An efficient volumetric method for non-rigid registration

We propose a novel and efficient volumetric method for registering 3D shapes with non-rigid deformations. Our method uses a signed distance field to represent the 3D input shapes and registers them by minimizing the difference between their distance fields. With the assumptions that the sampling points in each cell of the object volume follow the same rigid transformation, and the transformations of the sampling cells vary smoothly inside the object volume, a two-step method is used for the non-rigid registration. The first step is the locally rigid registration, which minimizes the difference between the source and target distance fields of the sampling cells. The second step is the globally non-rigid registration, which minimizes the difference between the transformations of adjacent cells. In just a few iterations, our method rapidly converges for the registration. We tested our method on several datasets, and the experimental results demonstrate the robustness and efficiency of our method.     

New methods for matching 3-d objects with single perspective views

In this paper we analyze the ability of a computer vision system to derive properties of the three-dimensional (3-D) physical world from viewing two-dimensional (2-D) images. We present a new approach which consists of a model-based interpretation of a single perspective image. Image linear features and linear feature sets are backprojected onto the 3-D space and geometric models are then used for selecting possible solutions. The paper treats two situations: 1) interpretation of scenes resulting from a simple geometric structure (orthogonality) in which case we seek to determine the orientation of this structure relatively to the viewer (three rotations) and 2) recognition of moderately complex objects whose shapes (geometrical and topological properties) are provided in advance. The recognition technique is limited to objects containing, among others, straight edges and planar faces. In the first case the computation can be carried out by a parallel algorithm which selects the solution that has received the largest number of votes (accumulation space). In the second case an object is uniquely assigned to a set of image features through a search strategy. As a by-product, the spatial position and orientation (six degrees of freedom) of each recognized object is determined as well. The method is valid over a wide range of perspective images and it does not require perfect low-level image segmentation. It has been successfully implemented for recognizing a class of industrial parts.     

Forward non-rigid motion tracking for facial MoCap

For the existing motion capture (MoCap) data processing methods, manual interventions are always inevitable, most of which are derived from the data tracking process. This paper addresses the problem of tracking non-rigid 3D facial motions from sequences of raw MoCap data in the presence of noise, outliers and long time missing. We present a novel dynamic spatiotemporal framework to automatically solve the problem. First, based on a 3D facial topological structure, a sophisticated non-rigid motion interpreter (SNRMI) is put forward; together with a dynamic searching scheme, it cannot only track the non-missing data to the maximum extent but recover missing data (it can accurately recover more than five adjacent markers under long time (about 5 seconds) missing) accurately. To rule out wrong tracks of the markers labeled in open structures (such as mouth, eyes), a semantic-based heuristic checking method was raised. Second, since the existing methods have not taken the noise propagation problem into account, a forward processing framework is presented to solve the problem. Another contribution is the proposed method could track facial non-rigid motions automatically and forward, and is believed to greatly reduce even eliminate the requirements of human interventions during the facial MoCap data processing. Experimental results proved the effectiveness, robustness and accuracy of our system.     

三维形状特征提取技术研究进展

三维形状模型广泛应用于工业设计、教育、生物医药、动画娱乐、文物保护等多个领域中。三维形状模型的特征提取是计算机图形学和模式识别领域的重要问题,近年来受到学者的广泛关注。尤其是具有铰链、关节等的非刚性三维形状通常会发生变形,进一步增加了形状特征提取的难度。主要研究、分析、总结了近几年出现的刚性三维形状和非刚性三维形状的特征提取算法,分析了三维形状特征提取的难点,给出了三维形状特征提取的发展进程。介绍了近年来三维形状特征匹配研究领域中常用的一些测试数据库,重点探讨了非刚性三维形状的特征匹配方法,并展望了三维形状特征提取、特征匹配的未来发展方向。     

Nonrigid structure-from-motion: estimating shape and motion with hierarchical Priors

This paper describes methods for recovering time-varying shape and motion of non-rigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talking person, we would like to estimate the 3D shape of the face at each instant, and learn a model of facial deformation. Time-varying shape is modeled as a rigid transformation combined with a non-rigid deformation. Reconstruction is ill-posed if arbitrary deformations are allowed, and thus additional assumptions about deformations are required. We first suggest restricting shapes to lie within a low-dimensional subspace, and describe estimation algorithms. However, this restriction alone is insufficient to constrain reconstruction. To address these problems, we propose a reconstruction method using a Probabilistic Principal Components Analysis (PPCA) shape model, and an estimation algorithm that simultaneously estimates 3D shape and motion for each instant, learns the PPCA model parameters, and robustly fills-in missing data points. We then extend the model to model temporal dynamics in object shape, allowing the algorithm to robustly handle severe cases of missing data.     

Continuous Generalized Procrustes analysis

Two-dimensional shape models have been successfully applied to solve many problems in computer vision, such as object tracking, recognition, and segmentation. Typically, 2D shape models are learned from a discrete set of image landmarks (corresponding to projection of 3D points of an object), after applying Generalized Procustes Analysis (GPA) to remove 2D rigid transformations. However, the standard GPA process suffers from three main limitations. Firstly, the 2D training samples do not necessarily cover a uniform sampling of all the 3D transformations of an object. This can bias the estimate of the shape model. Secondly, it can be computationally expensive to learn the shape model by sampling 3D transformations. Thirdly, standard GPA methods use only one reference shape, which can might be insufficient to capture large structural variability of some objects.To address these drawbacks, this paper proposes continuous generalized Procrustes analysis (CGPA). CGPA uses a continuous formulation that avoids the need to generate 2D projections from all the rigid 3D transformations. It builds an efficient (in space and time) non-biased 2D shape model from a set of 3D model of objects. A major challenge in CGPA is the need to integrate over the space of 3D rotations, especially when the rotations are parameterized with Euler angles. To address this problem, we introduce the use of the Haar measure. Finally, we extended CGPA to incorporate several reference shapes. Experimental results on synthetic and real experiments show the benefits of CGPA over GPA.     

Feature-Preserved 3D Canonical Form

Measuring the dissimilarity between non-rigid objects is a challenging problem in 3D shape retrieval. One potential solution is to construct the models’ 3D canonical forms (i.e., isometry-invariant representations in 3D Euclidean space) on which any rigid shape matching algorithm can be applied. However, existing methods, which are typically based on embedding procedures, result in greatly distorted canonical forms, and thus could not provide satisfactory performance to distinguish non-rigid models. In this paper, we present a feature-preserved canonical form for non-rigid 3D watertight meshes. The basic idea is to naturally deform original models against corresponding initial canonical forms calculated by Multidimensional Scaling (MDS). Specifically, objects are first segmented into near-rigid subparts, and then, through properly-designed rotations and translations, original subparts are transformed into poses that correspond well with their positions and directions on MDS canonical forms. Final results are obtained by solving nonlinear minimization problems for optimal alignments and smoothing boundaries between subparts. Experiments on two non-rigid 3D shape benchmarks not only clearly verify the advantages of our algorithm against existing approaches, but also demonstrate that, with the help of the proposed canonical form, we can obtain significantly better retrieval accuracy compared to the state of the art.     

A factorization-based approach for articulated nonrigid shape, motion and kinematic chain recovery from video

Recovering articulated shape and motion, especially human body motion, from video is a challenging problem with a wide range of applications in medical study, sport analysis and animation, etc. Previous work on articulated motion recovery generally requires prior knowledge of the kinematic chain and usually does not concern the recovery of the articulated shape. The non-rigidity of some articulated part, e.g. human body motion with nonrigid facial motion, is completely ignored. We propose a factorization-based approach to recover the shape, motion and kinematic chain of an articulated object with nonrigid parts altogether directly from video sequences under a unified framework. The proposed approach is based on our modeling of the articulated non-rigid motion as a set of intersecting motion subspaces. A motion subspace is the linear subspace of the trajectories of an object. It can model a rigid or non-rigid motion. The intersection of two motion subspaces of linked parts models the motion of an articulated joint or axis. Our approach consists of algorithms for motion segmentation, kinematic chain building, and shape recovery. It handles outliers and can be automated. We test our approach through synthetic and real experiments and demonstrate how to recover articulated structure with non-rigid parts via a single-view camera without prior knowledge of its kinematic chain.     

融合BOW模型的多特征子空间行人重识别算法

针对目前行人重识别算法在目标外观特征和度量算法方面的问题,提出一种融合BOW模型的多特征子空间行人重识别算法。在行人图像上采用2-D高斯模板将图像背景弱化,然后提取BOW特征描述子和YUV+HSV颜色特征描述子,并将其融合组成最终的特征描述子。在相似性度量方面,采用在原始特征空间学习一个子空间,并在该子空间学习测度矩阵的方法进行相似性度量。在VIPeR和CUHK01两个数据集上的实验结果表明,提出的算法能够明显地提高行人重识别率。     

On Single-Sequence and Multi-Sequence Factorizations

Subspace based factorization methods are commonly used for a variety of applications, such as 3D reconstruction, multi-body segmentation and optical flow estimation. These are usually applied to a single video sequence. In this paper we present an analysis of the multi-sequence case and place it under a single framework with the single sequence case. In particular, we start by analyzing the characteristics of subspace based spatial and temporal segmentation. We show that in many cases objects moving with different 3D motions will be captured as a single object using multi-body (spatial) factorization approaches. Similarly, frames viewing different shapes might be grouped as displaying the same shape in the temporal factorization framework. Temporal factorization provides temporal grouping of frames by employing a subspace based approach to capture non-rigid shape changes (Zelnik-Manor and Irani, 2004). We analyze what causes these degeneracies and show that in the case of multiple sequences these can be made useful and provide information for both temporal synchronization of sequences and spatial matching of points across sequences. A preliminary version of this paper appeared in Zelnik-Manor and Irani (2003).     

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.     

基于相关子空间的多源离群检测算法

传统的离群检测方法多数源于单个数据集或多数据源融合后的单一数据集,其检测结果忽略了多源数据之间的关联知识和单数据源中的关键信息。为了检测多源数据之间的离群关联知识,提出一种基于相关子空间的多源离群检测算法RSMOD。结合[k]近邻集和反向近邻集的双向影响,给出面向多源数据的对象影响空间,提高了离群对象度量的准确性;在影响空间基础上,提出面向多源数据的稀疏因子及稀疏差异因子,有效地刻画了数据对象在多源数据中的稀疏程度,重新定义了相关子空间的度量,使其能适用于多源数据集,并给出基于相关子空间的离群检测算法;采用人工合成数据集和真实的美国人口普查数据集,实验验证了RSMOD算法的性能并分析了源于多数据集的离群关联知识。     

基于随机子空间的局部鉴别投影*

针对高维数据容易对噪声敏感及容易造成维数灾难问题,文中提出基于随机子空间的局部鉴别投影算法(RSLDP).利用随机子空间方法对高维的原始数据进行特征选择,在生成的低维特征子空间构造近邻图,降低噪声影响.RSLDP通过最大化局部类间加权散度和最小化局部类内加权散度,同时最小化样本的总体局部散度,改进局部最大间距鉴别嵌入算法,较好刻画样本与其类间类内近邻中心点的关系,有利于鉴别特征的提取.在CMU PIE和AR这2个人脸数据库上的实验表明文中算法的有效性.     

A linear signal decomposition approach to affine invariant contour identification

Means for the identification of objects from contours despite affine transform induced distortions using a linear signal space decomposition are described. This technique also yields robust estimates of the 3-D rotations of a near planar object. The ability to determine object identity and orientation from a single model representation without iteration or combinatorial search proceeds from the use of affine invariant differential measures derived via Lie group theory. The technique is extremely robust owing to the error rejection properties of signal space projections. Results illustrating the resilience of the solutions in the presence of severe non-affine distortion and pixelization are given.     

物体变形的广义形态变换方法

将广义形态变换理论用于非刚体运动的描述和内插,通过对非刚体的凸剖分把非刚体的运动分解为非刚体的变形与子凸集的旋转,提出物体近似骨架的概念;通过近似骨架实现子凸集匹配,实现了任意非同拓扑结构(包括有孔及凹多面体)物体的变形．广义形态变换具有基于体元的变形方法和基于边界形状的变形方法的优点,同时克服了它们的缺点．实验表明,该方法变形物体边界光滑、定位精度高、计算速度快,可应用于CAD、虚拟现实和生物医学工程。     

Charting-based subspace learning for video-based human action classification

We use charting, a non-linear dimensionality reduction algorithm, for articulated human motion classification in multi-view sequences or 3D data. Charting estimates automatically the intrinsic dimensionality of the latent subspace and preserves local neighbourhood and global structure of high-dimensional data. We classify human actions sub-sequences of varying lengths of skeletal poses, adopting a multi-layered subspace classification scheme with layered pruning and search. The sub-sequences of varying lengths of skeletal poses can be extracted using either markerless articulated tracking algorithms or markerless motion capture systems. We present a qualitative and quantitative comparison of single-subspace and multiple-subspace classification algorithms. We also identify the minimum length of action skeletal poses, required for accurate classification, using competing classification systems as the baseline. We test our motion classification framework on HumanEva, CMU, HDM05 and ACCAD mocap datasets and achieve similar or better classification accuracy than various comparable systems.     

Acquiring 3-D models from sequences of contours

This paper explores shape from contour for acquiring 3-D graphics models. In this method, a continuous sequence of images is taken as an object rotates. A smooth convex shape can be estimated instantaneously from its contour and by the first derivative of contour movement (trace of contour, or contour distribution with time). We also analyze shapes that do not satisfy the conditions of smoothness and visibility, which are indispensable for modeling an object. A region that does not expose as contour yields a nonsmoothness in the tracked contour movement. We can thus detect such a region by contour distribution filtering and extract its accurate location by computing the left and right derivatives of the distribution. This has not been studied previously. These unknown regions are obtained for further investigation using other visual cues. A general approach for building a geometrical object model using contours is then described. The entire process from silhouettes to a 3-D model is based local computation; this is promising for producing shapes in real time. Our direct goal is to establish 3-D graphics models of human faces for the growing needs of visual communications. We have obtained some good results