一种基于多视立体视觉的多视图直线匹配方法

提出了一种基于多视立体视觉（Multiple view stereo，MVS）进行多视图直线匹配的方法. 本文方法首先利用MVS所得到的三维点云及其可见性信息，建立三维点与图像直线的对应关系. 根据此对应关系，为每条图像直线建立由一个三维点集和一个三维单位向量构成的描述子，用以衡量图像直线之间的相似性及一致性. 之后，本文方法以所有图像直线为顶点建立一个图，并引入了图谱分析来获取统一的顶点距离度量. 最后，本方法对DBSCAN聚类算法进行了修改，并用修改后的算法从图谱分析结果中获取可靠的直线匹配. 实验显示，本方法比已有方法更加鲁棒，并且有更高的准确率.     

Hough变换在表面污渍检测中的应用

针对具体芯片图像的形状特征,提出了基于改进Hough变换的几何配准算法.该算法利用边缘点的梯度方向信息,以及通过圆上任意一点并沿着该点法线方向的直线必定经过该圆的圆心这一几何性质,将三维Hough变换空间简化为二维空间,较好地解决了传统广义Hough变换运算时间长、存储空间大的问题.实验表明,可以有效地对两幅图像进行配准,从而检测出芯片表面的污渍.     

基于Hough变换的平行直线检测改进算法研究

根据经典Hough变换检测空间直线的原理,提出了一种基于Hough变换的平行直线检测改进算法,将采集到的图像进行二值化处理,再使用Sobel算子对该二值化图像进行边缘检测,对边缘检测得到的图像进行Hough变换和峰值点检测,由峰值点得到直线段图像,最后使用本文提出的改进算法计算出所有直线段的斜率,利用斜率相等来判定平行直线.通过对比实验证明,该算法能得到更高的精度,并缩短了运行时间.     

信号博弈的三维重建形变识别算法

现有双目立体视觉算法常常需要双目相机位置固定,在现实应用中,这类算法难以重构空间三维几何关系.为此,本文提出了一种不受位置限制的多视角图像三维重建与形变检测算法.该算法首先采用sift算法获取成对图像的特征点,以获取形变前后比对点对图像的特征信息;其次,利用信号博弈方法确定图像拍摄时相机的空间位置与视角,以准确获取图像的空间位置坐标;再次,依据上述信息完成物体的三维点云重建;进而,利用三维数据信息比对实现物体形变识别.最后,本文利用真实物体的实验,验证了三维重建形变识别算法的有效性.     

一种稳健的直线提取和匹配算法

在空间机器人遥操作中,需要快速的求解图像的摄像机参数来对操作对象进行三维建模.通过利用匹配直线的对应关系,可以直接求出图像的摄像机参数,而且比用角点匹配求得的结果具有更高的可靠性.现有的直线提取和匹配算法虽然已经有很多,但是大部分都比较耗时,不能满足实时性的要求.针对空间机器人遥操作等实时性较强的应用,提出了一种基于直线支持区域的稳健、快速的直线提取和匹配算法.实验结果表明了该算法的有效性.     

基于单幅全向图像的空间水平直线定位新方法

研究了在没有先验知识的前提下,基于单幅全向图像定位空间水平直线的问题.在已有算法的基础上,分析和推导了空间水平直线在全向成像系统中的成像特点,指出基于直线在全向图中的两个像点即可重建该水平直线,并相应地提出了一种基于"主像点/非主像点"的空间水平直线定位算法.试验表明,在不同的像点提取精度下,对于不同空间水平直线,本方法均能取得较好结果.     

基于空间上下文加权词汇树的图像检索方法

基于词汇树的词袋模型(Bag-of-Words)表示算法是目前图像检索领域中的主流算法.针对传统词汇树方法中空间上下文信息缺失的问题,提出一种基于空间上下文加权词汇树的图像检索方法.该方法在词汇树框架下,首先生成SIFT点的空间上下文信息描述.然后利用SIFT点间的空间上下文相似度对SIFT间的匹配得分进行加权,得到图像间的相似度.最后,通过相似度排序完成图像检索.实验结果表明,该方法能够大幅度提高图像检索的性能,同时,对大规模图像库有较好的适用性.     

基于消失点和主方向估计的道路分割算法

现有基于消失点估计的道路分割算法要求消失点位于图像内部,并且算法计算复杂度高,难以排除局部纹理特征较强的干扰点.针对这些问题,提出一种基于道路主方向的消失点估计和道路分割算法.首先根据道路主方向的定义对有效投票点进行筛选,然后提出一种多维投票策略,记录待定消失点在各纹理方向的投票信息,并运用该信息判断消失点是否在图像内;最后提出基于道路主方向的边界拟合策略,利用多维投票数据来进行道路边界提取.主观评价和量化分析表明,与经典算法相比,所提算法具有更好的精确度和执行速度,并且当消失点位于图像外部时算法仍有较好的分割效果.     

基于夹角的直线检测算法

为了能有效解决Hough变换计算量大、处理速度慢等问题,提出了一种基于夹角的直线提取算法.该算法直接在图像空间提取直线,通过判断图像中任意三点形成的直线夹角,获得一条可能的直线,然后再在数据空间中进一步判定这条直线的真实性.实验证明,该算法具有较高的直线检出率、检测精度和运行速度,与具有类似检出率的算法相比虚假直线数较少,综合性能具有优势.     

曼哈顿世界环境下消失点非线性优化估计算法

目的 符合曼哈顿假设的结构化场景简称曼哈顿世界,具有丰富的场景结构特征。消失点作为直线的潜在观测,是一种全局信息,可以显式地体现载体坐标系与世界坐标系之间的姿态关系。为更加准确地估计消失点,本文针对单目图像,同时考虑实时性和准确性,提出了具有更高精度的基于非线性优化的消失点估计算法。方法 分析目前性能最优的基于随机采样一致性（random sample consistency,RANSAC）的消失点估计方法,通过对直线单参数化、利用正交性约束生成候选假设以及RANSAC过程的重点分析与改进,更加快速准确地得到消失点估计,为后续优化提供初值。利用直线分类时计算的误差度量构建最小二乘优化模型,采用非线性优化方法迭代求解,并采用鲁棒核函数保证迭代的精确性和结果的最优性。结果 通过仿真实验和基于公共数据集的实验对本文提出算法与目前性能最优算法进行比较。仿真实验中,相比于RCM（R3_CM1）及RCMI（R3_CM1_Iter）,本文算法结果在轴角形式下的角度偏差减小了24.6%;有先验信息约束时,角度偏差降低一个数量级,仅为0.06°,精度大幅提高。在YUD（York urban city databbase）数据集中,本文算法相较于RCM和RCMI,角度偏差分别减小了27.2%和23.8%,并且80%的消失点估计结果角度偏差小于1.5°,性能明显提升且更具稳定性。此外,本文算法在仿真实验对每一图像帧的平均优化耗时为0.008 s,可保证整体的实时性。结论 本文提出的消失点估计算法,对基于RANSAC的方法进行了改进,在不影响实时性的基础上,估计结果更加准确、鲁棒,并且更具稳定性。     

基于 2 个灭点和局部尺度的三维空间尺度估计

三维空间尺度估计是三维重建中的一个重要工作,现实世界中也存在一些基于单幅图像进行三维空间尺度估计的需求。通常情况下,尺度估计需先对相机进行标定。根据单目图像符合透视原理的特性,提出了一种基于 2 个灭点和局部尺度信息的方法对相机进行标定,从而得到单目图像物体中三维空间尺度信息的估计。首先,从单目图像中选择 2 组互相正交的平行线组,得到对应 2 个灭点的坐标;然后,利用灭点坐标和焦距信息得到世界坐标系和相机坐标系之间的旋转矩阵,再利用灭点的性质和已知局部尺度信息得到平移向量,完成单目相机的标定;最后,还原二维图像中像素点对应的三维世界坐标值,计算出图像中 2 个像素点在三维空间的尺度信息。实验结果表明,该方法能有效地对单幅图像中的建筑物体进行尺度估计。     

Projection matrix by orthogonal vanishing points

Calculation of camera projection matrix, also called camera calibration, is an essential task in many computer vision and 3D data processing applications. Calculation of projection matrix using vanishing points and vanishing lines is well suited in the literature; where the intersection of parallel lines (in 3D Euclidean space) when projected on the camera image plane (by a perspective transformation) is called vanishing point and the intersection of two vanishing points (in the image plane) is called vanishing line. The aim of this paper is to propose a new formulation for easily computing the projection matrix based on three orthogonal vanishing points. It can also be used to calculate the intrinsic and extrinsic camera parameters. The proposed method reaches to a closed-form solution by considering only two feasible constraints of zero-skewness in the internal camera matrix and having two corresponding points between the world and the image. A nonlinear optimization procedure is proposed to enhance the computed camera parameters, especially when the measurement error of input parameters or the skew factor are not negligible. The proposed method has been run on real and synthetic data for more precise evaluations. The provided experimental results demonstrate the superiority of the proposed method.     

一种快速的人工场景图像消失点检测方法

人工场景中包含了大量的空间平行线以及垂直边,这些空间平行线映射到图像中相交产生的交点即消失点。消失点检测对摄像机标定、三维场景重建等都有着重要的意义。传统的消失点检测算法往往基于二维霍夫参数空间,复杂度高、效率低。因此,提出一种新的方法,先检测图像中较长的边界线,并将检测到的线段进行筛选、分组;然后利用消失点与焦距之间的制约关系,确定三向消失点的位置以及焦距的大小。该方法将传统的二维霍夫参数空间转换为二级一维霍夫参数空间。实验表明,这种方法运算复杂度低、运行时间短。在室外场景图像中,鲁棒性好,且保持较高的准确率。     

高速公路云台相机的自动标定

目的 云台相机因监控视野广、灵活度高,在高速公路监控系统中发挥出重要的作用,但因云台相机焦距与角度不定时地随监控需求变化,对利用云台相机的图像信息获取真实世界准确的物理信息造成一定困难,因此进行云台相机非现场自动标定方法的研究对高速公路监控系统的应用具有重要价值。方法 本文提出了一种基于消失点约束与车道线模型约束的云台相机自动标定方法,以建立高速公路监控系统的图像信息与真实世界物理信息之间准确描述关系。首先,利用车辆目标运动轨迹的级联霍夫变换投票实现纵向消失点的准确估计,其次以车道线模型物理度量为约束,并采用枚举策略获取横向消失点的准确估计,最终在已知相机高度的条件下实现高速公路云台相机标定参数的准确计算。结果 将本文方法在不同的场景下进行实验,得到在不同的距离下的平均误差分别为4.63%、4.74%、4.81%、4.65%,均小于5%。结论 对多组高速公路监控场景的测试实验结果表明,本文提出的云台相机自动标定方法对高速公路监控场景的物理测量误差能够满足应用需求,与参考方法相比较而言具有较大的优势和一定的应用价值,得到的相机内外参数可用于计算车辆速度与空间位置等。     

Geo-registration of wide-baseline panoramic image sequences using a digital map reference

This paper describes a method of geo-registering a sequence of panoramic images to a digital map by matching pixel information from the images with information on the building footprint contained in a digital map. Recently, images captured at the ground level using a Mobile Mapping System (MMS), such as the panoramic images displayed by Google Street View, have been considered as a valuable resource for three-dimensional (3D) building modeling. However, the wide intervals between these panoramic images, as well as locational and directional error from the related sensors, make it difficult to analyze the image data. This paper demonstrates a formulation method for connecting pixels in panoramic images with information on footprint vertices and building lines contained in a digital map. To allow both pixel and footprint information consistent in 3D space, each panoramic image is tilt-corrected in pre-processing to upright the image using the estimated pitch and roll of a vehicle and removing the pitch and roll effects from the panoramic image pixels. Through the proposed formulation, a single panoramic image can be easily geo-registered with simple user-provided constraints, and adjacent sequential images can then be automatically geo-registered using point feature matching. Experimental results showed a significant reduction in the locational and directional error of sequential panoramic images, and the proposed vanishing point (VP) based validation process was found to successfully detect failure cases.     

Hypercatadioptric line images for 3D orientation and image rectification

In central catadioptric systems 3D lines are projected into conics. In this paper we present a new approach to extract conics in the raw catadioptric image, which correspond to projected straight lines in the scene. Using the internal calibration and two image points we are able to compute analytically these conics which we name hypercatadioptric line images. We obtain the error propagation from the image points to the 3D line projection in function of the calibration parameters. We also perform an exhaustive analysis on the elements that can affect the conic extraction accuracy. Besides that, we exploit the presence of parallel lines in man-made environments to compute the dominant vanishing points (VPs) in the omnidirectional image. In order to obtain the intersection of two of these conics we analyze the self-polar triangle common to this pair. With the information contained in the vanishing points we are able to obtain the 3D orientation of the catadioptric system. This method can be used either in a vertical stabilization system required by autonomous navigation or to rectify images required in applications where the vertical orientation of the catadioptric system is assumed. We use synthetic and real images to test the proposed method. We evaluate the 3D orientation accuracy with a ground truth given by a goniometer and with an inertial measurement unit (IMU). We also test our approach performing vertical and full rectifications in sequences of real images.     

A multi-touch platform based on four corner cameras and methods for accurately locating contact points

This paper presents a low-cost and scalable multi-touch platform which uses four cameras to reduce occlusion. Three methods are provided for locating contact points on this platform, including the lookup table, vanishing point, and 3D reconstruction. With each of these methods, respectively, the contact point is located using the projection center and the reference point, the projection center and the vanishing point, and the back-projected rays of epipolar geometry. If the four directing lines of a contact point intersect, the contact point is considered to be real; if the lines do not intersect, the point is rejected. Experimental results indicate that all three methods are capable of locating contact points even under conditions of occlusion. The lookup table and vanishing point methods are, respectively, best suited to small and large platforms, while the accuracy of 3D reconstruction method has been found to be sensitive to the physical setup. The approach proposed here can be directly installed on existing display platforms and thus should be of practical applicability in the near future.     

A study on the dual vanishing point property

Vanishing points and vanishing lines are useful information in computer vision. In this study, an interesting dual property of vanishing point is first introduced. Next, we point out that there also exists a dual property of vanishing line. With the dual vanishing point and vanishing line properties, some 3D intersection inference can be made based on their image lines. Two applications are given to illustrate the usage of the new results. The first one is to derive the 3D pose determination of a circle using two parallel image lines. The second one uses six specially designed 3D lines to adjust the cameras with respect to a fixture in a binocular vision system such that the resultant camera coordinate axes become parallel.     

Interactive 3D reconstruction from multiple images: A primitive-based approach

This paper proposes a fast and stable image-based modeling method which generates 3D models with high-quality face textures in a semi-automatic way. The modeler guides untrained users to quickly obtain 3D model data via several steps of simple user interface operations using predefined 3D primitives. The proposed method contains an iterative non-linear error minimization technique in the model estimation step with an error function based on finite line segments instead of infinite lines. The error corresponds to the difference between the observed structure and the predicted structure from current model parameters. Experimental results on real images validate the robustness and the accuracy of the algorithm.