Curve skeleton extraction by coupled graph contraction and surface clustering

In this paper, we present a practical algorithm to extract a curve skeleton of a 3D shape. The core of our algorithm comprises coupled processes of graph contraction and surface clustering. Given a 3D shape represented by a triangular mesh, we first construct an initial skeleton graph by directly copying the connectivity and geometry information from the input mesh. Graph contraction and surface clustering are then performed iteratively. The former merges certain graph nodes based on computation of an approximate centroidal Voronoi diagram, seeded by subsampling the graph nodes from the previous iteration. Meanwhile, a coupled surface clustering process serves to regularize the graph contraction. Constraints are used to ensure that extremities of the graph are not shortened undesirably, to ensure that skeleton has the correct topological structure, and that surface clustering leads to an approximately-centered skeleton of the input shape. These properties lead to a stable and reliable skeleton graph construction algorithm.Experiments demonstrate that our skeleton extraction algorithm satisfies various desirable criteria. Firstly, it produces a skeleton homotopic with the input (the genus of both shapes agree) which is both robust (results are stable with respect to noise and remeshing of the input shape) and reliable (every boundary point is visible from at least one curve-skeleton location). It can also handle point cloud data if we first build an initial skeleton graph based on k-nearest neighbors. In addition, a secondary output of our algorithm is a skeleton-to-surface mapping, which can e.g. be used directly for skinning animation.Highlights(1) An algorithm for curve skeleton extraction from 3D shapes based on coupled graph contraction and surface clustering. (2) The algorithm meets various desirable criteria and can be extended to work for incomplete point clouds.     

保特征的点云骨架提取算法

三维模型的骨架提取是计算机图形学中一个重要的研究方向。对于有噪声的点云模型,曲线骨 架提取的难点在于保持正确的拓扑结构以及良好的中心性;对于无噪声的点云模型,曲线骨架提取的难点在于 对模型细节特征的保留。目前主流的点云骨架提取方法往往无法同时解决这 2 个难点。算法在最优传输理论的 基础之上结合聚类的思想,将点云骨架提取的问题转化为一个最优化问题。首先使用最优传输得到原始点云与 采样点云之间的传输计划。然后使用聚类的思想将原始点云进行分割,采样点即成为了簇的中心。接着通过簇 与簇之间的调整与合并减少聚类个数,优化聚类结果。最后通过迭代的方式得到粗糙的骨架并使用插点操作进 行优化。大量实验结果表明,该算法在有噪声与无噪声的三维点云模型上均能提取出质量良好的曲线骨架并保 留模型的特征。     

基于改进自适应k均值聚类的三维点云骨架提取的研究

针对三维点云中心骨架提取问题, 提出一种基于改进的自适应k均值聚类预分割引导的点云骨架提取算法. 首先, 将输入点云体素化, 利用八叉树算法覆盖输入点云并下采样实现点云化简; 其次, 在采样点中自适应选取初始聚类中心对点云进行区域划分, 并颜色标记; 最后, 在区域分割的引导下应用L₁-中值骨架提取算法实现点云骨架的提取. 该算法主要针对L₁-中值算法可重复性差、易丢失细节等缺点进行了改进, 并且对输入点云的质量以及形状的几何或拓扑信息, 都没有严格的先验要求, 可以直接应用到未经任何预处理、含有噪声或离群点的初始扫描点云上. 展示了从多种不规则点云提取的骨架结果, 包括矮小植物、人体动作等. 与传统算法相比, 该算法具有高准确率、强鲁棒性、强学习扩展能力等优点.     

基于曲率法线流的树点云骨架提取方法

针对树木点云拓扑结构复杂、特征细节繁多等问题,提出一种基于点云收缩提取曲线骨架的算法。首先,为了在点云表面直接应用网格收缩算法,对点云进行局部主成分分析和Delaunay三角剖分;其次,针对树木点云拓扑结构复杂和末枝细节繁多等问题,用曲率法线流算子对点云进行收缩,针对树木枝条细长且弯曲幅度平缓等特点,利用改进后的QEM网格简化方法将三角网格折叠成一维曲线骨架;最后,将得到的曲线骨架进行连通和居中处理。该算法直接在点云上进行操作,不需要额外的信息和预处理操作,对噪声和残缺点云有良好的鲁棒性。实验证明,该算法提取的树木点云骨架充分表达了树木在自然环境下的生物性结构和特征,相对于rosa、L1-中轴等经典算法,在树木点云的骨架提取速度上提高3倍以上,枝条重建度提高25%。     

基于等级划分的复杂点云骨架提取算法

对于复杂点云的骨架提取,由于原始点云的遮挡、缺失、分布不均、分支复杂等原因,所提取骨架会产生断裂、拓扑结构错误等问题.针对复杂结构点云的骨架提取,提出了一种基于等级划分的复杂点云骨架提取算法(multilevel divided skeleton extraction,MDSE).使用L1-medial提取初始骨架点,将初始骨架点连接成单分支骨架线,通过对单分支结构的初始骨架线进行等级划分,利用连通分支的平均分叉角确定骨架线断裂位置,由底至项修补断裂骨架线;最后采用Cardinal样条曲线改善骨架形态,形成完整且符合原始点云拓扑结构的骨架线.实验结果表明,该算法能够从复杂点云中提取出较为完整、拓扑结构正确的骨架线.     

Direct quad-dominant meshing of point cloud via global parameterization

In this paper, we present a new algorithm for quad-dominant meshing of unorganized point clouds based on periodic global parameterization. Our meshing method is guided by principal directions so as to preserve the intrinsic geometric properties. We use local Delaunay triangulation to smooth the initial principal directions and adapt the global parameterization to point clouds. By optimizing the fairness measure we can find the two scalar functions whose gradients best align with the guided principal directions. To handle the redundant vertices in the iso-lines due to overlapped triangles, an approach is specially designed to clean the iso-lines. Our approach is fully automatic and applicable to a surface of arbitrary genus. We also show an application of our method in curve skeleton extraction from incomplete point cloud data.     

Skeleton‐Intrinsic Symmetrization of Shapes

Enhancing the self‐symmetry of a shape is of fundamental aesthetic virtue. In this paper, we are interested in recovering the aesthetics of intrinsic reflection symmetries, where an asymmetric shape is symmetrized while keeping its general pose and perceived dynamics. The key challenge to intrinsic symmetrization is that the input shape has only approximate reflection symmetries, possibly far from perfect. The main premise of our work is that curve skeletons provide a concise and effective shape abstraction for analyzing approximate intrinsic symmetries as well as symmetrization. By measuring intrinsic distances over a curve skeleton for symmetry analysis, symmetrizing the skeleton, and then propagating the symmetrization from skeleton to shape, our approach to shape symmetrization is skeleton‐intrinsic. Specifically, given an input shape and an extracted curve skeleton, we introduce the notion of a backbone as the path in the skeleton graph about which a self‐matching of the input shape is optimal. We define an objective function for the reflective self‐matching and develop an algorithm based on genetic programming to solve the global search problem for the backbone. The extracted backbone then guides the symmetrization of the skeleton, which in turn, guides the symmetrization of the whole shape. We show numerous intrinsic symmetrization results of hand drawn sketches and artist‐modeled or reconstructed 3D shapes, as well as several applications of skeleton‐intrinsic symmetrization of shapes.     

SkelTre

Terrestrial laser scanners capture 3D geometry of real world objects as a point cloud. This paper reports on a new algorithm developed for the skeletonization of a laser scanner point cloud. The skeletonization algorithm proposed in this paper consists of three steps: (i) extraction of a graph from an octree organization, (ii) reduction of the graph to a skeleton, and (iii) embedding of the skeleton into the point cloud. For these three steps, only one input parameter is required. The results are validated on laser scanner point clouds representing 2 classes of objects; first on botanic trees as a special application and secondly on popular arbitrary objects. The presented skeleton found its first application in obtaining botanic tree parameters like length and diameter of branches and is presented here in a new, generalized version. Its definition as Reeb Graph, proofs the usefulness of the skeleton for applications like shape analysis. In this paper we show that the resulting skeleton contains the Reeb Graph and investigate the practically relevant parameters: centeredness and topological correctness. The robustness of this skeletonization method against undersampling, varying point density and systematic errors of the point cloud is demonstrated on real data examples.     

基于结构光相机的钢筋骨架整体点云获取算法

为了获取钢筋骨架质量自动检查所需的高精度钢筋骨架整体点云,建立了基于结构光相机的钢筋骨架整体点云获取算法。首先,对结构光相机采集得到的多幅钢筋骨架图像进行三维重建,得到结构光相机的无量纲位姿。其次,根据无量纲位姿获取有量纲位姿。然后,计算这些有量纲位姿间精确的转换矩阵。接着,基于这些有量纲位姿及其两两之间的精确转换矩阵,使用图优化对这些有量纲位姿进行优化,以得到高精度的有量纲位姿。最后,基于高精度的有量纲位姿对齐结构光相机采集的所有点云,获取钢筋骨架整体点云。实验结果表明,该算法获取实际预制钢筋混凝土构件钢筋骨架整体点云的耗时约10 min,且点云的误差约为5 mm。钢筋骨架整体点云获取算法可以快速获取钢筋骨架整体点云,而且所得点云的精度较高,可以满足钢筋骨架质量自动检查的要求。     

PointSkelCNN: Deep Learning-Based 3D Human Skeleton Extraction from Point Clouds

A 3D human skeleton plays important roles in human shape reconstruction and human animation. Remarkable advances have been achieved recently in 3D human skeleton estimation from color and depth images via a powerful deep convolutional neural network. However, applying deep learning frameworks to 3D human skeleton extraction from point clouds remains challenging because of the sparsity of point clouds and the high nonlinearity of human skeleton regression. In this study, we develop a deep learning-based approach for 3D human skeleton extraction from point clouds. We convert 3D human skeleton extraction into offset vector regression and human body segmentation via deep learning-based point cloud contraction. Furthermore, a disambiguation strategy is adopted to improve the robustness of joint points regression. Experiments on the public human pose dataset UBC3V and the human point cloud skeleton dataset 3DHumanSkeleton compiled by the authors show that the proposed approach outperforms the state-of-the-art methods.     

计算机生成中国传统祥云动画

开展用计算机生成具有中国民族特色动画的研究,对弘扬我国传统艺术和提高中国动画片竞争力都有重要意义。祥云图案历史悠久,是最富有中国特色的吉祥图案之一,现有的大部分研究工作主要针对真实感烟云的模拟和绘制,而对生成中国传统风格祥云动画的研究工作还很少。为此提出一个祥云动画生成模型。首先利用椭圆来构造云朵的骨架曲线,沿着曲线上的非均匀分布点排列多个半径不同的基本圆,然后通过对这些基本圆进行求并运算来生成云朵内部区域和轮廓线;通过控制基本圆沿以分布点为圆心的圆周上运动,来生成连续变化的轮廓线和云朵形状;利用轮廓线上的运动点作为起点,沿中心点方向绘制云尾内卷线条。实验结果表明,利用该模型用户可以生成各类具有中国传统风格的祥云动画。     

Cloud detection for high-resolution remote-sensing images of urban areas using colour and edge features based on dual-colour models

ABSTRACT

In this article, the colour and edge features of clouds are proposed based on the analysis of a large number of cloudy high-resolution remote-sensing images of urban area. Using the cloud features, a cloud detection method based on dual-colour space is proposed. First, two candidate cloud regions maps are built based on hue–saturation–intensity model and blue, green, red model, respectively. According to the superposition analysis of the two maps, fine cloud regions map are obtained. After removing the fine cloud regions from the image, the image is linearly stretched to enhance the intensity of thin clouds around the fine cloud regions. In the stretched image, the thin cloud regions map is built with the threshold technique. Finally, the fine cloud regions map and the thin cloud regions map are combined to form the complete cloud regions map. The results of experiments and comparisons indicate that our algorithm has good accuracy and efficiency.     

计算机生成中国传统祥云动画(CIDE2013)

开展用计算机生成具有中国民族特色动画的研究,对弘扬我国传统艺术和提高中国动画片竞争力都有重要意义。祥云图案历史悠久,是最富有中国特色的吉祥图案之一,现有的大部分研究工作主要针对真实感烟云的模拟和绘制,而对生成中国传统风格祥云动画的研究工作还很少。本文提出一个祥云动画生成模型。首先利用椭圆来构造云朵的骨架曲线,沿着曲线上的非均匀分布点排列多个半径不同的基本圆,然后通过对这些基本圆进行求并运算来生成云朵的内部区域和轮廓线;通过控制基本圆沿以分布点为圆心的圆周上运动,来生成连续变化的轮廓线和云朵形状;利用轮廓线上的运动点作为起点,沿中心点方向绘制云尾内卷线条。实验结果表明,利用该模型用户可以生成各类具有中国传统风格的祥云动画。     

融合稀疏点云补全的3D目标检测算法

基于雷达点云的3D目标检测方法有效地解决了RGB图像的2D目标检测易受光照、天气等因素影响的问题.但由于雷达的分辨率以及扫描距离等问题,激光雷达采集到的点云往往是稀疏的,这将会影响3D目标检测精度.针对这个问题,提出一种融合稀疏点云补全的目标检测算法,采用编码、解码机制构建点云补全网络,由输入的部分稀疏点云生成完整的密...     

Research on geometric features and point cloud properties for tree skeleton extraction

To solve skeleton extraction problems in the tree point cloud model, branch geometric features and local properties of point cloud are utilized to optimize tree skeleton extraction. First of all, according to the attribute information estimation and normal vector adjustment of point cloud neighbor domain, branch segmentation is made by estimated values and geometric features. Skeleton nodes are extracted in the branch subset in segmentations. Then, a graph is constructed based on skeleton node set and tree skeleton is reconstructed in this weighted directed graph. Finally, according to the tree growth characteristics, cubic Hermite curves are utilized to optimize the skeleton curve. This method is applied in the point cloud model of three-kind trees and it is compared with the skeleton extraction method based on voxel switch and point cloud contraction. The experiment results show that this method displays strong anti-interference and high-precision characteristics at branch bifurcation and crossed ending parts of fine tree branches. Thus, features of tree branches can be described more perfectly, obtaining the skeleton curve closer to the main axis.     

Meshing genus-1 point clouds using discrete one-forms

We present an algorithm to mesh point clouds sampled from a closed manifold surface of genus 1. The method relies on a doubly periodic global parameterization of the point cloud to the plane, so no segmentation of the point cloud is required. Based on some recent techniques for parameterizing higher genus meshes, when some mild conditions on the sampling density are satisfied, the algorithm generates a closed toroidal manifold which interpolates the input and is geometrically similar to the sampled surface.     

基于车载激光雷达的隧道内障碍物检测

采用激光雷达对隧道环境中的障碍物进行检测时,海量的隧道点云容易造成虚警.对此,文章提出了一种基于车载激光雷达的隧道内障碍物检测方法.其首先设计了背景点云的滤除策略,根据三维点云生成二维栅格图,并标记隧道边界栅格和地面栅格;对隧道边界栅格点云进行欧几里得聚类和边界曲线估计,根据估计曲线滤除隧道边界点云;对地面栅格点云进行...     

R-VPCG: RGB image feature fusion-based virtual point cloud generation for 3D car detection

Although 3D object detection methods based on feature fusion have made great progress, the methods still have the problem of low precision due to sparse point clouds. In this paper, we propose a new feature fusion-based method, which can generate virtual point cloud and improve the precision of car detection. Considering that RGB images have rich semantic information, this method firstly segments the cars from the image, and then projected the raw point clouds onto the segmented car image to segment point clouds of the cars. Furthermore, the segmented point clouds are input to the virtual point cloud generation module. The module regresses the direction of car, then combines the foreground points to generate virtual point clouds and superimposed with the raw point cloud. Eventually, the processed point cloud is converted to voxel representation, which is then fed into 3D sparse convolutional network to extract features, and finally a region proposal network is used to detect cars in a bird’s-eye view. Experimental results on KITTI dataset show that our method is effective, and the precision have significant advantages compared to other similar feature fusion-based methods.     

基于Octomap的仿人机器人局部环境与能力图模型算法

基于3D点云数据的机器人三维空间能力图模型算法存在体素网格搜索计算量大的问题，由于OcTree在三维空间细分时的层次化优势，提出一种基于Octomap的局部环境与能力图模型算法。首先，根据NAO机器人的关节组成、正向运动学、逆向运动学和刚体坐标变换，对NAO仿人机器人构建全身二叉树状运动学模型；其次在此基础上使用前向运动学在笛卡儿空间计算离散的三维可达点云，并将其作为机器人终端效应器的基础工作空间；然后重点描述将点云空间表示转化为Octomap空间节点表示的方法，尤其是空间节点的概率更新方法；最后提出根据节点几何关系进行空间节点更新顺序选择的优化方法，从而高效地实现了仿人机器人能力图的空间优化表示。实验结果表明，相对于之前的原始Octomap更新方法，优化后的算法能降低近30%空间节点数，提高计算效率。