正投影模型下基于秩1的遮挡点恢复方法

为了有效地恢复遮挡点,假设相机为正投影模型,提出了一种基于秩1的遮挡点恢复方法.该方法利用所有图像点组成一个秩的矩阵,并利用该特性构造一个投影矩阵,利用该投影矩阵求到遮挡点,再将求到的遮挡点代替图像中的遮挡点,经过多次迭代,最后求到遮挡点的真实图像位置.模拟实验和真实实验表明:该方法具有鲁棒性好、收敛性好及误差小等优点.     

一种存在遮挡的射影重建算法

提出一种存在遮挡的射影重建算法.该算法利用重投影点代替图像中的遮挡点,进行射影重建,经过多次迭代,最后求到遮挡点的真实图像位置并完成射影重建.该算法的优点是所有的图像及图像点都平等对待.模拟实验和真实实验表明,该射影重建算法具有鲁棒性好、收敛性好及重投影误差小等优点.     

基于列约束的低秩矩阵恢复方法

由于在成像过程中出现遮挡现象,图像矩阵的元素有缺失。在正投影相机模型下,提出一种基于列约束的低秩矩阵恢复方法。该方法利用图像矩阵是一个低秩矩阵从而图像序列具有冗余性的特性,利用奇异值分解由图像矩阵的列空间构造出一个投影矩阵,得到图像矩阵的列所满足的约束条件,将缺失元素的恢复转化为迭代求解二次型的极值问题,利用它恢复出图像矩阵的缺失元素。该方法从理论上能够保证收敛到全局最小值。仿真实验表明,此方法具有收敛速度快,恢复精度高等优点。     

基于结构化低秩表示和低秩投影的人脸识别算法

在实际的人脸识别中,给定的训练图像往往存在遮挡和噪声,导致稀疏表示分类（SRC）算法的性能下降。针对上述问题,提出一种基于结构化低秩表示（SLR）和低秩投影的人脸识别方法--SLR_LRP。首先通过SLR对原始训练样本进行低秩分解得到干净的训练样本,根据原始训练样本和恢复得到的干净训练样本得到一个低秩投影矩阵;然后将测试样本投影到该低秩投影矩阵;最后使用SRC对恢复后的测试样本进行分类。在AR人脸库和Extended Yale B人脸库上的实验结果表明,SLR_LRP可以有效处理样本中存在的遮挡和像素破坏。     

秩约束多帧特征对应算法

由于在一个关于刚体场景的长的图像序列中可能出现遮挡现象,使得度量矩阵中存在丢失数据项,为此提出一种在线多帧特征对应算法.由于图像度量值加权的偏移矩阵和轨迹矩阵均位于一个低维的线性子空间中,将偏移矩阵中的完整子矩阵秩约束后重组织成轨迹矩阵,对轨迹矩阵秩约束后求得相应的基矩阵和系数矩阵;为了解决光流的孔径问题,由基矩阵和系...     

基于低秩表示中稀疏误差的可变光照和局部遮挡人脸识别

可变光照和有遮挡人脸识别是人脸识别问题中的一个难点。受到鲁棒主成分分析法(RPCA)和稀疏表示分类法(SRC)的启发,提出一种基于低秩表示(LRR)中稀疏误差图像的可变光照有遮挡人脸识别算法。在训练阶段,利用LRR计算每类人脸低秩数据矩阵,在此基础上求解每类人脸图像低秩映射矩阵,通过各类低秩映射矩阵将未知人脸图像投影得到每类下的低秩数据矩阵和稀疏误差矩阵,为了有效提取稀疏误差图像中的鉴别信息,分别对稀疏误差图像进行边缘检测和平滑度分析,设计了基于两者加权和的类别判据。在Extended Yale B和AR两个数据库上进行了详细的实验分析,实验结果与其它算法相比较有明显提高,证实了所提算法的有效性和鲁棒性。     

基于鲁棒主成分分析的人脸子空间重构方法

子空间方法是人脸识别中的经典方法,其基本假设是人脸图像处于高维图像空间的低维子空间中.但是,由于光照变化、阴影、遮挡、局部镜面反射、图像噪声等因素的影响,使得子空间假设难以满足.为此,提出一种基于鲁棒主成分分析的人脸子空间重构方法.该方法将人脸图像数据矩阵表示为满足子空间假设的低秩矩阵和表征光照变化、阴影、遮挡、局部镜面反射、图像噪声等因素的误差矩阵之和,利用鲁棒主成分分析法求解低秩矩阵和误差矩阵.实验结果表明,文中方法能够有效地重构人脸图像的低维子空间.     

基于遮挡区域建模和目标运动估计的动态遮挡规避方法

对于运动视觉目标，如何对遮挡区域进行规避是视觉领域一个具有挑战性的问题.本文提出了一种新颖的基于运动视觉目标深度图像利用遮挡信息实现动态遮挡规避的方法.该方法主要利用遮挡区域最佳观测方位模型和视觉目标运动估计方程，通过合理规划摄像机的观测方位逐渐完成对遮挡区域的观测.主要贡献在于:1）提出了深度图像遮挡边界中关键点的概念，利用其构建关键线段对遮挡区域进行快速建模；2）基于关键线段和遮挡区域建模结果，提出了一种构建遮挡区域最佳观测方位模型的方法；3）提出一种混合曲率特征，通过计算深度图像对应的混合曲率矩阵，增加了图像匹配过程中提取特征点的数量，有利于准确估计视觉目标的运动.实验结果验证了所提方法的可行性和有效性.     

一种多视图分层重构算法研究

本文介绍了基于奇异值分解的射影重构算法的一般框架,以测量矩阵的秩为4作为约束,以仿射投影逼近透视投影,利用共轭梯度法估计射影深度,通过奇异值分解实现射影重构.利用共轭梯度法确定Kruppa方程中的未知比例因子,然后利用所确定的比例因子线性求解Kruppa方程,进而标定摄像机内参数.在摄像机内参数已知的情况下,求解一个满足欧氏重构条件的非奇异矩阵,然后通过此矩阵将射影重构变换为欧氏重构.实验结果表明所给出的算法是行之有效的.     

基于低秩子空间投影和Gabor特征的稀疏表示人脸识别算法

目前的人脸识别算法常常忽视训练过程中噪声的影响,特别是在训练数据和待测数据都受到噪声污染的情况下,识别性能会明显下降。针对含有光照变化、伪装、遮挡及表情变化等较大噪声的人脸识别问题,提出了一种基于低秩子空间投影和Gabor特征的稀疏表示人脸识别算法。该算法首先通过低秩矩阵恢复算法得到训练样本的潜在低秩结构和稀疏误差结构;然后利用主成分分析法找到低秩结构的Gabor特征所在低秩子空间的变换矩阵;再通过变换矩阵将所有样本的Gabor特征向量投影到低秩子空间上,在该低秩子空间上使用稀疏表示分类算法进行最终的分类识别。在Extend Yale B和AR数据库上的实验表明,新算法具有较高的识别率和较强的抗干扰能力。     

基于遗传算法的射影重构

在实现分层重构的过程中，射影重构是关键的第1步。目前，大多已有算法对模拟数值是非常有效的，但对于真实图象效果并不理想。为了寻求更为鲁棒的算法，提出了一种基于遗传算法的射影重构算法。该算法对于射影深度采用十进制编码，并以测量矩阵的秩为4作为约束，来定义适应度函数，然后利用遗传算法，并结合奇异值分解（SVD）技术来迭代估计射影深度，进而实现射影重构，该算法是行之有效的，且鲁棒性较好。     

基于射影不变量的三维重构

文中提出了利用射影不变量来求解基于图像对三维深度恢复问题。方法的基本思想是对于立体图像,利用密度段元素,引入了两个射影不变量来恢复密度段的深度信息。从这两个不变量,能推导立体图像中匹配的密度段对所满足的关系。利用这个关系,实现了密度段之间的匹配运算。这个方法能直接地从输入图像中得到密集和准确的深度,对变形的图像具有鲁棒性。     

Low-Rank Matrix Fitting Based on Subspace Perturbation Analysis with Applications to Structure from Motion

The task of finding a low-rank (r) matrix that best fits an original data matrix of higher rank is a recurring problem in science and engineering. The problem becomes especially difficult when the original data matrix has some missing entries and contains an unknown additive noise term in the remaining elements. The former problem can be solved by concatenating a set of r-column matrices that share a common single r-dimensional solution space. Unfortunately, the number of possible submatrices is generally very large and, hence, the results obtained with one set of r-column matrices will generally be different from that captured by a different set. Ideally, we would like to find that solution that is least affected by noise. This requires that we determine which of the r-column matrices (i.e., which of the original feature points) are less influenced by the unknown noise term. This paper presents a criterion to successfully carry out such a selection. Our key result is to formally prove that the more distinct the r vectors of the r-column matrices are, the less they are swayed by noise. This key result is then combined with the use of a noise model to derive an upper bound for the effect that noise and occlusions have on each of the r-column matrices. It is shown how this criterion can be effectively used to recover the noise-free matrix of rank r. Finally, we derive the affine and projective structure-from-motion (SFM) algorithms using the proposed criterion. Extensive validation on synthetic and real data sets shows the superiority of the proposed approach over the state of the art.     

基于外点检测与校正的填充射影分解算法

针对三维重构中存在的数据缺失和遮挡问题,提出可处理缺失数据的填充射影分解算法,利用子空间约束与对极几何约束进行矩阵拟合并填充缺失数据,通过奇异值分解得到射影运动与结构参数。为克服该算法对噪声和外点的敏感性,结合RANSAC算法和三角形法对其进行外点检测与校正。实验结果表明,加入外点校正后的算法可提高射影重构的鲁棒性,降低误差,具有较高的实用价值。     

Shape and motion from image streams under orthography: a factorization method

Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. We have developed a factorization method that can overcome this difficulty by recovering shape and motion under orthography without computing depth as an intermediate step.An image stream can be represented by the 2F×P measurement matrix of the image coordinates of P points tracked through F frames. We show that under orthographic projection this matrix is of rank 3.Based on this observation, the factorization method uses the singular-value decomposition technique to factor the measurement matrix into two matrices which represent object shape and camera rotation respectively. Two of the three translation components are computed in a preprocessing stage. The method can also handle and obtain a full solution from a partially filled-in measurement matrix that may result from occlusions or tracking failures.The method gives accurate results, and does not introduce smoothing in either shape or motion. We demonstrate this with a series of experiments on laboratory and outdoor image streams, with and without occlusions.     

一种空间直线重建方法

提出一种基于图像序列的空间直线重建新方法,这种方法是在空间点算法的基础上改进的,不需要特征点的参与。算法首先对直线测量矩阵估计射影深度,采用SVD（Singular Value Decomposition）分解矩阵。并最后应用变换,使得分解结果真实有效。在估计射影深度时运用了共轭法迭代。使得射影深度的估算更准确。     

图像特征点匹配的强壮算法

同一场景的不同图像匹配是计算机视觉中的一个基本问题，在诸如三维重度，对象识别和分类、图像对齐和相机自校正等应用中，特征匹配都是一个关键步骤，其中特征点匹配是较为常用的一种方法，特征点匹配的效果受到很多因素的影响，如景物的遮挡，光照和噪声等，变化很大，文中对结指标派算法进行扩以解决全局优化问题，并利用场景深度局部连续的条件作为附加约束，提出一种新的特征点匹配算法，整个算法只用到两次优化，而且几乎全部使用矩阵运算，效率比已有的算法高，实验表明该算法的效果是令人满意的。     

Estimating 3D shape from degenerate sequences with missing data

Reconstructing a 3D scene from a moving camera is one of the most important issues in the field of computer vision. In this scenario, not all points are known in all images (e.g. due to occlusion), thus generating missing data. On the other hand, successful 3D reconstruction algorithms like Tomasi & Kanade’s factorization method, require an orthographic model for the data, which is adequate in close-up views. The state-of-the-art handles the missing points in this context by enforcing rank constraints on the point track matrix. However, quite frequently, close-up views tend to capture planar surfaces producing degenerate data. Estimating missing data using the rank constraint requires that all known measurements are “full rank” in all images of the sequence. If one single frame is degenerate, the whole sequence will produce high errors on the reconstructed shape, even though the observation matrix verifies the rank 4 constraint. In this paper, we propose to solve the structure from motion problem with degenerate data, introducing a new factorization algorithm that imposes the full scaled-orthographic model in one single optimization procedure. By imposing all model constraints, a unique (correct) 3D shape is estimated regardless of the data degeneracies. Experiments show that remarkably good reconstructions are obtained with an approximate models such as orthography.     

一种非定标图像高精度三维重建算法

由非定标图像重建三维场景有着广泛的应用。给出了一种非定标多视图像三维重建算法。该算法主要基于因子分解和光束法平差技术。首先用因子分解方法得到射影空间下相机投影矩阵和物点坐标,以旋转矩阵的正交性以及对偶绝对二次曲面秩为3为约束,将射影空间升级到欧式空间,最后用光束法平差进行优化。该方法可同时获得相机的内外参数、畸变系数和场景的三维坐标。仿真实验表明,在1000 mm×1000 mm×400mm的范围内,当像点检测误差在0-1pixel和0-2pixel内,所重建三维点的误差分别为0.1530 mm和0.6712 mm。在500 mm×500 m×200 mm下,真实实验重构三维点的误差在0.3 mm以内。所提出的算法稳定可靠,可对实际工程进行指导。     

A generalized registration method for augmented reality systems

In augmented reality systems, registration is one of the most difficult problems currently limiting their applications. In this paper, we propose a generalized registration method using projective reconstruction technique in computer vision. This registration method is composed of embedding and tracking. Embedding involves specifying four points to build the world coordinate system on which a virtual object will be superimposed. In this stage, any arbitrary two unrelated images or any 3×4 projective matrices with rank 3 can be used to calculate the 3D pseudo-projective coordinates of the four specified points. In the tracking process, these 3D pseudo-projective coordinates are used to track the four specified points to compute the registration matrix for augmentation. The proposed method is simple, as only four points need to be specified at the embedding stage, and the virtual object can then be easily augmented onto a real scene from a video sequence. One advantage is that the virtual objects can still be superimposed on the specified regions even when the regions are occluded in the video sequence. Another advantage of the proposed method is that the registration errors can be adjusted in real-time to ensure that they are less than certain thresholds that have been specified at the initial embedding stage. Several experiments have been conducted to validate the performance of the proposed generalized method.