时变曲面一致性骨骼提取

针对提取时变曲面骨骼效率低下且骨骼序列不一致的问题,提出一种基于传播的策略使用配准算法修复初始不完整骨骼,从而提取时变曲面骨骼的方法。首先,提取时变曲面一些关键帧的完整骨骼,另外直接提取关键帧之间曲面的骨骼序列;然后,利用设计出的全局骨骼配准方法,将关键帧骨骼形变到其邻居骨骼;最后,将形变后的关键帧骨骼信息转移到邻居骨骼,从而产生一个新的完整骨骼。对整个骨骼序列执行该操作,以提取完整骨骼。实验结果表明,该方法高效、准确,且该系统可以应用到未经处理的扫描产生的动态几何数据上,这些数据往往包含着大量的噪声点、奇异点和大块的缺失数据,但仍能较快获得一致性骨骼序列。     

基于机载LiDAR点云的电力线自动提取

基于机载激光雷达数据提出了一种在林区中电力线自动提取方法,该方法是基于统计分析和二值化图像处理技术设计。首先采用高度阈值,分离出电力线候选数据集,并采用一组标准(例如,高度标准,密度标准和直方图阈值)来对候选集进行统计分析,选择电力线的候选点。然后将候选点转化为二值化图像,并进行形态学优化,采用基于图像的处理技术,利用渐进概率霍夫线性变换对图像进行直线分割。最后将分割出来的电力线二值化图像转换成三维点云,并利用区域增长精细化提取电力线点云。使用不同林区环境下的4组机载激光雷达数据进行实验,实验结果表明,算法在林区环境下能够完整地提取出电力线,且电力线分类精度较高,对于电力巡线具有较高的利用价值。     

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.     

应用遗传模糊聚类实现点云数据区域分割

为了准确地实现点云数据的区域分割,将基于遗传算法的模糊聚类算法应用于逆向工程中的点云数据区域分割中。首先估算出法矢量、高斯曲率和平均曲率,并与坐标一起组成八维特征向量,用加权距离代替欧氏距离,然后通过遗传算法获得全局最优解的近似解;最后将近似解作为模糊聚类的初始解进行迭代,实现点云数据的区域分割,从而避免传统FCM算法的局部性和对初始解的敏感性,减少了迭代次数。以汽车钣金件为例,证明了应用遗传模糊聚类实现点云数据区域分割的有效性,并验证了该方法能快速、准确地实现点云数据的区域分割。     

手写体汉字笔画特征点的完整性分析

提出了一种从手写体汉字骨骼图像．上提取分叉点的改进算法。采用新的骨骼图像分析技术提取新的候选特征点集，并且证明了骨骼上所有的分叉点都可以用该特征点集中的元素表示。实验表明新特征点集中元索的数量较以前大大减少。     

融合骨骼数据的弱监督视频行为检测方法研究

在视频理解任务中,为了减少行为检测任务中的数据标注成本同时提高检测精度,本文提出一种基于骨骼数据的弱监督视频行为检测方法,使用视频级的类别标注对行为检测网络进行弱监督训练.本文以二维人体骨骼数据和RGB图像数据作为网络输入,利用循环神经网络从骨骼数据中提取时域信息并送入全连接层输出所需的特征.骨骼数据提取的特征与RGB数据提取的特征分别传入注意力网络生成相应的权重,用来生成加权特征与加权时序类别激活图值.最后根据加权特征与加权时序类别激活图值进行行为的分类与时域定位.实验结果表明,所提出的结合人体骨骼数据的算法比有监督算法少使用了数据的时间标注.算法在THUMOS14数据集和ActivityNet1.3数据集上能够提高检测准确率.     

骨龄自动评测系统中骨骼边缘提取方法研究

骨龄是衡量少年儿童骨骼发育程度的数据指标,对骨龄自动评测系统中的预处理和骨骼边缘提取方法进行了研究.实验中,采用Laplacian增强和线性增强相结合的增强方法,增强了骨骼和软组织间的对比度,增强后的骨骼信息不失真;通过对几个边缘算子提取的边缘图像进行对比,采用Canny算子和Sobel算子边缘图像的"与"操作提取了较为完整的骨骼边缘.为将来骨骼特征的提取和骨骼的分类奠定了基础.     

从机载激光扫描数据中交互式提取人字形房屋模型的方法研究

快速有效地从机载激光扫描(airborne lidar)点云数据中提取房屋模型是机载激光扫描系统应用研究的一项重要课题。鉴于交互式半自动方法是从点云数据中提取简单规则房屋模型信息的一种可行的方法,为此采用3维空间中改进的Hough变换以及聚类分析,提出了一种从点云数据中交互式提取人字形房屋模型的方法。该方法分为3个步骤:第1步是用户确定房屋区域,并分割出候选的屋顶点集;第2步是对候选屋顶点集采用3维空间中改进的Hough变换,然后对Hough变换后所获得的参数集进行聚类分析,以此获得屋顶所在平面的参数表达;第3步是构造完整的房屋模型。通过屋顶平面相交得到屋脊线,通过点的范围分析确定屋顶的边缘,最后添加竖直的墙面构造完整的房屋模型。经采用Optech公司提供的数据进行实验初步证实,该方法是可行的,且整个提取过程只需要很少的用户交互,因此适合于大规模处理机载激光扫描数据。     

一种基于RANSAC 框架的椭球提取算法

面向点云数据,提出一种椭球的检测和提取算法。该算法采用随机采样一 致性（RANSAC）框架,通过多次随机采样点云模型,建立多个能够生成椭球体的最小点集, 对每个最小点集计算椭球参数,经过验证后建立椭球候选集合,利用分数函数评价各候选, 筛选出最佳提取椭球。实验结果表明：对于人工合成和扫描仪获取的点云数据,该算法稳定 可靠,可有效地提取出正确的椭球。     

复杂异型建筑立面测绘轮廓提取方法设计

为解决点云数据密度异常时复杂异型建筑立面测绘轮廓提取精度变差的问题,提出基于局部点云密度的复杂异型建筑立面测绘轮廓提取方法。引入基于平面投影和双边滤波的测绘点云数据平滑方法,对测绘数据进行去噪和平滑处理,并通过点云分割方法提取目标点云区域。通过基于改进Alpha Shapes算法的立面测绘轮廓提取方法,以边界网格筛选的方式,去除目标点云区域冗余点云数据后,使用滚动圆半径自适应调节方法提取轮廓数据。试验结果表明,所提取轮廓匹配度高达95.08%,具有良好的精度和可行性。该方法可在有效平滑点云数据、分割获取目标点云区域的同时,高精度提取复杂异型建筑立面测绘轮廓。     

Road pothole extraction and safety evaluation by integration of point cloud and images derived from mobile mapping sensors

The automatic detection and extraction of road pothole distress is an important issue regarding healthy road structures, monitoring, and maintenance. In this paper, a new algorithm that integrates the mobile point cloud and images is proposed for the detection of road potholes. The algorithm includes three steps: 2D candidate pothole extraction from the images using a deep learning method, 3D candidate pothole extraction via a point cloud, and pothole determination by depth analysis. Because the texture features of the pothole and asphalt or concrete patches greatly differ from those of a normal road, pothole or patch distress images are used to establish a training set and train and test the deep learning system. Subsequently, the 2D candidate pothole is extracted from the images and labeled via the trained DeepLabv3+, a state-of-the-art pixel-wise classification (semantic segmentation) network. The edge of the candidate pothole in the image is then used to establish the relationship between the mobile point cloud and images. The original road point cloud around the edge of the candidate pothole is categorized into two groups, that is, interior and exterior points, according to the relationship between the point cloud and images. The exterior points are used to fit the road plane and calculate the accurate 3D shape of the candidate potholes. Finally, the interior points of a candidate pothole are used to analyze the depth distribution to determine if the candidate pothole is a pothole or patch. To verify the proposed method, two cases, including real and simulation cases, are selected. The real case is an expressway in Shanghai with a length of 26.4 km. Based on the proposed method, 77 candidate potholes are extracted by the DeepLabv3+ system; 49 potholes and 28 patches are finally filtered. The affected lanes and pothole locations are analyzed. The simulation case is selected to verify the geometric accuracy of the detected potholes. The results show that the mean accuracy of the detected potholes is ∼1.5–2.8 cm.     

Detection of closed sharp edges in point clouds using normal estimation and graph theory

The reconstruction of a surface model from a point cloud is an important task in the reverse engineering of industrial parts. We aim at constructing a curve network on the point cloud that will define the border of the various surface patches. In this paper, we present an algorithm to extract closed sharp feature lines, which is necessary to create such a closed curve network. We use a first order segmentation to extract candidate feature points and process them as a graph to recover the sharp feature lines. To this end, a minimum spanning tree is constructed and afterwards a reconnection procedure closes the lines. The algorithm is fast and gives good results for real-world point sets from industrial applications.     

Isogeometric shape optimization of photonic crystals via Coons patches

In this paper, we present an approach that extends isogeometric shape optimization from optimization of rectangular-like NURBS patches to the optimization of topologically complex geometries. We have successfully applied this approach in designing photonic crystals where complex geometries have been optimized to maximize the band gaps.Salient features of this approach include the following: (1) multi-patch Coons representation of design geometry. The design geometry is represented as a collection of Coons patches where the four boundaries of each patch are represented as NURBS curves. The use of multiple patches is motivated by the need for representing topologically complex geometries. The Coons patches are used as a design representation so that designers do not need to specify interior control points and they provide a mechanism to compute analytical sensitivities for internal nodes in shape optimization, (2) exact boundary conversion to the analysis geometry with guaranteed mesh injectivity. The analysis geometry is a collection of NURBS patches that are converted from the multi-patch Coons representation with geometric exactness in patch boundaries. The internal NURBS control points are embedded in the parametric domain of the Coons patches with a built-in mesh rectifier to ensure the injectivity of the resulting B-spline geometry, i.e. every point in the physical domain is mapped to one point in the parametric domain, (3) analytical sensitivities. Sensitivities of objective functions and constraints with respect to design variables are derived through nodal sensitivities. The nodal sensitivities for the boundary control points are directly determined by the design parameters and those for internal nodes are obtained via the corresponding Coons patches.     

一种提取物体线形骨架的新方法

提出了一种提取物体线形骨架的新方法. 该方法首先计算物体距离变换的梯度, 从而得到一个矢量场. 距离变换的梯度对提取物体线形骨架具有重要意义, 可据此获得物体内部的关键点, 其中每一个关键点代表了物体的一个凸部分. 之后, 用搜索梯度最短路径的方法连接关键点, 得到物体的线形骨架. 本文方法得到的线形骨架能很好地反映物体拓扑和形状特征, 并不易受边界噪声干扰. 此外, 本文方法克服了基于距离变换的骨架提取算法的固有缺点, 获得了具有良好连通性的骨架. 因此, 基于本文方法得到的骨架能用于物体识别和匹配等领域. 对大量二维、三维物体的实验取得了令人满意的效果.     

On-the-fly Curve-skeleton Computation for 3D Shapes

The curve-skeleton of a 3D object is an abstract geometrical and topological representation of its 3D shape. It maps the spatial relation of geometrically meaningful parts to a graph structure. Each arc of this graph represents a part of the object with roughly constant diameter or thickness, and approximates its centerline. This makes the curve-skeleton suitable to describe and handle articulated objects such as characters for animation. We present an algorithm to extract such a skeleton on-the-fly, both from point clouds and polygonal meshes. The algorithm is based on a deformable model evolution that captures the object's volumetric shape. The deformable model involves multiple competing fronts which evolve inside the object in a coarse-to-fine manner. We first track these fronts' centers, and then merge and filter the resulting arcs to obtain a curve-skeleton of the object. The process inherits the robustness of the reconstruction technique, being able to cope with noisy input, intricate geometry and complex topology. It creates a natural segmentation of the object and computes a center curve for each segment while maintaining a full correspondence between the skeleton and the boundary of the object.     

An adaptive normal estimation method for scanned point clouds with sharp features

Normal estimation is an essential task for scanned point clouds in various CAD/CAM applications. Many existing methods are unable to reliably estimate normals for points around sharp features since the neighborhood employed for the normal estimation would enclose points belonging to different surface patches across the sharp feature. To address this challenging issue, a robust normal estimation method is developed in order to effectively establish a proper neighborhood for each point in the scanned point cloud. In particular, for a point near sharp features, an anisotropic neighborhood is formed to only enclose neighboring points located on the same surface patch as the point. Neighboring points on the other surface patches are discarded. The developed method has been demonstrated to be robust towards noise and outliers in the scanned point cloud and capable of dealing with sparse point clouds. Some parameters are involved in the developed method. An automatic procedure is devised to adaptively evaluate the values of these parameters according to the varying local geometry. Numerous case studies using both synthetic and measured point cloud data have been carried out to compare the reliability and robustness of the proposed method against various existing methods.     

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,...     

Roof plane extraction from airborne lidar point clouds

Planar patches are important primitives for polyhedral building models. One of the key challenges for successful reconstruction of three-dimensional (3D) building models from airborne lidar point clouds is achieving high quality recognition and segmentation of the roof planar points. Unfortunately, the current automatic extraction processes for planar surfaces continue to suffer from limitations such as sensitivity to the selection of seed points and the lack of computational efficiency. In order to address these drawbacks, a new fully automatic segmentation method is proposed in this article, which is capable of the following: (1) processing a roof point dataset with an arbitrary shape; (2) robustly selecting the seed points in a parameter space with reduced dimensions; and (3) segmenting the planar patches in a sub-dataset with similar attributes when region growing in the object space. The detection of seed points in the parameter space was improved by mapping the accumulator array to a 1D space. The range for region growing in the object space was reduced by an attribute similarity measure that split the roof dataset into candidate and non-candidate subsets. The experimental results confirmed that the proposed approach can extract planar patches of building roofs robustly and efficiently.