基于自适应支持加权准则的建筑物图像匹配扩散研究

室外建筑物图像由于建筑本身纹理单一且重复、图像间的基线较宽等特点,应用传统的匹配算法在进行图像匹配时会出现正确的匹配特征点少,匹配扩散后得到的准稠密和稠密匹配特征点的匹配多义性问题,同时,误匹配也影响了建筑物的三维重建效果。针对上述问题,研究并改进了适用于建筑物图像的匹配扩散算法。应用自适应支持加权匹配度量准则减少误匹配,同时扩散过程中应用仿射传递来获取新匹配的最佳邻域窗口。实验表明,改进的算法对于建筑物图像能获得数量较多、较正确的准稠密匹配扩散结果。     

基于尺度不变Harris特征的准稠密匹配算法

准稠密匹配是多视图三维重建的重要技术,其性能对重建结果至关重要。针对常用的Sift算法提取的种子点进行准稠密匹配正确率较低、重建效果不佳的问题,提出了一种基于尺度不变Harris角点特征的准稠密匹配算法。该算法首先在图像多尺度空间构造尺度不变Harris特征,并采用余弦距离测度对不同视图进行双向匹配;然后根据稀疏匹配获取种子点,采用最优最先匹配扩散策略进行准稠密扩散;最后采用局部非极大值抑制策略对匹配结果进行重采样。实验表明,本文算法提取的种子点既能够体现场景结构信息,又具有尺度不变特性,用于准稠密匹配能够提高匹配的效果和精度,是一种有效的用于三维重建的准稠密匹配算法。     

基于准稠密匹配的结构化场景三维重建

传统的准稠密对应点匹配算法大都是针对一般场景开发的,未考虑场景的结构特点.为此,针对结构化场景提出一种基于平面单应约束的准稠密匹配方法.首先采用基于仿射不变量的方法检测和匹配稀疏平面种子区域,然后根据平面间的几何约束和对应点相似性约束,利用区域增长的方法实现准稠密扩散匹配.最优种子区域优先扩散策略的应用大大减小了初始错误种子区域对扩散过程的影响,而对不可靠扩散点的后处理也有效地提高了最终三维重建的精度.实验结果表明,相比传统的准稠密匹配方法,对于结构化场景,采用文中方法更加精确和稳定.     

基于K近邻一致性的特征匹配内点选择算法

宽基线图像特征匹配是计算机视觉应用中一项极具挑战性的工作。由于图像之间存在较大的差异,宽基线图像初始特征匹配的结果中不可避免地包含大量的外点。提出了K近邻一致性算法来实现从宽基线图像初始匹配结果中快速选出高可靠性的点对。该算法采用仿射不变的结构相似度来衡量两组K近邻特征点的结构相似性。K近邻一致性算法采取由粗到精的策略,通过K近邻对应一致性检测和K近邻结构一致性检测两个步骤来选择内点。实验结果表明,提出的算法在查准率、查全率和运行速度等方面接近或优于当前几种最新的内点选择算法,可适用于存在大范围的视点、尺度和旋转变化的宽基线图像。     

基于FPFH特征的三维场景重建

文章在阐述不同视角下在对一对三维点云数据集两两配准的基础之上,针对ICP精确匹配算法须使初始点云收敛否则无法获取准确匹配结果的问题,提出了基于FPFH特征描述子的特征点云粗匹配;调整两片点云的初始位置,为ICP算法提供了良好的初始位置进一步提高点云的匹配精度;并且在此基础上通过大量实验得到点云对应点对之间的最大距离与拟合系数的函数关系,得到粗匹配最优值,进而得到最佳配准效果。实验证明通过粗匹配最高能将匹配拟合系数提高60.3%。     

一种用于三维重建的彩色Sift准稠密匹配算法

针对复杂光照条件下Sift算法对彩色图像匹配能力较差,基于Kubelka-Munk理论,提出了一种适用于未标定图像的准稠密立体匹配算法,有助于更精确地进行三维重建。该算法首先求出彩色图像各个像素的颜色不变量,提取彩色特征点并通过构造彩色Sift特征描述子进行初匹配,采用RANSAC鲁棒算法消除误匹配生成种子点;然后依据视差约束提出一种基于视差梯度均值自适应窗口方法,根据视差梯度均值调整搜索范围;最后采用最优先原则进行区域增长。实验证明,该算法能获得比较满意的匹配效果,是一种有效的用于三维重建的准稠密匹配算法。     

面向重复纹理及非刚性形变的像对高效稠密匹配方法

目的 像对稠密匹配是3维重建和SLAM（simultaneous localization and mapping）等高级图像处理的基础,而摄影基线过宽、重复纹理、非刚性形变和时空效率低下等问题是影响这类方法实用性的主要因素,为了更好地解决这类问题,本文提出一种面向重复纹理及非刚性形变的高效稠密匹配方法。方法 首先,采用DeepMatching算法获得降采样后像对的匹配点集,并采用随机抽样一致算法剔除其中外点。其次,利用上一步得到的匹配结果估计相机位姿及缩放比例,以确定每个点对稠密化过程中的邻域,再对相应点对的邻域提取HOG描述符并进行卷积操作得到分数矩阵。最后,根据归一化后分数矩阵的数值以及下标距离的方差确定新的匹配点对以实现稠密化。结果 在多个公共数据集上采用相同大小且宽高比为4：3的像对进行实验,实验结果表明,本文方法具备一定的抗旋转、尺度变化与形变的能力,能够较好地完成宽基线条件下具有重复纹理及非刚性形变像对的匹配。与DeepMatching算法进行对比实验,本文方法在查准率、空间效率和时间效率上分别提高了近10%、25%和30%。结论 本文提出的稠密匹配方法具有较高的查准率和时空效率,其结果可以运用于3维重建和超分辨率重建等高级图像处理技术中。     

基于匹配扩散的多视稠密深度图估计

提出一种高精度的基于匹配扩散的稠密深度图估计算法. 算法分为像素级与区域级两阶段的匹配扩散过程.前者主要对视图间的稀疏特征点匹配进行扩散以获取相对稠密的初始深度图; 而后者则在多幅初始深度图的基础上, 根据场景分段平滑的假设, 在能量函数最小化框架下利用平面拟合及多方向平面扫描等方法解决存在匹配多义性问题区域(如弱纹理区域)的深度推断问题. 在标准数据集及真实数据集上的实验表明, 本文算法对视图中的光照变化、透视畸变等因素具有较强的适应性, 并能有效地对弱纹理区域的深度信息进行推断, 从而可以获得高精度、稠密的深度图.     

一种快速稳健的图像配准算法

本文对图像配准问题进行了研究,提出了一种快速、稳健的基于特征点匹配的配准算法。采用小波变换建立图像金字塔,从分辨率最低的图像层开始进行特征点匹配,在次一层匹配时以上层匹配结果为粗值,在原始图像上得到初始匹配点后采用RANSAC算法稳健估计变换矩阵H;为了提高配准算法的精度,采用变换矩阵H引导两幅原始图像上的所有特征点重新进行匹配,对得到的匹配点集重新用RANSAC算法估计变换矩阵,并采用LM非线性优化算法进一步优化。通过实验分析对比,本文的算法比原算法速度更快,更稳健。     

光栅投影测量中点云配准技术的研究

针对在光栅投影测量中运用传统标志点法进行点云配准时点云产生孔洞的问题,提出一种无标志点的配准算法。利用光栅投影法所获点云可显示为距离图像,通过对获取的距离图像的局部曲面拟合,提取曲率特征点。根据余弦相似度和距离相似度得到匹配的特征点对,利用最终得到的匹配点对的几何信息计算初始配准参数,结合最近点迭代算法完成点云的配准。实验结果验证了该算法可以避免在物体上粘贴标志点,自动完成点云的准确配准。     

Match propagation for image-based modeling and rendering

This paper presents a quasi-dense matching algorithm between images based on the match propagation principle. The algorithm starts from a set of sparse seed matches, then propagates to the neighboring pixels by the best-first strategy, and produces a quasi-dense disparity map. The quasi-dense matching aims at broad modeling and visualization applications which rely heavily on matching information. Our algorithm is robust to initial sparse match outliers due to the best-first strategy. It is efficient in time and space as it is only output sensitive. It handles half-occluded areas because of the simultaneous enforcement of newly introduced discrete 2D gradient disparity limit and the uniqueness constraint. The properties of the algorithm are discussed and empirically demonstrated. The quality of quasi-dense matching are validated through intensive real examples.     

Registrating large mismatching SAR images based on corners and surface extremum strategy

Robust and accurate registration remains a difficult task for large mismatching Synthetic Aperture Radar (SAR) images because of severe viewpoint distortion, repetitive patterns, and speckle noise. In this paper, we propose a coarse-to-fine registration method with high precision by integrating corners and Surface Extremum Strategy (SES). Our method involves three steps. First, initial corresponding points are obtained based on the complementary invariant feature matching, and then the global and local Homographic Geometry Transformations (HGTs) are estimated between image pairs. Second, we consider quasi-dense corner matches with high accuracy. The reference image is divided into quasi-dense grids from which the Förstner corners are extracted. Subsequently, we produce the coarse corresponding corners by combining the global and local HGTs using Normalized Cross Correlation (NCC), and then employ the SES of the NCC coefficients to compensate the matching deviations. Third, highly precise registration is achieved based on the matches of the second step. Experiments on four groups of large mismatching SAR images verify the effectiveness of our method, and a comprehensive comparison with existing algorithms demonstrates that the proposed method is superior in terms of the number of matches, correctness, accuracy, and spatial distribution.     

A quasi-dense approach to surface reconstruction from uncalibrated images

This paper proposes a quasi-dense approach to 3D surface model acquisition from uncalibrated images. First, correspondence information and geometry are computed based on new quasi-dense point features that are resampled subpixel points from a disparity map. The quasi-dense approach gives more robust and accurate geometry estimations than the standard sparse approach. The robustness is measured as the success rate of full automatic geometry estimation with all involved parameters fixed. The accuracy is measured by a fast gauge-free uncertainty estimation algorithm. The quasi-dense approach also works for more largely separated images than the sparse approach, therefore, it requires fewer images for modeling. More importantly, the quasi-dense approach delivers a high density of reconstructed 3D points on which a surface representation can be reconstructed. This fills the gap of insufficiency of the sparse approach for surface reconstruction, essential for modeling and visualization applications. Second, surface reconstruction methods from the given quasi-dense geometry are also developed. The algorithm optimizes new unified functionals integrating both 3D quasi-dense points and 2D image information, including silhouettes. Combining both 3D data and 2D images is more robust than the existing methods using only 2D information or only 3D data. An efficient bounded regularization method is proposed to implement the surface evolution by level-set methods. Its properties are discussed and proven for some cases. As a whole, a complete automatic and practical system of 3D modeling from raw images captured by hand-held cameras to surface representation is proposed. Extensive experiments demonstrate the superior performance of the quasi-dense approach with respect to the standard sparse approach in robustness, accuracy, and applicability.     

基于灰度差分不变量的点特征匹配

本文提出了一种新的基于灰度差分不变量的点特征匹配方法。首先，利用灰度差分不变量获得点集之间的初始匹配；然后，利用初始匹配快速、稳健地估计图象之间的唯一几何约束－对极几何约束；最后，利用对极几何约束改进初始匹配。大量的实际图象实验表明，本文所提出的匹配算法有非常快的运算速度和很高的匹配正确率。     

迭代的图变换匹配算法

目的：图像的精确匹配在图像处理与识别中起着重要的作用。为了提高图像的匹配效果,本文提出了一种迭代的图变换匹配算法来实现误匹配关系的去除从而提高图像的匹配精度。方法：该算法首先利用传统的图变换匹配(GTM)算法从初始匹配关系集合中获得较为精确的匹配关系子集,然后,利用已经获得的正确匹配点集与初始匹配点集之间的几何关系对初始匹配进行修正。最后,利用GTM对修正后的匹配关系进一步优化,从而得到更多的精确匹配关系。结果：实验结果显示在不同的图像变换场景下,相比于传统GTM算法,该算法具有较高的查全率。结论：所提算法能够克服传统GTM算法所得正确匹配关系少的缺陷。     

Robust multi-view feature matching from multiple unordered views

This paper explores the problem of multi-view feature matching from an unordered set of widely separated views. A set of local invariant features is extracted independently from each view. First we propose a new view-ordering algorithm that organizes all the unordered views into clusters of related (i.e. the same scene) views by efficiently computing the view-similarity values of all view pairs by reasonably selecting part of extracted features to match. Second a robust two-view matching algorithm is developed to find initial matches, then detect the outliers and finally incrementally find more reliable feature matches under the epipolar constraint between two views from dense to sparse based on an assumption that changes of both motion and feature characteristics of one match are consistent with those of neighbors. Third we establish the reliable multi-view matches across related views by reconstructing missing matches in a neighboring triple of views and efficiently determining the states of matches between view pairs. Finally, the reliable multi-view matches thus obtained are used to automatically track all the views by using a self-calibration method. The proposed methods were tested on several sets of real images. Experimental results show that it is efficient and can track a large set of multi-view feature matches across multiple widely separated views.