利用Voronoi协方差矩阵重建隐式曲面

目的 针对含少量离群点的噪声点云,提出了一种Voronoi协方差矩阵的曲面重建方法。方法 以隐函数梯度在Voronoi协方差矩阵形成的张量场内的投影最大化为目标,构建隐函数微分方程,采用离散外微分形式求解连续微分方程,从而将曲面重建问题转化为广义特征值求解问题。在点云空间离散化过程中,附加最短边约束条件,避免了局部空间过度剖分。并引入概率测度理论定义曲面窄带,提高了算法抵抗离群点能力,通过精细剖分曲面窄带,提高了曲面重建精度。结果 实验结果表明,该算法可以抵抗噪声点和离群点的影响,可以生成不同分辨率的曲面。通过调整拟合参数,可以区分曲面的不同部分。结论 提出了一种新的隐式曲面重建方法,无需点云法向、稳健性较强,生成的三角面纵横比好。     

基于法向量距离的路面坑槽提取方法

以路面高程激光点云为研究对象,提出一种基于法向量距离的路面坑槽提取方法.首先对路面高程点云数据进行数据清洗;其次采用自适应最优邻域的PCA方法估算路面点云数据的法向量,通过计算路面点云中采样点到其局部二次曲面的切平面的法向距离作为法向量距离;以法向量距离描述采样点的三维空间特征,并通过阈值分割自动提取路面坑槽点云集合,...     

Establishing a balanced neighborhood of discrete points for local quadric surface fitting

This paper presents a novel algorithm to establish a balanced neighborhood of points for reliable local quadric surface fitting, a common task in point cloud data processing. The underlying smooth surface geometry of a point cloud in the vicinity of a point can be locally approximated by the best fitted quadric surface at the point. The quality of the fitted surface considerably depends on what neighboring points are selected for the fitting. Specifically, if the selected neighboring points carry a biased distribution, the fitted geometry becomes biased, resulting in loss of accuracy in the fitting. The presented algorithm in this paper is able to reliably select neighboring points considering measures of both distance and direction. The main feature is the development of a geometric relationship, named as Territory Claiming, between the selected and the candidate neighboring points. The fundamental principle is for the selected point set to cover the whole neighborhood domain without redundancy. The selection procedure starts with a distance-based sequence of neighboring points with the territory claiming relationship functioning as a filter to establish a well-balanced neighborhood. The neighborhood can be expanded to incorporate sufficient number of points for the quadric surface fitting while maintaining the balance of the overall neighborhood. The implementation results have demonstrated that the presented method is robust and selects local neighboring points with superior fitting performance in comparison with the distance-based neighbors, mesh neighbors, and elliptic Gabriel graph neighbors.     

基于模糊极大似然估计聚类的点云数据分块

对散乱点云数据采用微切平面法进行法矢估计,对法矢方向进行全局协调性调整。采用稳定性较好的二次曲面拟合法估算点云数据的高斯曲率和平均曲率。将点的坐标、法矢和曲率合并为八维特征向量,通过模糊极大似然估计聚类技术,将具有类似几何特征的向量聚为一类,从而实现点云数据的分块。实验证明该方法有效。     

智能配镜三维特征参数提取方法研究

摘 要：针对智能配镜中三维面部特征点提取算法复杂度较高的问题,提出一种将三维点 云转换为映射图像定位特征点的方法。采用 Voronoi 方法计算面部三角网格各顶点处的高斯曲 率、平均曲率。选取鼻尖、眼角等曲率特征明显的区域估计面部点云姿态。根据曲率旋转不变 性,使用初选的点云方向向量简化旋转矩阵的计算,使面部点云正面朝向视点。将点云映射转 换为图像,三维网格模型中三角面片一对一映射到图像中的三角形。搭建卷积神经网络,使用 Texas 3DFRD 数据集进行模型训练。进行人脸对齐,预测所得各面部特征点分别限制在图像某 三角形中。根据图像中三角形映射查找三维网格模型中对应三角面片,通过三角面片顶点坐标 计算配镜所需的面部特征点位置坐标,实现配镜特征参数的提取。     

Facial feature localization using weighted vector concentration approach

We propose an efficient and generic facial feature localization method based on a weighted vector concentration approach. Our method does not require any specific priors on facial shape but implicitly learns its structural information from a training data. Unlike previous work, facial feature points are globally estimated by the concentration of directional vectors from sampling points on a face region, and those vectors are weighted by using local likelihood patterns which discriminate the appropriate position of the feature points. The directional vectors and local likelihood patterns are provided through nearest neighbor search between local patterns around the sampling points and a trained codebook of extended templates. The combination of the global vector concentration and the verification with the local likelihood patterns achieves robust facial feature point detection. We demonstrate that our method outperforms state-of-the-art method based on the Active Shape Models in our evaluation.     

规则特征曲面点云法向估计

目的 针对特征曲面点云法矢估计不准确,点云处理时容易丢失曲面的细节特征等问题,提出基于高斯映射的特征曲面散乱点云法向估计法。方法 首先,用主成分分析法粗略地估算点云法向和特征点;其次,将特征点的各向同性邻域映射到高斯球,用K均值聚类法对高斯球上的数据分割成多个子集,以最优子集对应的各向异性邻域拟合曲面来精确估算特征点的法向量;最后,通过测试估计法向与标准法向的误差来评价估计法矢的准确性,并且将估计的法向应用到点云曲面重建中来比较特征保留效果。结果 本文方法估计的法向最小误差接近0,对噪声有较好的鲁棒性,重建的曲面能保留曲面的尖锐特征,相比于其他法向估计法,所提出的方法估计的法向更准确。结论 本文方法能够比较准确的估算尖锐特征曲面法向量,对噪声鲁棒性强,具有较高的适用性。     

基于三角网格构建的扫描测头半径三维补偿

采用扩展的自组织特征映射神经网络探讨了三坐标测量机接触式密集数据采集的测头半径三维补偿。构建了基于三角形网格构建的测头半径三维补偿模型。经过训练,神经网络将整个数字化点群数据分成许多子区域,每个子区域用一个微切平面逼近;对子区域的分类核心,即神经元位置权重,沿微切平面法矢方向进行修正,得到逼近测头球心面的三角形网格II;根据微切平面的法线,对测头半径进行三维补偿,得到逼近接触曲面的三角形网格III。测头半径三维补偿的法矢方向,也可通过估算三角网格II顶点的法矢得到。算例表明所创建的测头半径三维补偿模型有效可行。     

点云模型适应性上采样算法

针对点云模型采样密度的不足,提出一种新的适应性上采样算法。算法首先采用均匀栅格法建立点云模型的拓扑关系,提高数据点K-邻域的查找效率,利用协方差矩阵求取点云模型中数据点的法向量,并用法向传播算法进行法向重定向,然后检测点云模型中采样点密度不足的区域,在采样密度不足区域的点的切向矩形平面内适应性均匀采样,并把这些采样点几乎垂直投影到点云模型所在的原始曲面上,由此得到的模型即为上采样模型。该算法得到的上采样模型可以较好地补充点云模型的细节信息,能够满足点云模型的绘制和后续几何处理的需求。     

Estimating differential quantities from point cloud based on a linear fitting of normal vectors

Estimation of differential geometric properties on a discrete surface is a fundamental work in computer graphics and computer vision. In this paper, we present an accurate and robust method for estimating differential quantities from unorganized point cloud. The principal curvatures and principal directions at each point are computed with the help of partial derivatives of the unit normal vector at that point, where the normal derivatives are estimated by fitting a linear function to each component of the normal vectors in a neighborhood. This method takes into account the normal information of all neighboring points and computes curvatures directly from the variation of unit normal vectors, which improves the accuracy and robustness of curvature estimation on irregular sampled noisy data. The main advantage of our approach is that the estimation of curvatures at a point does not rely on the accuracy of the normal vector at that point, and the normal vectors can be refined in the process of curvature estimation. Compared with the state of the art methods for estimating curvatures and Darboux frames on both synthetic and real point clouds, the approach is shown to be more accurate and robust for noisy and unorganized point cloud data. Supported in part by the National Natural Science Foundation of China (Grant Nos. 60672148, 60872120), the National High-Tech Research & Development Program of China (Grant Nos. 2006AA01Z301, 2008AA01Z301), and Beijing Municipal Natural Science Foundation (Grant No. 4062033)     

激光三维扫描数据的表面重建

对激光三维扫描系统获得的没有任何附加信息的轮廓线点云数据进行处理,首先采用求最大连通域的方法删除噪声点,利用设定相邻点连线夹角正切阈值的方法精简数据,然后采用基于局部切平面簇的方法对数据点云进行切平面的估算、法向量的调整和计算距离函数,用改进的MC方法输出三维网格,并且应用基于顶点的网格删除算法对三维网格进行简化,在估算切平面的时候采用新的估算原则,提高了重建速度,改善了重建效果,所表述的重建流程,成功地解决了激光扫描系统所得轮廓数据点的表面重建问题。     

结合超体素和区域增长的植物器官点云分割

点云分割是点云识别与建模的基础。为提高点云分割准确率和效率，提出一种结合超体素和区域增长的自适应分割算法。根据三维点云的空间位置和法向量信息，利用八叉树对点云进行初始分割得到超体素。选取超体素的中心体素组成一个新的重采样后的密度均匀点云，降低原始点云数据处理量，从而减少运算时间。建立重采样后点云数据的K-D树索引，根据其局部特征得到点云簇。最后将聚类结果返回到原始点云空间。分别选取植物三个物候期的激光扫描点云，对该方法的有效性进行验证。实验结果表明，该方法分割后点云与手工分割平均拟合度达到93.38%，高于其他同类方法，且算法效率得到明显提升。     

Smoothing Normal Vectors on Discrete Surfaces While Preserving Slope Discontinuities

A new method is proposed which smoothes normal vectors over a discrete surface, preserving slope discontinuities and small details. Assume an estimate of the normal vector at each surface point is known and these estimates are computed from small neighbourhoods such that slope discontinuities and small details are still reflected by these normals. To smooth these normals, the normal vectors at points in a certain neighbourhood are averaged. The size of the neighbourhood considered for the smoothing at a point is adapted according the local surface configuration. The adaptation is performed, depending on the tangent plane at the point considered as well as the angles between the normals at neighbouring points and the normal at the point in question.     

分区加权Voronoi图的性质及其面积计算

分区加权Voronoi图是Voronoi图和加权Voronoi图的推广,可以用来模拟移动通信中基站发射天线分扇区以不同功率向周围发射时所覆盖区域的形状。首先,给出了分区加权Voronoi图的性质、定理及相关证明;其次,分析了分区加权Voronoi图中的各种区域,并给出了一种计算相应区域面积的算法;最后,利用分区加权Voronoi图模拟石家庄市部分城区中的基站建设情况,并对模拟产生的重复覆盖、服务区和盲区面积进行了计算。     

Point Cloud Denoising via Moving RPCA

We present an algorithm for the restoration of noisy point cloud data, termed Moving Robust Principal Components Analysis (MRPCA). We model the point cloud as a collection of overlapping two‐dimensional subspaces, and propose a model that encourages collaboration between overlapping neighbourhoods. Similar to state‐of‐the‐art sparse modelling‐based image denoising, the estimated point positions are computed by local averaging. In addition, the proposed approach models grossly corrupted observations explicitly, does not require oriented normals, and takes into account both local and global structure. Sharp features are preserved via a weighted ?₁ minimization, where the weights measure the similarity between normal vectors in a local neighbourhood. The proposed algorithm is compared against existing point cloud denoising methods, obtaining competitive results.     

面向点云三维重建的空间感知对抗神经网络

为了解决由原始点云数据局部密度稀疏、不均匀或者法向量错误等制约因素引起的重建网格质量问题,利用对抗神经网络中权重共享的特性和对抗的训练过程,提出一种基于对抗网络的点云三维重建方法。首先,利用预测器对网格模型边的偏移量进行预测,从而得到每一个顶点的位移,并进行拓扑保持的顶点重定向,得到新的网格模型。然后,利用判别器中的点云分类器,提取原始点云数据和网格模型表面采样点集的高维特征,并基于高维特征进行空间感知的判别,用于区分原始点云与采样点集数据。最后,使用对抗的训练方式将预测器与判别器的输出数据关联起来,通过多次迭代优化网络模型,从而得到满足点云空间特征的三维网格模型。在不同的点云数据集上进行实验,并使用MeshLab软件进行效果展示,结果表明,该方法能够重建出满足点云空间信息的三维网格模型,同时能够解决粗劣的点云数据引起的网格质量问题。     

Hadoop下面元加权Voronoi图并行算法及应用

面元加权Voronoi图是生成元为面元的加权Voronoi图。针对大规模数据情况下面元加权Voronoi图存在的计算效率不高问题,结合面元边界点提取方法,提出一种基于Hadoop云平台的面元加权Voronoi图的并行生成算法,进行了单机和集群实验。实验结果表明,算法能有效处理大规模栅格数据,明显提高面元加权Voronoi图的生成速度。还可应用于城市绿地设计规划,为绿地设计提供决策依据。     

牙颌点云数据的显著性特征提取

随着激光扫描测量技术的发展,其数据测量精度的逐渐增高使得获取的几何模型表面点云数据的细节信息越丰富,能更准确的反应物体几何表面特征,但如此海量的点云数据同时也带来对应的技术挑战,海量的点云数据在计算机文件存储、数据后期进一步处理以及软件可视化方面都不方便且效率低下.本文中的算法首先采用栅格法对点云进行空间划分及领域关系的建立,其次利用局部表面拟合的方法估算点云法向量,然后利用点云K领域法的向量求解坐标点的显著性值,最后根据显著性的值构建点云八叉树.该算法实现了对点云显著性特征的提取和对点云数据量的进一步简化,它不仅保留了对点云细节特征保持方面的优势,而且在时间效率上得到了提高.     

基于无人机的道路点云数据分割提取算法

针对机载LiDAR获得道路的数据信息精确度低问题,提出基于无人机的低空扫描三维点云数据,动态拟合提取分割道路信息的算法.首先使用主成分分析法获得道路点数据的法向量,之后将高程信息和法向量信息结合,利用聚类算法获得道路的高程和法向量的范围,提取道路点云数据;其次利用多项式拟合对道路数据进行数学建模;然后通过动态多项式拟合提取出所有路面数据和路面上的资产以及行人车辆数据;最后使用区域生长算法对路面上的资产以及行人车辆数据进行分割.实验表明算法对道路上的遮挡物有很强的抗干扰能力,可以将路面提取出来并将路面上的数据分割进行分割,将本文算法与区域生长算法进行对比,本文算法对路面数据更加敏感.