几何特征保持的文物点云去噪算法

三维激光扫描是一种快速获取高精度点云的新技术,但由于受物体本身的构造、粗糙程度、纹理以及测量环境等因素的影响,获取的点云数据大多存在孤立的噪声点。针对文物点云数据模型中复杂噪声难以去除的问题,提出一种几何特征保持的点云去噪算法。首先通过栅格划分删除点云中的大尺度噪声;然后定义点云中数据点的曲率因子和密度因子,并通过对其加权构造模糊C均值聚类（Fuzzy C-means clustering, FCM）的目标函数;最后采用该特征加权FCM算法删除小尺度噪声,从而实现点云的去噪处理。实验结果表明,该几何特征保持的去噪算法对文物点云数据具有良好的去噪效果,是一种有效的点云去噪算法。     

一种新的散乱点云快速去噪算法

针对三维扫描仪获取的含噪点云数据会严重影响到后期三维重建的精度,提出一种新的散乱点云快速去噪算法。该算法首先通过改进的K-means聚类算法来建立点云的空间拓扑关系,然后对聚类后每一类的点云进行噪声点识别及去除。实验结果表明算法简单快速,在散乱点云实现有效聚类的基础上不但去噪效果良好,而且能够快速去除点云中的明显离群噪声点,保留理想目标点云。     

一种基于RANSAC的点云特征线提取算法

点云中提取的特征线在点云处理中具有重要的应用价值,已被应用于对称性检测、表面重建及点云与图像之间的注册等。然而,已有的点云特征线提取算法无法有效地处理点云中不可避免的噪声、外点和数据缺失,而随机采样一致性RANSAC由于具有较高的鲁棒性,在图像和三维模型处理中具有广泛的应用。为此,针对由建筑物或机械部件等具有平面特征的物体扫描得到的点云,提出了一种基于RANSAC的特征线提取算法。本算法首先基于RANSAC在点云中检测出多个平面,然后将每个平面参数化域的边界点作为候选,在这些候选点上再应用基于全局约束的RANSAC得到最终的特征线。实验结果表明,该算法对点云中的噪声、外点和数据缺失具有很强的鲁棒性。     

分形维数的全局点云初始配准算法

针对重叠率低、角度大的点云数据之间的配准进行了研究,提出基于分形维数的全局点云初始配准算法。计算点云中各点的维数值;通过维数属性,从点云中提取特征点;聚类特征点,形成全局结构;从全局结构中,获得全等三角形对,作为匹配点对,进行初始配准;进行剪枝迭代最近点（Trimmed Iterative Closest Point,Trimmed-ICP）细配准。该算法与全局最优迭代最近点（Global optimal Iterative Closest Point,Go-ICP）算法相比,能够有效缩小不同角度的点云数据之间的位姿差异,显著提升对重叠率低、角度大的点云数据的配准效果。     

基于直升机激光点云的分裂导线重建研究

电力线三维模型是输电线路安全和增容分析的基础,机载/直升机激光雷达技术已经成为电力三维模型重建的重要技术手段,但少有研究涉及分裂导线的高精度建模。通过分析分裂导线点云数据的特点,提出一种基于点云分段、聚类分析和曲线拟合的分裂导线精细三维重建方法。最后利用获取的四分裂导线点云数据,考虑实际作业中可能遇到的点云缺失、密度偏低等情况,对算法进行了测试和分析。结果表明:该算法能够自适应地识别点云中分裂导线的数目,分离不同分裂导线的点云,建模结果可以满足输电线路安全分析的要求。     

激光点云提取建筑物平面目标算法研究

从激光点云中提取建筑物信息是当前遥感数据处理的热点与难点,而构成建筑物的平面以及轮廓线的提取是LIDAR数据处理和建筑物三维建模的关键技术。本文通过分析激光点云数据中建筑物的特征,综合点云滤波、KD树索引、三维Hough变换以及Gauss球法向量统计算法的各自优点,提出了一套建筑物平面及轮廓的自动提取算法,并通过实验验证了该算法的有效性。     

基于距离统计的有序纹理点云离群点检测

三维数据的离群点检测是纹理点云数据处理的重要内容之一，为了有效快速地检测离群点，根据纹理点云的有序结构特征，提出了基于距离统计的检测算法。首先在每个点到其K邻域中其他点距离的基础上计算出K邻域距离；然后根据有序点云中该距离符合正态分布的特点和正态分布3σ定理，将超出3倍方差范围的点认定为离群点。实验结果显示算法采用曼哈顿-最大距离进行检测，当K为4时可以更加快速准确地将有序点云中的离群点检测出来。由此得出，基于距离统计的算法可以有效地将离群点检测出来，同时成功地应用于纹理点云的离群点检测。     

基于多判据的散乱点云特征点提取算法

为了有效获取散乱点云中的尖锐特征点和边界特征点,提出一种利用多判据融合的特征点提取算法。首先利用一种改进的k-d tree构建点云拓扑,搜索样点的K局部邻域;然后利用法向夹角判定准则、核密度判定准则、场力和判定准则分别求取各个样点局部邻域的三个特征参数,最后通过加权计算特征参数得到每个样点的特征值与全局判定阈值,特征值比阈值大的点即为特征点。实验证明,该算法能有效的获取散乱点云中边沿特征点与尖锐特征点。     

基于纹理特征的三维点云数据配准算法研究

使用Kinect可以方便地获取物体的纹理图像和三维点云数据。研究一种通过获取纹理图像的特征点进行快速三维点云数据配准的算法．并最终应用到室内环境的三维场芾重建中。实验表明,此算法具有直观、实现简单、运算量小等优点。     

机载LiDAR数据提取山区道路方法研究

结合山区道路的空间分布特点和激光点云特征,提出了一种从机载LiDAR数据中快速提取山区道路的方法。首先,利用形态学滤波方法进行点云滤波,以去除原始数据的非地面点(建筑、输电线路以及植被等)。在此基础上,采用基于多规则区域生长算法提取道路点并进行优化、然后采用Freeman链编码方法定位追踪道路边界,并利用数学形态学方法进一步细化道路中心线,进而提取完整的道路信息。利用山区机载LiDAR点云数据进行试验并与其他方法的处理结果进行比较,结果表明:本文方法能够有效地从激光点云中提取道路信息:提取道路的完整度为93.87%,正确率为93.84%,质量为88.43%。     

基于虚拟格网的建筑物点云轮廓线自动提取

在分析现有轮廓线提取方法不足的基础上，提出基于虚拟格网的建筑物轮廓线自动提取方法。该方法利用建筑物点云生成虚拟格网并进行二值填充；采用邻域分析方法进行边界格网的标记与追踪；为了避免边界追踪错误，设计了基于方向的单边缘格网抑制方法及基于距离的连接关系调整方法以改善提取结果质量；根据格网追踪结果，从原始建筑物点云中提取真实轮廓点以保持原始建筑物轮廓形态；采用随机抽样一致性估计及最小二乘拟合方法进行轮廓线规则化处理，实现建筑物轮廓线的自动提取。实验结果表明，该方法能快速从建筑物点云中提取轮廓线，可为建筑物轮廓线的自动提取提供一种可行的解决方案。     

一种去除机载LiDAR航带重叠区冗余点云的方法

机载LiDAR系统在获取高密度地表点云的同时,也带来了数据冗余的问题,特别是在航带重叠区中尤为突出。旨在研究无完整航迹信息辅助下去除航带重叠点,提出了基于点云GPS时间直方图的去除航带重叠点的方法。该方法包括三个步骤:(1)建立点云的GPS时间直方图,并根据GPS时间直方图特点获取航带重叠区外包矩形以及外包矩形中的所有点云;(2)考虑到城市中高密度点云有助于建筑物的三维重建,通过滤波分类处理获取建筑物点并予以全部保留;(3)对重叠区中除建筑物点外的其他所有点进行格网数据组织并根据GPS时间直方图逐格网去除航带冗余点。实验结果表明,该方法能较好地保留建筑物点的同时高效去除航带重叠点且不依赖于航迹信息,提高了后续数据分析处理的效率。     

改进ICP算法用于多组图像的点云拼接与融合

随着计算机图形图像技术、机器视觉、虚拟现实技术等的发展,近年来,通过室外场景的序列图像进行三维重建的方法逐渐成为计算机视觉和图形学等相关领域的重点研究方向。但是,通常在图像的采集过程中由于受到测量设备和环境的影响,单次拍摄的序列组图可能并不能提取到足够的物体表面信息,导致不能够完成三维物体的重构,而不能为后续的目标识别和精确打击提供准确信息依据。针对此类问题,文中采用融合多组图像点云的方法,先利用彩色直方图匹配补充补拍图像序列,然后单独解算补拍组图的点云数据,再对不同点云的重叠部分利用改进的迭代最近点算法计算变换参数,最后进行融合处理,从而完成不同组图的点云数据间的配准和融合工作。实验证明,该方法能快速有效补充用于重构的点云数据,拼接和融合效果良好。     

基于线特征及迭代最近点算法的地基建筑物点云自动配准方法

为克服迭代最近点(ICP)算法易陷入局部最优的缺陷，提出一种基于线特征及ICP算法的地基建筑物点云自动配准方法。首先，基于法向一致性进行建筑物点云平面分割；接着，采用alpha-shape算法进行点簇轮廓线提取，并拆分和拟合处理得到特征线段；然后，以线对作为配准基元，以线对夹角和距离作为相似性测度进行同名特征匹配，实现建筑物点云的粗配准；最后，以粗配准结果为初值，进一步采用ICP算法完成点云精确配准。利用两组部分重叠的建筑物点云进行配准实验，实验结果表明，采用由粗到精的配准方法能有效改善ICP算法对初值依赖的问题，实现具有部分重叠的建筑物点云的有效配准。     

An approach to combine progressively captured point clouds for BIM update

Building information models (BIMs) provide opportunities to serve as an information repository to store and deliver as-built information. Since a building is not always constructed exactly as the design information specifies, there will be discrepancies between a BIM created in the design phase (called as-designed BIM) and the as-built conditions. Point clouds captured by laser scans can be used as a reference to update an as-designed BIM into an as-built BIM (i.e., the BIM that captures the as-built information). Occlusions and construction progress prevent a laser scan performed at a single point in time to capture a complete view of building components. Progressively scanning a building during the construction phase and combining the progressively captured point cloud data together can provide the geometric information missing in the point cloud data captured previously. However, combining all point cloud data will result in large file sizes and might not always guarantee additional building component information. This paper provides the details of an approach developed to help engineers decide on which progressively captured point cloud data to combine in order to get more geometric information and eliminate large file sizes due to redundant point clouds.     

Memory-efficient real-time map building using octree of planes and points

This paper presents an octree-based map building algorithm for mobile home-service robots. The robot is equipped with a time-of-flight camera, which produces point clouds of the environment surfaces. Given the successive input of point clouds, a 3D map is incrementally computed in real time. The map is accurate and memory-efficient because the octree nodes containing points on a plane are merged and represented simply by an index to the plane. The real-time performance is achieved largely due to the parallel processing capability of the many-core Graphics Processing Unit used for plane extraction.     

Urban building reconstruction from raw LiDAR point data

We present a method for automatic reconstruction of the volumetric structures of urban buildings, directly from raw LiDAR point clouds. Given the large-scale LiDAR data from a group of urban buildings, we take advantage of the “divide-and-conquer” strategy to decompose the entire point clouds into a number of subsets, each of which corresponds to an individual building. For each urban building, we determine its upward direction and partition the corresponding point data into a series of consecutive blocks, achieved by investigating the distributions of feature points of the building along the upward direction. Next, we propose a novel algorithm, Spectral Residual Clustering (SRC), to extract the primitive elements within the contours of blocks from the sectional point set, which is formed by registering the series of consecutive slicing points. Subsequently, we detect the geometric constraints among primitive elements through individual fitting, and perform constrained fitting over all primitive elements to obtain the accurate contour. On this basis, we execute 3D modeling operations, like extrusion, lofting or sweeping, to generate the 3D models of blocks. The final accurate 3D models are generated by applying the union Boolean operations over the block models. We evaluate our reconstruction method on a variety of raw LiDAR scans to verify its robustness and effectiveness.     

Textured mesh surface reconstruction of large buildings with multi-view stereo

There are three main approaches for reconstructing 3D models of buildings. Laser scanning is accurate but expensive and limited by the laser’s range. Structure-from-motion (SfM) and multi-view stereo (MVS) recover 3D point clouds from multiple views of a building. MVS methods, especially patch-based MVS, can achieve higher density than do SfM methods. Sophisticated algorithms need to be applied to the point clouds to construct mesh surfaces. The recovered point clouds can be sparse in areas that lack features for accurate reconstruction, making recovery of complete surfaces difficult. Moreover, segmentation of the building’s surfaces from surrounding surfaces almost always requires some form of manual inputs, diminishing the ease of practical application of automatic 3D reconstruction algorithms. This paper presents an alternative approach for reconstructing textured mesh surfaces from point cloud recovered by patch-based MVS method. To a good first approximation, a building’s surfaces can be modeled by planes or curve surfaces which are fitted to the point cloud. 3D points are resampled on the fitted surfaces in an orderly pattern, whose colors are obtained from the input images. This approach is simple, inexpensive, and effective for reconstructing textured mesh surfaces of large buildings. Test results show that the reconstructed 3D models are sufficiently accurate and realistic for 3D visualization in various applications.     

CrackEmbed: Point feature embedding for crack segmentation from disaster site point clouds with anomaly detection

Laser-scanned point clouds can be used to represent the 3D as-damaged condition of building structures in a post-disaster scenario. Performing crack detection from the acquired point clouds is a critical component of disaster relief tasks such as structural damage assessment and risk assessment. Crack detection methods based on intensity or normals commonly result in noisy detections. On the other hand, deep learning methods can achieve higher accuracy but require a large dataset of annotated cracks. This research proposes an unsupervised learning framework based on anomaly detection to segment out cracked regions from disaster site point clouds. First, building components of interest are extracted from the point cloud scene using region growing segmentation. Next, a point-based deep neural network is used to extract discriminative point features using the geometry of the local point neighborhood. The neural network embedding, CrackEmbed, is trained using the triplet loss function on the S3DIS dataset. Then, an anomaly detection algorithm is used to separate out the points belonging to cracked regions based on the distribution of these point features. The proposed method was evaluated on laser-scanned point clouds from the 2015 Nepal earthquake as well as a disaster response training facility in the U.S. Evaluation results based on the point-level precision and recall metrics showed that CrackEmbed in conjunction with the isolation forest algorithm resulted in the best performance overall.     

A CNN-based 3D patch registration approach for integrating sequential models in support of progress monitoring

Significant advancements in three-dimensional (3D) imaging technologies have enabled the ability to effectively monitor and manage the progress of works in construction. Traditionally, 3D point clouds have been used in conjunction with building information models to visualize the progress of works. The discrepancies between ‘as-planned’ and ‘actual’ models are unable to be automatically identified using the existing approaches due the absence of an effective registration algorithm. To ensure the registration accuracy of multi-scanned point clouds, an automated method based on a data-driven Convolutional Neural Network (CNN) deep learning algorithm is proposed. In this instance, 3D Point cloud patches are aligned with spatial datasets that are scanned from different locations using range cameras. The registration results are used to automatically detect spatial changes when compared with different point clouds. The quantified changes are utilized to determine the percentage of work that has been completed at fixed intervals. The developed registration approach is tested and validated using a series of experiments. It is demonstrated that discrepancies between ‘as-planned’ and ‘actual’ models can be identified with a higher level of accuracy, which can enable the baseline for monitoring construction to be undertaken in real-time.