Reconstruction of a Scene with Multiple Linearly Moving Objects

In this paper we describe an algorithm to recover the scene structure, the trajectories of the moving objects and the camera motion simultaneously given a monocular image sequence. The number of the moving objects is automatically detected without prior motion segmentation. Assuming that the objects are moving linearly with constant speeds, we propose a unified geometrical representation of the static scene and the moving objects. This representation enables the embedding of the motion constraints into the scene structure, which leads to a factorization-based algorithm. We also discuss solutions to the degenerate cases which can be automatically detected by the algorithm. Extension of the algorithm to weak perspective projections is presented as well. Experimental results on synthetic and real images show that the algorithm is reliable under noise.     

Reconstruction of General Curves,Using Factorization and Bundle Adjustment

In this paper, we extend the notion of affine shape, introduced by Sparr, from finite point sets to curves. The extension makes it possible to reconstruct 3D-curves up to projective transformations, from a number of their 2D-projections. We also extend the bundle adjustment technique from point features to curves.The first step of the curve reconstruction algorithm is based on affine shape. It is independent of choice of coordinates, is robust, does not rely on any preselected parameters and works for an arbitrary number of images. In particular this means that, except for a small set of curves (e.g. a moving line), a solution is given to the aperture problem of finding point correspondences between curves. The second step takes advantage of any knowledge of measurement errors in the images. This is possible by extending the bundle adjustment technique to curves.Finally, experiments are performed on both synthetic and real data to show the performance and applicability of the algorithm.     

A Model-Selection Framework for Multibody Structure-and-Motion of Image Sequences

Given an image sequence of a scene consisting of multiple rigidly moving objects, multi-body structure-and-motion (MSaM) is the task to segment the image feature tracks into the different rigid objects and compute the multiple-view geometry of each object. We present a framework for multibody structure-and-motion based on model selection. In a recover-and-select procedure, a redundant set of hypothetical scene motions is generated. Each subset of this pool of motion candidates is regarded as a possible explanation of the image feature tracks, and the most likely explanation is selected with model selection. The framework is generic and can be used with any parametric camera model, or with a combination of different models. It can deal with sets of correspondences, which change over time, and it is robust to realistic amounts of outliers. The framework is demonstrated for different camera and scene models. Most of the presented research was carried out while all three authors were at Monash University.     

A Geometric Approach for the Theory and Applications of 3D Projective Invariants

A central task of computer vision is to automatically recognize objects in real-world scenes. The parameters defining image and object spaces can vary due to lighting conditions, camera calibration and viewing position. It is therefore desirable to look for geometric properties of the object which remain invariant under such changes in the observation parameters. The study of such geometric invariance is a field of active research. This paper presents the theory and computation of projective invariants formed from points and lines using the geometric algebra framework. This work shows that geometric algebra is a very elegant language for expressing projective invariants using n views. The paper compares projective invariants involving two and three cameras using simulated and real images. Illustrations of the application of such projective invariants in visual guided grasping, camera self-localization and reconstruction of shape and motion complement the experimental part.     

基于特征点跟踪的运动目标接触时间估计方法研究

解决估计运动目标和静止观测者之间的接触时间(time-to-contact)的问题.首先定义了广义接触时间的概念,并提出了基于特征点跟踪的估计匀速运动目标接触时间的理论依据和利用特征线段估计接触时间的解决思路.随后,提出了一个结合Kalman滤波器的估计匀速运动目标和静止观测者之间接触时间的特征点跟踪方案,并讨论了特征点的选择准则、运动分割的方法、以及所采用的特征点跟踪的方法.最后,针对标定TTC的运动目标序列图像进行接触时间的估计实验,实验的结果是令人满意的.     

一种受雨滴影响的运动目标检测方法

提出一种在户外受雨滴影响的视频场景中检测运动目标的方法.在R,G,B空间构建雨滴在视频中的成像模型,该模型可以计算受雨滴影响像素的亮度变化值.能够有效克服现有模型只能针对某些特定类型雨滴进行辨识的局限性.在使用基于颜色信息的雨滴成像模型基础上,提出运动目标检测函数,此函数可以有效抑制雨滴产生的干扰.实验结果表明,提出的雨滴成像模型和相应的检测函数与现有模型比较,能够适用于多种不同受雨滴影响的图像序列采样环境,对于运动目标具有更好的分辨能力,并有更强的鲁棒性.     

Machine vision for industry: Tasks,tools and techniques

The ‘why’, ‘how’ and ‘what’ of industrial machine vision systems are surveyed-why vision is important, how it is accomplished and what sorts of tasks it is being applied to. Examples are given of vision techniques and applications from Japan, France, the GDR and the USA.     

照明方向及反射特性参数的鲁棒估计

由图象明暗度提取物体表面三维形状需要预知照明方向及表面反射特性参数，但这些参数在实际应用中往往难于得到，文中提出了一种新的方法，该方法只需图象存在奇点，就可直接由灰度图象估计照明方向和反射特性参数，实验证明，该方法具有计算量少，误差小，鲁棒性好等优点。     

EM-GPA: Generalized Procrustes analysis with hidden variables for 3D shape modeling

Aligning shapes is essential in many computer vision problems and generalized Procrustes analysis (GPA) is one of the most popular algorithms to align shapes. However, if some of the shape data are missing, GPA cannot be applied. In this paper, we propose EM-GPA, which extends GPA to handle shapes with hidden (missing) variables by using the expectation-maximization (EM) algorithm. For example, 2D shapes can be considered as 3D shapes with missing depth information due to the projection of 3D shapes into the image plane. For a set of 2D shapes, EM-GPA finds scales, rotations and 3D shapes along with their mean and covariance matrix for 3D shape modeling. A distinctive characteristic of EM-GPA is that it does not enforce any rank constraint often appeared in other work and instead uses GPA constraints to resolve the ambiguity in finding scales, rotations, and 3D shapes. The experimental results show that EM-GPA can recover depth information accurately even when the noise level is high and there are a large number of missing variables. By using the images from the FRGC database, we show that EM-GPA can successfully align 2D shapes by taking the missing information into consideration. We also demonstrate that the 3D mean shape and its covariance matrix are accurately estimated. As an application of EM-GPA, we construct a 2D + 3D AAM (active appearance model) using the 3D shapes obtained by EM-GPA, and it gives a similar success rate in model fitting compared to the method using real 3D shapes. EM-GPA is not limited to the case of missing depth information, but it can be easily extended to more general cases.     

Application of Self-Organisation Neural Network for Direct Shape from Shading

In this paper, a supervised self-organisation Neural Network (NN) for direct shape from shading is developed. The structure of the NN for the inclined light source model is derived based on the maximum uphill direct shape from shading approach. The major advantage of the NN model presented is the parallel learning or weight evolution for the direct shading. Here the proved convergent learning rule, the rate of convergence and a zero initialisation condition are shown. To increase the rate of convergence, the momentum factor is introduced. Further-more, the application of the network on IC (Integrated Circuit) component shape reconstruction is presented.     

基于神经网络的运动参数估计

分别就两种约束使用神经网络对三维刚体运动进行参数估计.一是基于三维点匹配,将预测的运动参数作用于运动前的坐标,与运动后坐标进行比较;二是基于二维运动场,将使用预测的运动参数计算得出的二维运动场与图像序列中计算得出的二维运动场进行比较.两个神经网络均使用Newton-Raphson方法更新权值,以达到目标误差最小化.通过实验验证了该神经网络方法.     

基于SFM算法的三维人脸模型重建

提出了一种根据两幅正面人脸图像和一幅侧面图像重建人脸三维模型的算法，该算法主要包括4个步骤：寻找匹配点；采用SFM算法计算出特征点的三维坐标，并组成稀疏的三维网格结构；采用分步紧支撑径向基函数进行三维插值，得到三维模型；最后根据多分辨图像拼接算法生成纹理图像并将其映射到三维模型上，从而增强真实感，与其它算法相比，该算法最大的不同之处在于匹配点的寻找，匹配点的准确与否直接影响SFM算法结果的正确性，许多寻找匹配点的算法如角点匹配算法，在处理人脸图像时得到的结果并不稳定，这是因为人脸图像上包含了许多低纹理和重复纹理区域，大多数算法将代表人脸结构基本特征的基准模型运用在重建过程的最后一步，通过三维逼近运算，得到最终的重建模型，而该算法将反映人脸共性特征的几何对称性和规律性运用到匹配点的寻找中，能够快速准确地找出SFM算法需要的匹配点，用户使用普通照相机拍摄到的图像经本算法的处理后就可以得到相应的三维人脸结构。     

基于图像的几何建模技术综述

三维建模是计算机图形学与计算机视觉领域研究的重要问题.近年来,基于图像的三维建模技术因其成本低、操作简单、逼真性高等优势,逐渐得到研究者的重视,相关研究成果也被广泛应用于文物数字保护、智能人机交互、数字特效制作、实时监控等领域,具有极其重要的研究意义与实用价值.基于图像的建模研究由单一图像、图像序列或视频中,通过自动或交互的方式,恢复出物体、场景三维模型的方法.而基于图像的建模首先需要解决的核心问题是基于图像的几何建模问题.它主要研究的是如何从图像中恢复出物体或场景的三维几何信息.而该技术领域当前综述性文章的缺乏成为其发展的制约因素.因此,对基于图像的几何建模技术进行了综述性的分析与讨论.侧重从计算机视觉的角度,按照建模时所使用视觉线索信息的区别,对目前主流的基于图像几何建模方法进行了归类;分别对各类方法进行了基本原理探讨与研究现状介绍,并作了较深入的对比分析与讨论;最后,经过对现有研究工作的分析,对该领域存在的问题作出了总结,并对其未来可能的发展与研究方向给出了一些预测性建议.     

Appearance Sampling of Real Objects for Variable Illumination

The appearance of an object greatly changes under different lighting conditions. Even so, previous studies have demonstrated that the appearance of an object under varying illumination conditions can be represented by a linear subspace. A set of basis images spanning such a linear subspace can be obtained by applying the principal component analysis (PCA) for a large number of images taken under different lighting conditions. Since little is known about how to sample the appearance of an object in order to correctly obtain its basis images, it was a common practice to use as many input images as possible. In this study, we present a novel method for analytically obtaining a set of basis images of an object for varying illumination from input images of the object taken properly under a set of light sources, such as point light sources or extended light sources. Our proposed method incorporates the sampling theorem of spherical harmonics for determining a set of lighting directions to efficiently sample the appearance of an object. We further consider the issue of aliasing caused by insufficient sampling of the object's appearance. In particular, we investigate the effectiveness of using extended light sources for modeling the appearance of an object under varying illumination without suffering the aliasing caused by insufficient sampling of its appearance.     

自动分割视频运动目标的一种实现方法

随着基于运动对象特征编码的MPEG-4压缩标准的制定及智能监控系统的广泛应用,从视频序列中分割出运动对象的算法成为当今研究的热点。为此,文章提出并实现了一种基于互帧差的视频运动对象分割方法。它先从互帧差图像中提取出运动物体的基本轮廓,通过膨胀运算将尽可能是前景的区域分离出来。再将前景区域边缘的象素作为种子队列的元素,从种子队列出发向前景区域内部收缩,最后搜索到运动物体。这种算法方法简单,运算量小,而且只使用了头两帧的信息,因而适合于实时应用。实验结果表明,这种方法能有效地分割出主要的运动目标。     

基于直线光流场的三维运动和结构重建

利用直线间运动对应关系,将像素点光流的概念和定义方法应用于直线,提出了直线光流的概念,建立了求解空间物体运动参数的线性方程组,利用三幅图像21条直线的光流场,可以求得物体运动的12个参数以及空间直线坐标．但是在实际应用当中,要找出这21条直线的光流场是很困难的,因此该文提出了运用解非线性方程组的方法,只需要6条直线的光流．就可以分步求出物体的12个运动参数,并根据求得的12个运动参数和一致的图像坐标系中的直线坐标,求得空间直线的坐标,从而实现了三维场景的重建．     

Using a simple shape measure to improve automatic 3D reconstruction

, a semi-automatic system for 3D reconstruction of brain cells, makes errors in the presence of dense internal cellular structures: it computes the wrong boundary. This paper presents a simple consistency measue based on shape that allows to recognize this error; recovery is achieved by extending previously computed trial boundaries until an improved boundary is computed. More increase in performance will come with more sophisticated consistency measures based on a complete model of the cell.     

复杂表面物体3D模型的获取方法

提出了一种从真实物体中获得其3D模型的方法.该方法通过TOF- Camera获得原始的点云数据,在对点云数据进行三角化、分割、滤波去噪等处理后得到部分物体模型,然后再应用ICP(迭代最近点)算法对其进行配准.配准过程中为了节省内存,删掉重叠的冗余数据.最后对生成的数据进行网格重建,得到完整的网格模型.实验表明该方法能较为快速地获取真实物体的3D模型,显著提高TOF相机获取数据的质量.     

Analysis of three-dimensional rotation and linear shape changes

A relationship between 3D rotation of an object and 2D shape changes in a sequence of images is established. It is shown that with orthographic projections, the 3D rotation angles can be computed from a set of linear shape change parameters.     

破碎刚体复原中的断裂面匹配算法

给出一种断裂面匹配的算法.首先根据形状描述子提取断裂面的特征点;然后根据特征点的特征值是否相近及邻域曲面是否相似得到少量特征显著的相似点对,算法以显著特征点为中心将断裂面划分为多个曲面片,使用三维直方图比较面片间的相似性,对于相似面片内部的特征点不再寻找其相似点,所以得到的相似点对数量少,可靠性高;最后使用引入三角形约束的穷举搜索的方法进行断裂面匹配.实验结果表明,算法能够实现断裂面的部分和完全匹配.