基于形变模型由立体序列图象恢复物体的3D形状

结合立体视觉和形变模型提出了一种新的物体3D形状的恢复方法。采用立体视觉方法导出物体表面的3D坐标;利用光流模型估计物体的3D运动,根据此运动移动形变模型,使其对准物体的表面块;由形变模型将由各幅图象得到的离散的3D点融为一起,得到物体的表面形状。实验结果表明该方法能用于形状复杂的物体恢复。     

Tracking rigid objects using integration of model-based and model-free cues

Model-based 3-D object tracking has earned significant importance in areas such as augmented reality, surveillance, visual servoing, robotic object manipulation and grasping. Key problems to robust and precise object tracking are the outliers caused by occlusion, self-occlusion, cluttered background, reflections and complex appearance properties of the object. Two of the most common solutions to the above problems have been the use of robust estimators and the integration of visual cues. The tracking system presented in this paper achieves robustness by integrating model-based and model-free cues together with robust estimators. As a model-based cue, a wireframe edge model is used. As model-free cues, automatically generated surface texture features are used. The particular contribution of this work is the integration framework where not only polyhedral objects are considered. In particular, we deal also with spherical, cylindrical and conical objects for which the complete pose cannot be estimated using only wireframe models. Using the integration with the model-free features, we show how a full pose estimate can be obtained. Experimental evaluation demonstrates robust system performance in realistic settings with highly textured objects and natural backgrounds.     

基于BP神经网络的隐式曲线构造方法

隐式曲线与曲面是当前计算机图形学研究的热点之一。通过把BP神经网络与隐式曲线构造原理相结合，提出了一种构造隐式曲线的新方法，即首先由约束点构造神经网络的输入与输出，把描述物体边界曲线的隐式函数转化为显式函数；然后用BP神经网络对此显式函数进行逼近；最后由仿真曲面得到物体边界的拟合曲线。该新方法不同于传统的对显式函数的逼近方法，因为传统方法无法描述封闭的曲线；也不同于基于优化的拟合隐式曲线方法，因为它无须考虑函数的形式或多项式的次数。实验表明，该新方法有很强的物体边界描述能力和缺损修复能力，因而在物体边界重建、缺损图像复原等领域有一定的应用前景。     

General-purpose curvilinear object detection with fuzzy mathematical morphology

Curvilinear object detection is the common denominator of several applications. Some illustrative examples are road detection from aerial or satellite images, human airways from volumetric 3D scans or vascular structures in eye-fundus images. In this work, we propose two general-purpose curvilinear object detectors that may serve as building blocks for application-specific systems. To do so, we employ fuzzy mathematical morphology operators due to their robustness with respect to uncertainty and noise, and the trade-off they offer between expressive power and computational requirements. The extraction of linear features is based on, respectively, the fuzzy hit-or-miss transform and the fuzzy top-hat transform. They can be customized depending on the width of the objects of interest. We compare these two approaches with other state-of-the-art, general-purpose curvilinear object detectors to highlight their strengths and shortcomings. Both detectors succeed at localizing the objects of interest in different greyscale images.     

Wireframe Projections: Physical Realisability of Curved Objects and Unambiguous Reconstruction of Simple Polyhedra

The reconstruction of an object from a single 2D projection of a 3D wireframe model is a vision problem with applications in CAD/CAM and computer graphics.We propose an algorithm for the interpretation of wireframe projections based on assigning semantic and numerical depth labels to lines. This method allows us to state necessary and sufficient conditions for the physical realisability of a wireframe projection of a curved object. The presence of linear features provides further constraints on the positions of object vertices. For example, each straight line gives rise to a coplanarity constraint between a set of object vertices.We show that extra information, such as vanishing points, parallel lines or user-entered depth-parity information, is sufficient to uniquely determine the face-circuits in wireframe projections of polyhedra with simple trihedral vertices. In fact, a polyhedron with simple trihedral vertices can be unambiguously reconstructed from its 3D wireframe model.     

Isthmus based parallel and symmetric 3D thinning algorithms

We propose a 3D symmetric homotopic thinning method based on the critical kernels framework. It may produce either curvilinear or surface skeletons, depending on the criterion that is used to prevent salient features of the object from deletion. In our new method, rather than detecting curve or surface extremities, we detect isthmuses, that is, parts of an object that are “locally like a curve or a surface”. This allows us to propose a natural extension of our new method that copes with the robustness to noise issue, this extension is based on a notion of “isthmus persistence”. As far as we know, this is the first method that permits to obtain 3D symmetric and robust curvilinear/surface skeletons of objects made of voxels.     

一种三角网格模型的轮廓生成方法

从三维网格模型中提取轮廓信息是一个具有挑战性的过程.现有的方法一般是基于局部形状特征分析,如曲面的曲率和相邻面法向之间的夹角,但其特性通常对模型中的局部特征变化敏感.为了解决这个问题,提出一种基于三维形状几何近似的轮廓提取方法.利用完善的变分几何分割算法来得到一套完整的描述性特征曲线,首先基于变分几何近似方法划分模型为...     

A Framework for Automatically Recovering Object Shape,Reflectance and Light Sources from Calibrated Images

In this paper, we present a complete framework for recovering an object shape, estimating its reflectance properties and light sources from a set of images. The whole process is performed automatically. We use the shape from silhouette approach proposed by R. Szeliski (1993) combined with image pixels for reconstructing a triangular mesh according to the marching cubes algorithm. A classification process identifies regions of the object having the same appearance. For each region, a single point or directional light source is detected. Therefore, we use specular lobes, lambertian regions of the surface or specular highlights seen on images. An identification method jointly (i) decides what light sources are actually significant and (ii) estimates diffuse and specular coefficients for a surface represented by the modified Phong model (Lewis, 1994). In order to validate our algorithm efficiency, we present a case study with various objects, light sources and surface properties. As shown in the results, our system proves accurate even for real objects images obtained with an inexpensive acquisition system.     

立体视频对象分割及其三维重建算法研究*

为更加有效分析立体视频对象,本文提出了一种基于离散冗余小波变换的立体视频对象分割算法,首先采用离散冗余小波变换提取特征点结合DT网格技术的视差估计方法,获得了可靠的视差场,再利用视差信息对立体视频中静止对象进行分割。对于立体视频序列中的运动对象,采用离散冗余小波提取运动区域的方法进行分割。实验结果表明,本算法对有重叠的多视频对象具有较好的分割效果,可同时分割静止物体和运动物体,具有较好的精确性和鲁棒性。对于分割出的立体视频对象,结合深度信息对其进行三维重建,得到较好的三维效果。     

用于遥感图像人造目标识别的三维建模方法研究

该文研究了用于遥感图像人造地物目标识别的三维建模方法,文中分析了识别任务的特点,比较了一般的建模方法,介绍了一种基于广义锥思想的几何表示方法,并利用面向对象的技术来表示模型内部数据及其操作。     

Sketch-Based 3D-Shape Creation for Industrial Styling Design

While recent decades have seen significant progress in CAD software, current state of the art still appears insufficient when it comes to the styling design of products. This is evidenced by the fact that a-significant portion of early design activities such as concept development and style generation occurs almost exclusively in 2D environments - be it the traditional pen-and-paper environment or its digital equivalents. The authors describe a pen-based modeling system for the styling design of 3D objects. Their system is tailored toward the rapid and intuitive design of styling features such as free-form curves and surfaces. Basic wireframe and surfaces are constructed and modified using the strategy of curve creation, curve modification, surface creation, and finally surface modification     

基于几何特征的曲面物体识别

基于几何特征的曲面物体识别方法是通过从景物深度图象上提取景物表面的高斯曲率和平均曲率、曲率直方图,曲率的熵等几何信息,将景物用一个属性关系图ＡＲＧ来表示,并与模型库中的模型ＡＲＧ图进行优化匹配,从而来识别曲面景物。该方法主要是针对机器零部件等人造曲面物体的识别问题而设计的,其曲面几何特征的描述方法对二阶曲面比较有效,实验表明,应用该方法可成功地从深度图象中识别机器零部件等曲面物体,且有较好的识别结     

融合目标增强与稀疏重构的显著性检测

目的 为了解决图像显著性检测中存在的边界模糊,检测准确度不够的问题,提出一种基于目标增强引导和稀疏重构的显著检测算法（OESR）。方法 基于超像素,首先从前景角度计算超像素的中心加权颜色空间分布图,作为前景显著图;由图像边界的超像素构建背景模板并对模板进行预处理,以优化后的背景模板作为稀疏表示的字典,计算稀疏重构误差,并利用误差传播方式进行重构误差的校正,得到背景差异图;最后,利用快速目标检测方法获取一定数量的建议窗口,由窗口的对象性得分计算目标增强系数,以此来引导两种显著图的融合,得到最终显著检测结果。结果 实验在公开数据集上与其他12种流行算法进行比较,所提算法对具有不同背景复杂度的图像能够较准确的检测出显著区域,对显著对象的提取也较为完整,并且在评价指标检测上与其他算法相比,在MSRA10k数据集上平均召回率提高4.1%,在VOC2007数据集上,平均召回率和F检验分别提高18.5%和3.1%。结论 本文提出一种新的显著检测方法,分别利用颜色分布与对比度方法构建显著图,并且在显著图融合时采用一种目标增强系数,提高了显著图的准确性。实验结果表明,本文算法能够检测出更符合视觉特性的显著区域,显著区域更加准确,适用于自然图像的显著性目标检测、目标分割或基于显著性分析的图像标注。     

结合关键点与引导向量的旋转目标检测网络

目的 目标检测是遥感智能解译中重要的研究方向之一,大多数目标检测算法难以实现密集排列的旋转目标的高精度检测。提出了一种基于关键点与引导向量预测的目标检测算法,实现高精度旋转目标检测的同时,还可对目标的朝向进行表征。方法 首先提出了一种新的旋转目标建模方式,将目标检测分解成中心点、头部顶点、引导向量以及目标宽度的参数回归以更贴合检测目标;其次设计旋转椭圆高斯核,能够更好地拟合遥感目标的形状,从而提升关键点的预测精度;最后通过预测中心点指向头部顶点的引导向量,完成同一个目标内中心点与头部顶点的匹配,从而生成一个精准的带方向的旋转矩形检测框。结果 在大长宽比舰船目标的HRSC(high-resolution ship collections)数据集上的实验结果表明,相比于其他主流的目标检测算法,本文算法获得了更好的检测结果,在VOC 2007(visual object classes)和VOC 2012的平均精度分别达到了90.78%和97.85%。在小长宽比飞机目标UCAS-AOD(UCAS-high resolution aerial object detection dataset)数据集上达到了98.81%的平均精度。实验结果表明了本文算法的可行性与有效性。结论 本文算法利用椭圆高斯核计算中心点与头部顶点,并设计引导向量对点匹配关系进行约束,实现了旋转目标的方向检测。     

3D reconstruction of complex curved objects from line drawings

An active research topic in computer vision and graphics is developing algorithms that can reconstruct the 3D surface of curved objects from line drawings. There are a number of algorithms have been dedicated to solve this problem, but they can't solve this problem when the geometric structure of a curved object becomes complex. This paper proposes a novel approach to reconstructing a complex curved 3D object from single 2D line drawings. Our approach has three steps:(1) decomposing a complex line drawing into several simpler line drawings and transforming them into polyhedron;(2) reconstructing the 3D wireframe of curved object from these simpler line drawings and generating the curved faces;(3) combining the 3D objects into the complete objects. A number of examples are given to demonstrate the ability of our approach to successfully perform reconstruction of curved objects which are more complex than previous methods.     

Error estimation in reconstruction of quadratic curves in 3D space

Many natural and man-made objects have planar and curvilinear surfaces. The images of such curves do not usually have sufficient distinctive features to apply conventional feature-based reconstruction algorithms. In this paper, we describe a method for the reconstruction of various kinds of quadratic curves in 3D space as an intersection of two cones containing the respective projected digitized curve images in the presence of Gaussian noise. The advantage of this method is that it overcomes the correspondence problem that occurs in pairs of projections of the curve. Using nonlinear least-squares curve fitting, the parameters of a curve in 2D digitized image planes are determined. From this we reconstruct the 3D quadratic curve. Relevant mathematical formulations and analytical solutions for obtaining the equation of the reconstructed curve are given. Simulation studies have been conducted to observe the effect of noise on errors in the process of reconstruction. Results for various types of quadratic curves are presented using simulation studies. These are the main contributions of this work. The angle between the reconstructed and the original quadratic curves in 3D space has been used as the criterion for the measurement of the error. The results of this study are useful for the design of a stereo-based imaging system (such as the LBW decision in cricket, the path of a missile, robotic vision, path planning, etc.) and for the best reconstruction with minimum error.     

Thermophysical algebraic invariants from infrared imagery forobject recognition

An important issue in developing a model-based vision system is the specification of features that are invariant to viewing and scene conditions and also specific, i.e., the feature must have different values for different classes of objects. We formulate a new approach for establishing invariant features. Our approach is unique in the field since it considers not just surface reflection and surface geometry in the specification of invariant features, but it also takes into account internal object composition and state which affect images sensed in the nonvisible spectrum. A new type of invariance called thermophysical invariance is defined. Features are defined such that they are functions of only the thermophysical properties of the imaged objects. The approach is based on a physics-based model that is derived from the principle of the conservation of energy applied at the surface of the imaged object     

多方法相融合的复杂物体深度信息的恢复

在恢复图象深度信息的方法之中,利用立体视觉的偏差来精确地定位物体的深度,是行之有效的,但只能适用于可匹配的特征点,如何建立左右图象中对应点的匹配是该方法的主要障碍;Ｓｈａｐｅ Ｆｒｏｍ Ｓｈａｄｉｎｇ方法是利用单幅图象的灰度信息获取物体表面的形状信息（表面的方向）,而不能获得其深度信息,其约束条件是表面的光滑性。在此用神经网络方法将二者融合起来,形成优势互补,用来获取物体的深度信息,通过对合成图象