像压缩和图像数据库检索等许多领域都有重要应用，但是，对称性检测一直是计算机视觉的难题，至今缺少通用性好，能同时检测各种对称性并且效率较高的算法，利用隐含多项式曲线对复杂物体的良好描述能力，提出了基于隐含多项式曲一的物体对称性检测方法，这将平面图形的对称性检测问题转化对隐含多项式曲线的研究，理论与实验表明该算法能检测物体的各种对称性，算法简单，而且还可以检测出有噪音和缺失部分信息的物体对称性     

一种基于学习的复杂非刚体运动跟踪方法

复杂非刚体运动的跟踪是计算机视觉中的一个重要研究问题，在人机交互、运动合成与识别等领域有着广泛的应用。复杂非刚体运动跟踪的困难在于运动的自由度比较大，运动状态向量是一个高维的向量，而直接在高维空间中跟踪或求解图像中物体的运动状态向量是一个约束不充分、并因此而难以解决的问题。本文的基本思想是采用机器学习的方法来学习复杂非刚体运动的状态表示及其动态模型，从而将一个约束不充分的跟踪问题转化成一个约束充分的跟踪问题。     

线性逼近获取深度图象算法研究

三维表面重建是计算机视觉领域中的一个重要课题，也是计算机视觉中最困难的问题之一。该文提出了一种用线性逼近方法、基于灰度信息从图像获取物体深度信息，从而实现物体三维表面重建的算法。该算法原理简单，容易实现，速度快，具有较高的实用价值。     

基于单视觉原理实时提取运动物体三维信息的一种方法

针对多视觉方式中对应点匹配及系统复杂性等问题，采用单视觉方式，应用专用特征点匹配器实时进行特征点的匹配，运动刚体运动模型、摄像机模型、物体几何形状模型以及旋转矩阵的正交性，给出了一种实时提取运动物体平移、旋转等６个自由度信息的新方法。     

基于智能优化算法的非刚体三维运动结构重建

从动态图像序列中恢复非刚性物体的3D运动和结构是计算机视觉领域中重要的研究内容之一。之前大多算法都假设摄像机是仿射摄像机模型,但是这种假设在目标距相机很近时会变得无效和产生较大的重建误差。通过线性递归估计法将非刚体的因式分解从弱透视投影模型扩展到一般透视投影模型,并在线性递归估计过程中使用遗传算法(GA)对迭代因子进行优化。实验结果表明提出的方法具有很高的准确性。     

双目视觉基于修正卡尔曼滤波器的运动估计

研究了目标物体的远程运动估计.首先,建立了一种双目视觉系统的基于卡尔曼滤波器的目标物体运动估计的运动学模型,并且证明了双目视觉系统同步的各自连续两帧图像中至少三个对应图像点能完全确定刚性物体的运动参数和空间位置;然后,通过对状态向量中的速度分量进行再估计,提出了一种修正卡尔曼滤波器对目标物体远程运动估计的算法,与直接卡尔曼滤波器的远程运动估计相比,提高了估计的精度.将该方法运用到一种实时预测的实验中,其结果证明了该算法的有效性.     

几何不变性及其在3D物体识别中的应用

三维物体识别是计算机视觉研究的重要内容之一，它要求从3D物体的2D图象中识别和定位物体．由于物体成像时会受到观察视角、摄像机参数的影响，因此使得同一物体在不同观察视角、不同摄像机参数等条件下所得到的图象存在差异．但由于几何不变性方法可以有效地消除这种差异带给3D物体识别的不利影响，所以，近20年来这种方法受到了广泛的关注和研究．为使人们了解该领域的研究现状，以对该领域的研究有所启发，首先讨论了基于几何不变性的3D物体识别方法的研究内容，包括研究的几何框架和其不变性以及几何不变性在3D物体识别中的主要应用；其次，总结性地评述了该领域的研究现状；最后，提出了研究的发展方向．     

一种保持纹理的网面简化算法

在计算机视觉领域,三维网面的简化不仅要求保持物体形状和拓扑关系,还要求保持物体表面法线,纹理,颜色和边缘等物体特征,以使计算机视觉系统能有效地表示,描述,识别和理解物体和场景,为此讨论了一种基于边操作（边收缩,边分裂）,并具有颜色或灰度纹理特征保持的三维网面的简化算法,该算法将网面不对称最大距离作为形状改变测度,将邻域内颜色或灰度最大改变量作为纹理改变测试,从而在大量简化模型数据的同时,有效地保持了模型的几何形状,拓扑关系,颜色或灰度特征,以及网面顶点均匀分布。     

视觉跟踪技术综述

视觉跟踪问题是当前计算机视觉领域中的热点问题,本文对这一问题进行了详细的介绍.首先,对视觉跟踪技术在视频监视、图像压缩和三维重构等三个主要方面的应用进行了论述.其次,详细阐述了该技术的研究现状,介绍了其中的一些常用方法,为清楚说明这些方法,先对视觉跟踪问题进行了分类,然后介绍了处理视觉跟踪问题的两种思路即自底向上和自顶向下的思路,最后将具体的视觉跟踪方法分为四类进行了介绍,这四类分别是基于区域的跟踪、基于特征的跟踪、基于变形模板的跟踪和基于模型的跟踪.最后,从控制论角度给出视觉跟踪算法所面临的难点,即算法要满足鲁棒性、准确性和快速性要求时所遇到的困难,并对视觉跟踪问题的研究前景进行了展望.     

视觉跟踪算法综述

随着信息技术与智能科学的迅速发展,计算机视觉已经成为IT产业和高新技术领域的前沿.视觉跟踪是当前计算机视觉领域的热点问题之一.阐述了视觉跟踪算法的研究现状,包括视觉跟踪算法的种类,常用数学方法,研究了基于区域的跟踪算法、基于模型的跟踪算法、基于特征的跟踪算法、基于主动轮廓的跟踪算法、参数估计方法和无参密度估计方法,并探讨了视觉跟踪算法的未来研究方向.     

用二维点对应数据分割和估计多刚体运动

已知含有多个三维刚体的场景,在运动前后的二维点对应数据集合,其中可以包 含高斯噪声和出格点数据,发展了初始部分匹配的生成-生长技术并运用刚性约束.将上述 二维点对应数据集合.分割成多个分别对应于不同刚体运动的二维点对应数据子集,并能分 离出所有出格点数据.再利用单刚体运动估计算法就可估计出各个刚体运动参数.实验结果 表明了算法的有效性.     

Mathematical modeling of elastic inverted pendulum control system

Inverted pendulums are important objects of theoretical investigation and experiment in the area of control theory and engineering. The researches concentrate on the rigid finite dimensional models which are described by ordinary differential equations(ODEs) .Complete rigidity is the approximation of practical models; Elasticity should be introduced into mathematical models in the analysis of system dynamics and integration of highly precise controller. A new kind of inverted pendulum, elastic inverted pendulum was proposed, and elasticity was considered. Mathematical model was derived from Hamiltonian principle and variational methods, which were formulated by the coupling of partial differential equations (PDE) and ODE. Becausse of infinite dimensional, system analysis and control of elastic inverted pendulum is more sophisticated than the rigid one.     

基于相对形变模型及正则化技术的人体运动估计

为了使根据人体行走的单目动态图象序列，对人体手臂及腿部的运动及结构参数进行估计的结果更为可信、更具鲁棒性，提出了一种基于相对形变模型及正则化技术的人体运动估计方法，该方法首先在物体中心坐标的运动表示方式下，通过在刚体运动模型中加入形变系数的方法给出了基于相对形变概念的非刚体运动模型；然后，根据这一非刚体运动模型进行正则化运动及结构参数的估计，再以正则化的形式融入人体运动的先验知识，使运动估计的结果更具鲁棒性，实验结果证明，该方法有效地反映了人体的非刚体运动模式，运动模型中所加入的相对形变系数也一定程度反映了人体的运动规律。     

Reconstruction of non-rigid 3D shapes from stereo-motion

Several non-rigid structure from motion methods have been proposed so far in order to recover both the motion and the non-rigid structure of an object. However, these monocular algorithms fail to give reliable 3D shape estimates when the overall rigid motion of the sequence is small. Aiming to overcome this limitation, in this paper we propose a novel approach for the 3D Euclidean reconstruction of deformable objects observed by an uncalibrated stereo rig. Using a stereo setup drastically improves the 3D model estimation when the observed 3D shape is mostly deforming without undergoing strong rigid motion. Our approach is based on the following steps. Firstly, the stereo system is automatically calibrated and used to compute metric rigid structures from pairs of views. Afterwards, these 3D shapes are aligned to a reference view using a RANSAC method in order to compute the mean shape of the object and to select the subset of points which have remained rigid throughout the sequence. The selected rigid points are then used to compute frame-wise shape registration and to robustly extract the motion parameters from frame to frame. Finally, all this information is used as initial estimates of a non-linear optimization which allows us to refine the initial solution and also to recover the non-rigid 3D model. Exhaustive results on synthetic and real data prove the performance of our proposal estimating motion, non-rigid models and stereo camera parameters even when there is no rigid motion in the original sequence.     

人运动的视觉分析综述

目前，人运动的视觉分析是计算机视觉领域中最活跃的研究主题之一，其核心是利用计算机视觉技术从图像序列中检测，跟踪，识别人并对其行为进行理解与描述，它在虚拟现实，视觉监控，感知接口等领域均有着广泛的应用前景，人运动的视觉分析系统一般遵从下述的处理过程：（1）运动检测，（2）运动目标分类，（3）人的跟踪，（4）行为理解与描述，该文将重点从此四个方面回顾人运动分析的发展水平和常用的处理方法，并对研究难点及未来的发展趋势作了较为详细的分析。     

Approach to Nonrigid Body Metamorphosis UsingGeneralized Morph-translation

An approach of morphing by decomposing two objects into sets of individual convex sub objects respectively and contructing the mapping between two sets is presented The Minkvski addition of two convex sub-objects according to their mapping ralationship is calculated, then all the Minkovski additions are combined to obtain the final result. Nonrigid body motion can be divided into nonrigid body metamorphosis and rigid body rotation A novel method for describing nonrigid body motion based on generalized morph-translation is proposed. This method can solve the metamorphosis problem of two non-homotopic objects. Experiments show tha this method can generate natural, high quality metamorphosis results with simple computation. This method can also be used in interpolation between two keyframes in 2D and 3D computer animation automatically.     

Inherent ambiguities in recovering 3-D motion and structure from anoisy flow field

One of the major areas in research on dynamic scene analysis is recovering 3-D motion and structure from optical flow information. Two problems which may arise due to the presence of noise in the flow field are examined. First, motion parameters of the sensor or a rigidly moving object may be extremely difficult to estimate because there may exist a large set of significantly incorrect solutions which induce flow fields similar to the correct one. The second problem is in the decomposition of the environment into independently moving objects. Two such objects may induce optical flows which are compatible with the same motion parameters, and hence, there is no way to refute the hypothesis that these flows are generated by one rigid object. These ambiguities are inherent in the sense that they are algorithm-independent. Using a mathematical analysis, situations where these problems are likely to arise are characterized. A few examples demonstrate the conclusions. Constraints and parameters which can be recovered even in ambiguous situations are presented     

Motion Analysis by Random Sampling and Voting Process

In computer vision, motion analysis is a fundamental problem. Applying the concepts of congruence checking in computational geometry and geometric hashing, which is a technique used for the recognition of partially occluded objects from noisy data, we present a new random sampling approach for the estimation of the motion parameters in two- and three-dimensional Euclidean spaces of both a completely measured rigid object and a partially occluded rigid object. We assume that the two- and three-dimensional positions of the vertices of the object in each image frame are determined using appropriate methods such as a range sensor or stereo techniques. We also analyze the relationships between the quantization errors and the errors in the estimation of the motion parameters by random sampling, and we show that the solutions obtained using our algorithm converge to the true solutions if the resolution of the digitalization is increased.     

Accurate spatio-temporal reconstruction of missing data in dynamic scenes

In this paper, the accurate method for texture reconstruction with non-desirable moving objects into dynamic scenes is proposed. This task is concerned to editor off-line functions, and the main criteria are the accuracy and visibility of the reconstructed results. The method is based on a spatio-temporal analysis and includes two stages. The first stage uses a feature points tracking to locate the rigid objects accurately under the assumption of their affine motion model. The second stage involves the accurate reconstruction of video sequence based on texture maps of smoothness, structural properties, and isotropy. These parameters are estimated by three separate neural networks of a back propagation. The background reconstruction is realized by a tile method using a single texton, a line, or a field of textons. The proposed technique was tested into reconstructed regions with a frame area up to 8–20%. The experimental results demonstrate more accurate inpainting owing to the improved motion estimations and the modified texture parameters.     

单目人体图像序列的运动及结构参数估计

利用人体行走的单目动态图像序列,估计手臂及腿部的运动及结构参数.在物体中心坐标的运动表示方式下,提出了基于弹性连接概念的非刚体运动模型,通过加入弹性系数的方法,使非刚体运动模型和刚体运动模型得到了良好的统一.在此模型的基础上,用Levenberg-Marquardt方法实现了运动及结构参数的估计.实验证明了该方法的有效性,运动模型中的弹性系数也反映了一定程度的运动模式.