基于二次特征提取的煤矿巷道表面点云数据精简方法

采用三维激光扫描技术提取的煤矿巷道表面点云数据量大且存在较多的冗余数据,而现有点云数据精简方法存在大数量级点云处理过程中细节保留不足的问题。针对上述问题,提出了一种基于二次特征提取的煤矿巷道表面点云数据精简方法。首先对采集到的原始巷道点云数据进行去噪预处理;其次建立K-d树,并利用主成分分析法对去噪后点云数据估算来拟合邻域平面的法向量;然后通过较小的法向量夹角阈值对点云进行初步的特征区域与非特征区域划分,保留特征区域并随机下采样非特征区域,接着依据较大的法向量夹角阈值将特征区域点云划分为特征点和非特征点,并对非特征点进行体素随机采样;最后将2次点云精简结果与特征点合并得到最终的精简数据。仿真结果表明,该方法在百万数据量级点云和高精简率条件下,相较曲率精简方法、随机精简方法和栅格精简方法,在特征保留和重构精度方面都取得了更好的效果,三维重构后计算所得标准偏差平均可低于相同精简率下其他方法 30%左右。     

基于改进随机抽样一致算法的视频拼接算法

为了解决实时视频拼接中的鬼影和拼接缝问题,提出了一种基于改进随机抽样一致算法的实时视频拼接算法。首先,针对双目摄像头的重叠区域,采用加速鲁棒特征算法提取特征点,寻找特征匹配点对;然后利用改进的随机抽样一致算法去除误匹配点对,获得最优单应性矩阵;最后,对重叠区域像素进行动态融合处理。实验结果表明,采用本文算法可以有效地消除视频重叠区域的拼接缝和鬼影,同时可保证视频拼接系统的实时性。     

物体坐标系曲面投影立体环视图像生成算法

针对立体环视图像拼接准确度的难点,提出了一种基于物体坐标系的曲面投影图像拼接算法.根据实际应用场合建立合适的三维模型,对图像进行基于物体坐标系的纹理映射,将三维模型划分为融合、非融合区域,将原始图像映射到非融合区域,对于拼接融合区域,结合模型特点,设计了一种基于角度信息的加权平均融合算法,对拼接后的图像进行颜色校正,消...     

基于 FPFH 特征提取的散乱点云精简算法

针对原始点云模型中存在大量冗余数据问题,提出一种基于快速点特征直方图(FPFH)特征提取的点云精简算法,有效兼顾了特征信息保留和整体完整性。算法首先查找并保留原始模型的边缘点;然后计算非边缘点的 FPFH 值,由此得到点云的特征值,并进行排序且划分出特征区域和非特征区域,保留特征区域内的点;最后将非特征区域划分为 k 个子区间,对每个子区间用改进的最远点采样算法进行采样。将该算法与最远点采样算法、非均匀网格法、k-means 算法和自适应曲率熵算法进行对比实验,并用标准化信息熵评价方法对精简后的点云进行评价,实验表明其优于其他精简算法。此外,可视化结果也表明,该算法能够在保证精简模型完整性的同时,较好地保留住点云大部分特征信息。     

路侧多激光雷达协同感知和误差自校准方法

多激光雷达3D点云数据融合能够弥补单个激光雷达感知范围有限的缺陷,而雷达安装误差自校准能够获取更加准确的感知数据。基于此,提出了路侧激光雷达协同感知数据融合算法和安装误差自校准方法。首先,使用KD-tree和k近邻算法查找两幅点云的重叠点,并对重叠点进行拼接处理。其次,基于深度学习模型实现多激光雷达数据融合,利用点云数据拼接特征实现激光雷达的误差自校准。最后,基于长安大学车联网与智能汽车试验场搭建多激光雷达数据采集平台,采集试验场内的点云数据来验证本次提出的数据融合算法和误差自校准方法。结果表明,后融合目标识别比前融合目标识别效率提升11.6%,且激光雷达误差自校准方法使有效数据精度提升了13.44%。     

基于改进法向量估计的多视角点云配准算法

针对多视角三维测量中多片点云重叠区域提取及高精度配准的问题,本文提出一种多视角异源低重叠率点云配准方法。首先基于点云之间的初始位置,互相计算源点云和目标点云彼此的最近点集,自动提取两片点云重叠部分;然后使用迭代最近点算法精配准重叠点云。通过法向量特征进一步提高点云配准精度,并提出改进点云法向量估计算法用以剔除错误匹配点对,显著减小了复杂结构点云配准的距离均方根误差。结果表明,使用经典点云数据仿真实验验证了该算法的性能,并通过多视角条纹投影三维测量系统采集点云数据验证了算法的有效性。     

含噪点云预处理技术研究

用三维光学测量系统进行测量时,由于周围环境、人、设备等各方面的影响,测量数据中常常会掺入噪声。针对体外飞点和离群成簇噪声分别采取基于K_近邻搜索的平均距离去噪算法和改进的基于近邻点距传播的去噪算法进行处理,取得了较好的去噪效果。针对直接测量或者多次测量拼接获取的点云存在"粗糙毛刺"和点云多层重叠的状况,采用基于MLS的拟合平面投影光顺算法进行光滑处理,去除"粗糙毛刺"和打薄重叠区域。该光顺去噪预处理算法已经成功运用到三维测量系统的点云处理模块中。     

基于多视角图像的三维人脸重建

多视角图像三维信息重建一直是计算机视觉领域的研究难点,通常需要多摄像机多角度同时拍摄,才能够恢复物体的点云数据。本文提出了一种基于SIFT特征的三维拼接方法 ,可以实现非标定拼接。该方法计算特征向量之间的欧氏距离,通过比较最小距离与次小距离之比来进行匹配。实验结果表明本方法基本能够描述物体的真实轮廓,但点云数据精度仍有待提高。     

网格形变细分的大视差图像拼接算法

针对大视差图像拼接后重叠区域出现重影、非重叠区域发生透视失真等问题,提出一种改进的大视差图像拼接算法。利用尽可能投影算法(APAP)建立低密度网格形变,根据待拼接图像成对匹配点的分布对重叠区域内的网格形变进行细分。通过随机采样一致性算法计算全局最优相似矩阵,校正非重叠区域发生的透视失真现象。将全局最优相似矩阵与网格单应矩阵加权叠加,实现目标图像形变。在此基础上,对目标图像重叠区域进行内容感知,保留重要度较低的区域并完成拼接,以避免重叠区域出现重影问题。实验结果表明,相对APAP、SPHP等算法,该算法的拼接效果更能还原真实场景,且拼接图像的均方根误差值较低。     

保留边界的点云简化方法

针对点云简化算法中边界点丢失的问题,提出了一种保留边界的三维散乱点云的非均匀简化算法。首先利用kd-tree建立散乱数据点云的空间拓扑关系,计算出每个数据点的k邻域;然后针对目前依据点云分布均匀性算法提取边界效率低的问题,提出一种改进的点云边界点判定算法;最后保留所有边界点,对非边界点,根据曲面变分值和k邻域点已保留比例,进行点云的非均匀简化。实验结果表明,该算法精度高,空间复杂度低,而且简化后点云边界保留完整。     

A fast 3D seed-filling algorithm

The 3D seed-filling algorithm that fills consecutive object voxels at a time has shown higher efficiency than the method of filling only one voxel at a time. However, it searches seeds for filled voxels already containing no seeds. This paper presents a fast 3D seed-filling algorithm that uses a 2D pointer array of linked lists to avoid the redundant seed searches. The linked lists record the spans of filled voxels. Five comparison cases determine the current filling span, and the neighboring spans for searching seeds are either non-overlapping, or completely or partially overlapping. Seed searches are executed only for the non-overlapping span or part (in the case of the partial overlapping span) to minimize the searches. The experimental results show that the proposed algorithm is effective in eliminating the redundant seed searches and achieves high efficiency.     

基于凸壳与有向包围盒的骨架提取方法

为获取三维模型的几何及拓扑信息,提出一种基于凸壳与有向包围盒(OBB)的线性骨架提取方法.首先将三维网格模型进行分割生成多个子网格模型;然后对各子网格中的点集求取凸壳作为该子网格点集的近似,由凸壳顶点的形心构成原始骨架点;再用OBB进行重叠计算求出相交点集,以生成关节骨架点;最后对原始骨架点与关节骨架点进行连接,经冗余检测后形成完整骨架.实验结果表明,该方法快速、有效,提取出的骨架能保证连通性与中心性且能很好地提取关节骨架点,为蒙皮关节动画、模型形状分析等提供有效信息.     

Reducing Redundancy in Subspace Clustering

In this paper, we first study an important but unsolved dilemma in the literature of subspace clustering, which is referred to as “information overlapping-data coverage” challenge. Current solutions of subspace clustering usually invoke a grid-based Apriori-like procedure to identify dense regions and construct subspace clusters afterward. Due to the nature of monotonicity property in Apriori-like procedures, it is inherent that if a region is identified as dense, all its projected regions are also identified as dense, causing overlapping/redundant clustering information to be inevitably reported to users when generating clusters from such highly correlated regions. However, naive methods to filter redundant clusters will incur a challenging problem in the other side of the dilemma, called the “data coverage” issue. Note that two clusters may have highly correlated dense regions but their data members could be highly different to each other. Arbitrarily removing one of them may lose the coverage of data with clustering information, thus likely reporting an incomplete and biased clustering result. In this paper, therefore, we further propose an innovative algorithm, called "NOnRedundant Subspace Cluster mining” (NORSC), to efficiently discover a succinct collection of subspace clusters while also maintaining the required degree of data coverage. NORSC not only avoids generating the redundant clusters with most of the contained data covered by higher dimensional clusters to resolve the information overlapping problem but also limits the information loss to cope with the data coverage problem. As shown by our experimental results, NORSC is very effective in identifying a concise and small set of subspace clusters, while incurring time complexity in orders of magnitude better than that of previous works.     

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。     

Accurate integration of multi-view range images using k-means clustering

3D modelling finds a wide range of applications in industry. However, due to the presence of surface scanning noise, accumulative registration errors, and improper data fusion, reconstructed object surfaces using range images captured from multiple viewpoints are often distorted with thick patches, false connections, blurred features and artefacts. Moreover, the existing integration methods are often expensive in the sense of both computational time and data storage. These shortcomings limit the wide applications of 3D modelling using the latest laser scanning systems. In this paper, the k-means clustering approach (from the pattern recognition and machine learning literatures) is employed to minimize the integration error and to optimize the fused point locations. To initialize the clustering approach, an automatic method is developed, shifting points in the overlapping areas between neighbouring views towards each other, so that the initialized cluster centroids are in between the two overlapping surfaces. This results in more efficient and effective integration of data. While the overlapping areas were initially detected using a single distance threshold, they are then refined using the k-means clustering method. For more accurate integration results, a weighting scheme reflecting the imaging principle is developed to integrate the corresponding points in the overlapping areas. The fused point set is finally triangulated using an improved Delaunay method, guaranteeing a watertight surface. A comparative study based on real images shows that the proposed algorithm is efficient in the sense of either running time or memory usage and reduces significantly the integration error, while desirably retaining geometric details of 3D object surfaces of interest.     

RANSAC-based DARCES: a new approach to fast automatic registrationof partially overlapping range images

In this paper, we propose a new method, the RANSAC-based DARCES method (data-aligned rigidity-constrained exhaustive search based on random sample consensus), which can solve the partially overlapping 3D registration problem without any initial estimation. For the noiseless case, the basic algorithm of our method can guarantee that the solution it finds is the true one, and its time complexity can be shown to be relatively low. An extra characteristic is that our method can be used even for the case that there are no local features in the 3D data sets     

Receiver-based loss tolerance method for 3D progressive streaming

While progressive compression techniques were proposed long time ago, fast and efficient streaming of detailed 3D models over lossy networks still remains a challenge. A primary reason is that packet loss occurring in unreliable networks is highly unpredictable, leading to connectivity inconsistency and distortions of decompressed meshes. Although prior researches have proposed various methods to handle errors caused by transmission loss, they are always accompanied by additional costs such as redundant transmission data, bandwidth overloads, and result distortions. In this paper, we address this problem from a receiver’s point of view and propose a novel receiver-based loss tolerance scheme which is capable of recovering the lost data when streaming 3D progressive meshes over lossy networks. Specifically, we use some constraints during the model compression procedure on the server side, and suggest a prediction method to handle loss of structural and geometric data on the client/receiver side. Our algorithm works without any data retransmission or introducing any unnecessary protection bits. We stream mesh refinement data on reliable and unreliable networks separately so as to reduce the transmission delay as well as to obtain a satisfactory decompression result. The experimental results indicate that the decompression procedure can be accomplished quickly, suggesting that it is an efficient and practical solution. It is also shown that the proposed prediction technique achieves a very good approximation of the original mesh with low distortions, and in the mean time, error propagations are also well controlled.     

Fast accessing Web3D contents using lightweight progressive meshes

Accessing Web3D contents is relatively slow through Internet under limited bandwidth. Preprocessing of 3D models can certainly alleviate the problem, such as 3D compression and progressive meshes (PM). But none of them considers the similarity between components of a 3D model, so that we could take advantage of this to further improve the efficiency. This paper proposes a similarity‐aware data reduction method together with PM, called lightweight progressive meshes (LPM). LPM aims to excavate similar components in a 3D model, generates PM representation of each component left after removing redundant components, and organizes all the processed data using a structure called lightweight scene graph. The proposed LPM possesses four significant advantages. First, it can minimize the file size of 3D model dramatically without almost any precision loss. Because of this, minimal data is delivered. Second, PM enables the delivery to be progressive, so called streaming. Third, when rendering at client side, due to lightweight scene graph, decompression is not necessary and instanced rendering is fully exerted. Fourth, it is extremely efficient and effective under very limited bandwidth, especially when delivering large 3D scenes. Performance on real data justifies the effectiveness of our LPM, which improves the state‐of‐the‐art in accessing Web3D contents. Copyright © 2015 John Wiley & Sons, Ltd.     

3D crystal structure identification using fuzzy neural networks

The problem of recognizing nano-scale images of lattice projections comes down to identification of crystal lattice structure. The paper considers two types of fuzzy neural networks that can be used for tackling the problem at hand: the Takagi-Sugeno-Kang model and Mamdani-Zadeh model (the latter being a modification of the Wang-Mendel fuzzy neural network). We offer a threestage neural network learning process. In the first two stages crystal lattices are grouped in non-overlapping classes, and lattices belonging to overlapping classes are recognized at the third stage. In the research, we thoroughly investigate the applicability of the neural net models to structure identification of 3D crystal lattices.     

Area-wide roof plane segmentation in airborne LiDAR point clouds

Most algorithms performing segmentation of 3D point cloud data acquired by, e.g. Airborne Laser Scanning (ALS) systems are not suitable for large study areas because the huge amount of point cloud data cannot be processed in the computer’s main memory. In this study a new workflow for seamless automated roof plane detection from ALS data is presented and applied to a large study area. The design of the workflow allows area-wide segmentation of roof planes on common computer hardware but leaves the option open to be combined with distributed computing (e.g. cluster and grid environments). The workflow that is fully implemented in a Geographical Information System (GIS) uses the geometrical information of the 3D point cloud and involves four major steps: (i) The whole dataset is divided into several overlapping subareas, i.e. tiles. (ii) A raster based candidate region detection algorithm is performed for each tile that identifies potential areas containing buildings. (iii) The resulting building candidate regions of all tiles are merged and those areas overlapping one another from adjacent tiles are united to a single building area. (iv) Finally, three dimensional roof planes are extracted from the building candidate regions and each region is treated separately. The presented workflow reduces the data volume of the point cloud that has to be analyzed significantly and leads to the main advantage that seamless area-wide point cloud based segmentation can be performed without requiring a computationally intensive algorithm detecting and combining segments being part of several subareas (i.e. processing tiles). A reduction of 85% of the input data volume for point cloud segmentation in the presented study area could be achieved, which directly decreases computation time.