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Harris和几何哈希法的目标匹配

复杂环境下的目标匹配会受到物体缩放、旋转、遮挡及光强变化等影响,是模式识别领域的一项难题。针对该问题,提出一种基于Harris算法和改进几何哈希法的目标匹配方法。利用Harris角点提取算法检测兴趣点,通过改进的几何哈希法实现多目标匹配。实验结果表明,该方法可实现复杂环境下的目标匹配,提高匹配精度和速度。     

基于直线基元的实时定位与匹配方法

为实现工业过程中对工件的实时定位,提出一种基于直线基元的几何哈希法实时定位与匹配方法。离线学习模板过程,提取图像中的直线基元,选择其中两个直线基元构建基底,量化剩余基元并建立几何哈希表;在线实测图像中,选择一组直线基元构成基底,量化剩余基元,通过坐标在几何哈希表中查询对应的基底并投票,来实现实时定位与匹配。实验证明,该方法对于工件的定位与匹配,实时性好、准确性高。     

一种哈希表快速查找的改进方法

哈希表由于其速度快的优点在数据查询中有着广泛的应用。本文在结合冲突解决机制和数据元素被查找的先验概率的基础上,提出了一种提高哈希表查找效率的优化方法,并对该方法在链地址法处理哈希冲突的情况下进行了理论分析,与原哈希表方法相比,该方法降低了冲突时执行查询的查找长度,从而使查询响应时间更短。最后对该方法进行行了实例验证,实验结果表明,新方法是有效并且简便的。     

动态识别三维几何约束冲突的方法研究

基于装配几何特征的广义几何约束图,避免了传统几何约束图的超图性质和模糊性,为几何约束满足问题提供了一个清晰的分析模型。文中以此模型来分析产生约束冲突的原因。空间分析法定义和推导了约束满足空间约束满足条件,提出了自由空间和自由度的计算方法,并据此在动态满足三维几何约束的过程中识别约束冲突,明确指出产生约束冲突的原因。     

基于局部坐标系和哈希技术的空间曲线匹配算法

针对三维物体识别领域中的问题,提出了一种基于局部坐标系和哈希技术的空间曲线匹配算法,该方法通过提取一条曲线的恒定特征点,构造局部坐标系;然后再计算局部坐标系中的相似不变量,构造哈希表;采哈希技术对这些不变量进行比较,达到匹配曲线的目的。此算法应用于计算机辅助文物复原系统中,经实验表明,给所方法具有运行稳定,高效和适用性强等优点。     

三维几何约束系统的等价性分析

针对过约束、完整约束和欠约束三维几何约束系统的求解问题,提出了等价性分析方法.该方法基于三维几何约束系统的内在等价性,充分挖掘几何领域知识,依据拆解约束闭环、缩减约束闭环和析出约束闭环等原则,采用等价约束替换来处理几何约束闭环问题,优化几何约束图的结构,实现几何约束系统的优化分解.最后用多个实例验证了该方法的正确性和有...     

三维几何约束闭环的动态识别与满足

针对三维几何约束闭环的满足问题,提出了“充分推理＋最小数值”的约束求解策略及其具体的实施方法。自由传播法可在动态求解约束的过程中识别出约束闭环;几何归约法将约束闭环子图归约简化为层次分明的归约树,并进一步明确了闭环的组成和结构;矢量闭环法建立了约束闭环的矢量模型,据此模型可以建立最小规模的方程组来求解约束闭环,方程组的变量具有明确的几何意义,便于初值的确定和多解的处理,并能求解欠约束的闭环。     

基于形态图表示的三维物体识别算法

基于形态图表示的三维物体识别的基本思路是：首先建立待识别物体的模型库，找出模型集中所有模型物体的形态图和特征视图，并提取以它们的拓扑结构信息和几何信息；其次对物体真实图像作轮廓提取和0边界跟踪，得到二维图像的线架图，同时提取出它的拓扑结构信息和几何信息；最后将物体图像的拓扑结构信息和几何信息与模型库中模型物体的拓扑结构信息和几何信息匹配，从而达到识别的目的。文中提出了在生成线图链码时提取其拓扑结构信息和几何信息的方法，由拓扑结构信息和几何信息构造特征矩阵的方法，以及识别过程中特征矩阵的匹配算法。     

基于立体成像几何特性的动态有限搜索匹配法

提出了一种基于立体成像几何特性的动态有限搜索匹配法。该法根据被测物体与摄像机标定参照物在空间上的相互关系及被测物体形态，确定被测物体特征点视差匹配大致范围。利用立体成像几何特性，采用动态有限搜索法，以求出的视差为参考，根据左(右)图像中特征点与所得匹配对应点的水平视差值，确定在右(左)图像中的搜索方向和搜索范围，采用灰度区域相关计算，确定下一个匹配特征点，并依此类推。由于特征点灰度不稳定，且随视点的不同而有很大差异，为能得到正确匹配，需结合几何相似性约束。通过对一已知三维坐标标准件的计算机仿真实验，证实了该方法的有效性。     

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.     

几何不变性及其在3D物体识别中的应用

三维物体识别是计算机视觉研究的重要内容之一，它要求从3D物体的2D图象中识别和定位物体．由于物体成像时会受到观察视角、摄像机参数的影响，因此使得同一物体在不同观察视角、不同摄像机参数等条件下所得到的图象存在差异．但由于几何不变性方法可以有效地消除这种差异带给3D物体识别的不利影响，所以，近20年来这种方法受到了广泛的关注和研究．为使人们了解该领域的研究现状，以对该领域的研究有所启发，首先讨论了基于几何不变性的3D物体识别方法的研究内容，包括研究的几何框架和其不变性以及几何不变性在3D物体识别中的主要应用；其次，总结性地评述了该领域的研究现状；最后，提出了研究的发展方向．     

Local association based recognition of two-dimensional objects

A model based two-dimensional object recognition system capable of performing under occlusion and geometric transformation is described in this paper. The system is based on the concept of associative search using overlapping local features. During the training phase, the local features are hashed to set up the associations between the features and models. In the recognition phase, the same hashing procedure is used to retrieve associations that participate in a voting process to determine the identity of the shape. Two associative retrieval techniques for discrete and continuous features, respectively, are described in the paper. The performance of the system is studied using a test set of 1,000 shapes that are corrupted versions of 100 models in the shape database. It is shown that the incorporation of a verification phase to confirm the retrieved associations can provide zero error performance with a small reject rate.     

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     

基于几何配准的三维模型几何比对方法研究

针对设计师在进行协同建模时无法快速查看模型变更信息的问题,提出了快速比 对两个模型几何差异的方法。首先,通过等步长采点获取两个模型的点云数据;然后,利用主 元分析法计算两个点云的特征向量从而获取点云的参考坐标系,推导两个点云参考坐标系的坐 标变换,将两个点云调整到一致,即可实现点云的初始配准;最后,利用最近点迭代法对两个 点云进行精确配准,记录配准后两个点云中的非重叠区域,可获取两个点云的几何差异区域。 测试结果表明该方法可以有效识别两个模型的几何差异。     

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.     

基于特征点匹配和哈希法的图像检索方法

提出一种基于点特征匹配和几何型哈希法的图像检索方法。利用小波变换提取图像的突变点，以点为辜心划定一小块区域，将图像划分成图像块。提取块的低层次特征矢量，将两幅图像之间的匹配转换成图像块之间的匹配。并采用几何型哈希索引方法实现图像的快速检索。实验证明，这种方法能够取得较高的检索精度，且对图像形变以及局部遮挡等都有较好的适应能力。     

Robust 3D mesh model hashing based on feature object

3D model hashing can be very useful for the authentication, indexing, copy detection, and watermarking of 3D content, in a manner similar to image hashing. 3D models can be easily modified by graphics editing while preserving the geometric shape, and the modeling representations are not regular, unlike an image with a fixed pixel array. A 3D model must be authenticated, indexed, or watermarked while being robust against graphics attacks and irregular representations. For these purposes, this paper presents a 3D mesh model hashing based on object feature vectors with the robustness, security, and uniqueness. The proposed hashing groups the distances from feature objects with the highest surface area in a 3D model that consists of a number of objects, permutes indices of groups in feature objects, and generates a binary hash through the binarization of feature values that are calculated by two combinations of group values and a random key. The robustness of a hash can be improved by group coefficients that are obtained from the distribution of vertex distances in feature objects, and the security and uniqueness can be improved by both the permutation of groups, feature vectors, and random key. Experimental results verified that the proposed hashing is robust against various perceptual geometrical and topological attacks and has the security and uniqueness of a hash.