基于形态及受约束结构的三维物体建模方法

文中提出一种基于物体形态及受约束结构的三维物体建模方法,该方法利用具有透视不变性的三维结构来表达物体的各个形态。利用该表达方法可以使机器视觉系统在用单幅灰度图像识别物体时,在模型索引阶段避开求解物体位姿、摄像机参数、特征对应等复杂问题,从而实现先索引后匹配的识别策略,提高识别物体的实时性。文中首先论述了透视不变性和具有透视不变性的受约束结构的基本概念;其次,给出了用受约束结构进行三维物体建模的一般方法和应用实例;最后,指出了这种方法的不足和进一步的研究方向。     

3D虚拟摄像机视角调节的研究

3D应用已经成为趋势,各种3D技术得到广泛的应用,许多3D应用都用到了3D虚拟摄像机.文中主要对3D虚拟摄像机进行了研究,通过调节3D摄像机来调节3D场景的渲染视角,这里主要研究的是通过3D摄像机的平移和旋转来调节渲染视角.由于对于不同的场景,场景的大小不同,场景中3D摄像机的位置和状态也不同,所以需要一种方法,能够对于用户的同一操作,根据不同场景,计算出相应的变换参数来操作3D摄像机.文中找到了一种调节3D摄像机的方法,该方法主要利用变换矩阵和几何关系来计算相应的变换参数,能够根据用户的操作自动计算相应参数来改变3D场景中虚拟摄像机的位置和状态,对3D摄像机进行调节,从而改变渲染视角,使交互更加方便.     

近距离3D人机交互技术研究实现

3D人机交互技术是计算机图形学、虚拟现实和模式识别的交叉融合领域,可分为虚拟环境的显示和三维物体识别。该研究将虚拟环境显示和三维物体识别整合成一个完整的解决方案并应用到1∶1模拟虚拟场景的近距离交互。研究了虚拟现实之间的坐标转换;分析了影响虚拟物体立体显示的三个主要因素：OpenGL中摄像机的张角,摄像机间距和立体图像对的产生;并实现了基于Intel Perceptual Computing的三维物体识别。实验结果显示：该方案在1∶1模拟虚拟场景方面具有良好的3D显示效果,同时在手势识别方面有较高的识别率。     

基于支持向量机与细节层次的三维地形识别与检索

提出对相似3D物体识别与检索的算法．该算法首先使用细节层次模型对3D物体进行三角面片数量的约减，然后提取3D物体的特征．由于所提取的特征维数很大，因此独立成分分析被用来进行3D特征约减．基于约减后的特征，使用支持向量机进行识别与检索．将该算法用于3D丘陵与山地的地形识别中，取得了良好效果。     

基于颜色信息和几何不变性的人脸检测定位

由先验知识我们知道,2D人脸正面图像几何对称;然而,当姿态发生变化时,对于人脸这样的不规则3D几何体,不同的视角、不同的摄像机参数使得在透视成像下得到的图像也不同,并且发现正面人脸具有的对称特性也消失了,因此3D人脸的识别是十分困难的;提出一种从人脸特征的结构特殊性出发,利用2D人脸形状、面部特征等内在的几何约束关系构造射影不变的特征参数、特征关系的射影不变性,同时结合颜色物理信息的人脸检测定位方法,有效地避免了构造3D人脸模型的难题,增强了实验结果的效率、可靠性和稳定性.     

图像特征识别方法研究

图像特征识别的方法及其技术实现系当前模式识别研究领域中最为热门的研究课题之一。本文针对NMI(归一化转动惯量)特征识别、不变矩特征识别和比例特征识别三种图像特征识别方法．通过实验分析了该三种识别方法的缩放不变性、旋转不变性、平移不变性以及不同物体之间的特征差异。实验数据显示NMI特征识别方法具有最佳的识别效果和最快的处理速度。     

一种新的几何约束结构及其射影不变量

几何不变量,特别是射影不变量,是基于单视点灰度图像识别三维物体的一条有效途径．但理论研究表明,只有特定的几何约束结构,才具有射影不变量．所以,研究并发现这种几何约束结构就具有十分重要的意义．该文提出了一种新的由相邻3平面上5条直线组成的几何约束结构及其所具有的射影不变量．该结构较Sugimoto提出的几何约束结构简单,可从结构同样复杂的物体中获得更多的几何不变量,有利于提高物体识别的稳定性;同时,由于该结构大量存在于由多面体组合而构成的人造物体及地面建筑物中,因此它非常适合这类物体的识别．实验验证了文中提出的几何约束结构具有不随物体成像视点改变的射影不变量．     

基于纹理映射与Phong光照模型的体绘制加速算法

为了提高体绘制速度，提出了一种基于纹理映射、具有Phong光照效果的体绘制加速算法．该算法是根据Phong光照模型，利用一单位球面体来仿真相同光照绘制条件下的每一个体素的反射光强，首先形成一个以法线矢量为索引值的反射光强查寻表，再应用窗值变换的加速算法来计算体素的不透明度；然后采用纹理映射的方法将体素光强值与由不透明度组成的3D数据集从物体空间投射到观察空间，再沿视方向融合为3D图象．实验表明，这种3D旋转的明暗修正保证了体绘制中3D旋转几何变换的多视角观察的交互速度．由于该算法综合了体绘制软件算法数据处理与纹理映射硬件加速的优点，并用2D纹理映射与融合的方法实现了体数据的3D重建，因而不仅降低了对计算机硬件与软件环境的要求，而且在目前通用个人计算机上即可获得近似实时的交互绘制速度和良好的3D图象品质．据研究，该算法同样适用于3D纹理映射的体绘制方法．     

基于分层和Radon变换的透视图像矫正技术

由于受到物体与摄像机三维空间相对位置关系的影响,摄像机获取的图像存在透视畸变,影响图像特征提取、识别等后续处理,为此提出一种通过分层矫正和Radon变换相结合的矫正技术.利用射影几何知识,将畸变的图像矫正为满足仿射变换的图像,再将仿射变换矫正为相似变换,利用Radon变换矫正得到标准图像.仿真实验结果表明,该算法可行性高、稳定性好,能推广应用于目标识别等领域.     

一个基于知识的航空影像目标自动识别算法

针对航空影像中复杂背景下目标的自动提取与识别这一难题，提出一种智能型目标识别算法。该算法包括图象分割，不变性参数提取和目标分类，利用一种基于知识的多特征融合和小波理论的多分辨率分析分割和提取图象目标，被提取的每个图象目标的不变性参数由改进的ＢＰ模型将图象目标分类，实验结果表明该识别虎法依据一定的先验知识，辅以人工智能的手段对复杂背景下的目标进行提取，复合，识别处理，从而到较为准确地识别出目标的最终     

基于形态和约束结构的几何哈希法

几何哈希法,作为一种有效的模型搜索算法,在物体识别中有着重要的应用。现有的几何哈希法仅适合于仿射变换下的二维景物识别,论文提出了适合透视投影变换下三维物体识别的几何哈希方法。该方法利用物体的三维形态和物体中具有射影不变量的几何约束结构来构造哈希表。一方面,几何约束结构提供了物体模型的索引功能;另一方面,物体的三维形态提供了物体成像位姿的有关信息,使后续的匹配验证得以简化。实验中使用人造物体对该方法进行了验证,实验表明该方法正确有效。     

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.     

Higher-Order Neural Networks Applied to 2D and 3D Object Recognition

A higher-order neural network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous scaled, translated, and rotated views. Because the 2D object recognition task is a component of the 3D object recognition task, built-in 2D invariance also decreases the size of the training set required for 3D object recognition. We present results for 2D object recognition both in simulation and within a robotic vision experiment and for 3D object recognition in simulation. We also compare our method to other approaches and show that HONNs have distinct advantages for position, scale, and rotation-invariant object recognition.The major drawback of HONNs is that the size of the input field is limited due to the memory required for the large number of interconnections in a fully connected network. We present partial connectivity strategies and a coarse-coding technique for overcoming this limitation and increasing the input field to that required by practical object recognition problems.     

Lines in space. 2. The line formulation

In part 1, we were talking about points, planes, and lines in 3D, more particularly in projective 3-space. The idea is to find algebraic expressions for the various geometric relationships between these objects. We were just on the verge of discovering what would be a good algebraic formulation for lines in projective 3D space. My goal here is to update my original paper to see how the results look using tensor diagram notation. I start by reviewing what we did last time, but will say some things a bit differently. You might pick up more insight from this different viewpoint.     

Model-Based Object Recognition Using Geometric Invariants of Points and Lines

In this paper, we derive new geometric invariants for structured 3D points and lines from single image under projective transform, and we propose a novel model-based 3D object recognition algorithm using them. Based on the matrix representation of the transformation between space features (points and lines) and the corresponding projected image features, new geometric invariants are derived via the determinant ratio technique. First, an invariant for six points on two adjacent planes is derived, which is shown to be equivalent to Zhu's result [1], but in simpler formulation. Then, two new geometric invariants for structured lines are investigated: one for five lines on two adjacent planes and the other for six lines on four planes. By using the derived invariants, a novel 3D object recognition algorithm is developed, in which a hashing technique with thresholds and multiple invariants for a model are employed to overcome the over-invariant and false alarm problems. Simulation results on real images show that the derived invariants remain stable even in a noisy environment, and the proposed 3D object recognition algorithm is quite robust and accurate.     

A Neural Network Approach to Planar-Object Recognition in 3D Space

Most existing 2D object recognition algorithms are not perspective (or projective) invariant, and hence are not suitable for many real-world applications. By contrast, one of the primary goals of this research is to develop a flat object matching system that can identify and localise an object, even when seen from different viewpoints in 3D space. In addition, we also strive to achieve good scale invariance and robustness against partial occlusion as in any practical 2D object recognition system. The proposed system uses multi-view model representations and objects are recognised by self-organised dynamic link matching. The merit of this approach is that it offers a compact framework for concurrent assessments of multiple match hypotheses by promoting competitions and/or co-operations among several local mappings of model and test image feature correspondences. Our experiments show that the system is very successful in recognising object to perspective distortion, even in rather cluttered scenes. Receiveed: 29 May 1998?,Received in revised form: 12 October 1998?Accepted: 26 October 1998     

Model-based recognition of 3D objects from single images

In this work, we treat major problems of object recognition which have received relatively little attention lately. Among them are the loss of depth information in the projection from a 3D object to a single 2D image, and the complexity of finding feature correspondences between images. We use geometric invariants to reduce the complexity of these problems. There are no geometric invariants of a projection from 3D to 2D. However, given certain modeling assumptions about the 3D object, such invariants can be found. The modeling assumptions can be either a particular model or a generic assumption about a class of models. Here, we use such assumptions for single-view recognition. We find algebraic relations between the invariants of a 3D model and those of its 2D image under general projective projection. These relations can be described geometrically as invariant models in a 3D invariant space, illuminated by invariant “light rays,” and projected onto an invariant version of the given image. We apply the method to real images