应用激光雷达与相机信息融合的障碍物识别

针对探测器在地外星体表面软着陆过程中的障碍物识别问题,提出了一种融合三维点云数据与灰度图像数据进行精确障碍物识别的方法。首先利用坐标转换将灰度图像与三维点云归一化到同一坐标系下,实现传感器数据的融合。然后采用改进K均值聚类算法对预处理后灰度图像进行图像分割,生成光学障碍图。最后利用开源库PCL(Point Cloud Library)对激光雷达生成的三维激光点云数据进行处理,采用随机采样一致性算法提取着陆区地形水平面,对去除水平面后的点云数据进行点云分割,分离出突起物、凹坑等障碍物,并通过激光雷达与相机转换坐标系,投影到像平面,生成最终障碍图。     

基于独立三视图的图像序列三维重建

针对图像序列的高效、稳定三维重建问题,提出一种基于独立三视图的三维重建方法.首先以三视图为重建单元,叠加三视图约束,实现基础矩阵的鲁棒性计算,然后通过三角测量恢复得到三视图对应的三维场景局部三维点云.对于三视图的稳定三维点云刚体结构,通过求解相邻三视图间转换参数,将整个图像序列的三维点云统一到同一空间坐标系,实现完整图像序列的三维点云重建.实验表明,所提出算法计算简单、效率高,并且不产生误差累积,重投影误差在1个像素左右,实现建模所需可靠三维点云数据的快速生成.     

板金属冲压零件表面模型与实测点云配准研究

为研究板料零件成形后实测点与设计原型之间的制造偏差,需要将实测坐标点云数据和产品数字模型进行配准,实现设计坐标系和实测点云数据的测量坐标系的统一。以CAD模型离散点云数据为引导,将配准过程分为初步配准和精确配准两个步骤。采用基于PCA提取特征坐标系的方法进行初步配准,采用k-d tree加速的ICP算法进行精确配准,将实测点云数据和设计原型离散点云数据转换到同一个坐标系中。基于UG NX平台将经过坐标转换的实测点云数据读入到CAD模型中,得到同一环境坐标系下配准后的实测点云数据和CAD模型,为制造偏差分析提供了基础,并进行了实例验证。     

对三视图的DXF图形数据进行特征识别与立体重构

本文介绍了一种对在ＡｕｔｏＣＡＤ环境下绘制的三视图的ＤＸＦ图形数据进行特征识别和立体重构的原理与方法；通过对三视图的ＤＸＦ图形数据的分析，利用三视图的尺寸标注信息，可以将ＤＸＦ文件提供的三视图进行自动分离，按特征建模的要求对各视图的实体进行特征识别和特征分类；采用特征文件作为媒介，利用ＣＳＧ模型，可以将识别的特征在ＡｕｔｏＣＡＤ环境下重构出来；本文的方法不仅能识别ＡｕｔｏＣＡＤ系统设计的零件，产生     

基于三视图的实体重建技术研究

基于三视图的三维实体重建技术是根据已有二维视图中的几何信息和拓扑信息,生成相应的三维实体模型.以AutoCAD绘制的三视图及DXF格式的文件信息为基础,提出并实现了一种由三视图重建三维实体的算法.通过对三视图的规则处理,由计算机自动实现实体重建,对三视图分别进行平移、旋转、拉伸操作,然后作相应的布尔运算即可反求出该视图...     

基于Kinect的人体三维重建方法

通过Kinect体感仪,实现人体三维重建.使用Kinect体感仪,扫描获取人体三维数据,利用深度数据转换算法实现二维顶点的三维化,再通过红外相机姿态跟踪算法进行顶点集配准,求解出相机每次的相对位移与转动角度,实现相机姿态跟踪,并将每次拍摄到的点集转换到同一全局坐标系下,使用晶格化显示集成算法将点云集成到提前划分好精度及尺寸的体素晶格中,最后利用投影映射算法获得可视化的人体三维立体模型.使用Kinect体感仪及三脚架等辅助设备方便快捷地获取人体三维重建结果,并通过3D打印技术对模型进行输出.该研究实现了人体三维重建中人体扫描、处理、重建、输出全流程.     

基于Spider卷积的三维点云分类与分割网络

针对传统的卷积神经网络（CNN）不能直接处理点云数据，需先将点云数据转换为多视图或者体素化网格，导致过程复杂且点云识别精度低的问题，提出一种新型的点云分类与分割网络Linked-Spider CNN。首先，在Spider CNN基础上通过增加Spider卷积层数以获取点云深层次特征；其次，引入残差网络的思想在每层Spider卷积增加短连接构成残差块；然后，将每层残差块的输出特征进行拼接融合形成点云特征；最后，使用三层全连接层对点云特征进行分类或者利用多层卷积层对点云特征进行分割。在ModelNet40和ShapeNet Parts数据集上将所提网络与PointNet、PointNet++和Spider CNN等网络进行对比实验，实验结果表明，所提网络可以提高点云的分类精度和分割效果，说明该网络具有更快的收敛速度和更强的鲁棒性。     

利用标志点多视图约束实现结构光扫描高精度粗拼接

在采用标志点拼接的结构光扫描系统中,两两相邻视图拼接存在累积误差,导致拼接精度会随拼接次数下降,为此提出一种利用标志点多视图几何约束的高精度拼接方法.首先利用两两视图拼接的方式在扫描过程中构建标志点多视图网络,并利用光束法平差技术优化多视图网络得到高精度全局控制点;在此过程中保存每个视局部坐标系下三维点云,然后将各局部坐标系下点云和全局控制点进行拼接,得到物体表面完整的三维数据.该方法克服了传统拼接过程中累积误差,提高了多视角三维扫描拼接精度;并通过实验证明了所提出算法的有效性.     

基于相似图投影学习的多视图聚类

随着数据来源方式的多样化发展,多视图聚类成为研究热点。大多数算法过于专注利用图结构寻求一致表示,却忽视了如何学习图结构本身;此外,一些方法通常基于固定视图进行算法优化。为了解决这些问题,提出了一种基于相似图投影学习的多视图聚类算法(multi-view clustering based on similarity graph projection learning, MCSGP),通过利用投影图有效地融合了全局结构信息和局部潜在信息到一个共识图中,而不仅是追求每个视图与共识图的一致性。通过在共识图矩阵的图拉普拉斯矩阵上施加秩约束,该算法能够自然地将数据点划分到所需数量的簇中。在两个人工数据集和七个真实数据集的实验中,MCSGP算法在人工数据集上的聚类效果表现出色,同时在涉及21个指标的真实数据集中,有17个指标达到了最优水平,从而充分证明了该算法的优越性能。     

基于图像变形技术的平行坐标可视化

针对传统的平行坐标可视化方法不适于处理大量高维数据等不足,将基于控制点的图像变形技术引入到可视化中,首先利用学习集中的数据建立控制点到目标点的变形函数,求出方程的参数,再将测试集中的数据通过变形函数映射到平行坐标系中,实验结果表明,通过图像变形原理能较好地实现高维数据的分类和可视化效果,优于传统的平行坐标方法。     

Estimation of three-dimensional objects from orthographic views with inconsistencies

Many algorithms to construct 3-D solid objects from orthographic views assume the bottom-up approach. This paper describes a method for identifying conflictions found in inconsistent views which improbably present complete objects and estimating solid objects. The sources of inconsistencies are extra segments, missing segments and incorrect classifications of line types (visible lines or hidden lines). In order to supply candidates for missing segments, probable segments are generated not from three views but from two views. The signs appearing in each step of the bottom-up algorithm are examined, and then the heuristic method for selecting more probable segments is developed. The estimation of solid objects and identification of incoherences are useful, for example, to detect improper input of three views and incorrect recognition of engineering drawings.     

Finite-resolution aspect graphs of polyhedral objects

We address the problem of computing the aspect graph of a polyhedral object observed by an orthographic camera with limited spatial resolution, such that two image points separated by a distance smaller than a preset threshold cannot be resolved. Under this model, views that would differ under normal orthographic projection may become equivalent, while “accidental” views may occur over finite areas of the view space. We present a catalogue of visual events for polyhedral objects and give an algorithm for computing the aspect graph and enumerating all qualitatively different aspects. The algorithm has been fully implemented and results are presented     

Detecting moving objects using the rigidity constraint

A method for visually detecting moving objects from a moving camera using point correspondences in two orthographic views is described. The method applies a simple structure-from-motion analysis and then identifies those points inconsistent with the interpretation of the scene as a single rigid object. It is effective even when the actual motion parameters cannot be recovered. Demonstrations are presented using point correspondences automatically determined from real image sequences     

Three-Dimensional Reconstruction of Points and Lines with Unknown Correspondence across Images

Three-dimensional reconstruction from a set of images is an important and difficult problem in computer vision. In this paper, we address the problem of determining image feature correspondences while simultaneously reconstructing the corresponding 3D features, given the camera poses of disparate monocular views. First, two new affinity measures are presented that capture the degree to which candidate features from different images consistently represent the projection of the same 3D point or 3D line. An affinity measure for point features in two different views is defined with respect to their distance from a hypothetical projected 3D pseudo-intersection point. Similarly, an affinity measure for 2D image line segments across three views is defined with respect to a 3D pseudo-intersection line. These affinity measures provide a foundation for determining unknown correspondences using weighted bipartite graphs representing candidate point and line matches across different images. As a result of this graph representation, a standard graph-theoretic algorithm can provide an optimal, simultaneous matching and triangulation of points across two views, and lines across three views. Experimental results on synthetic and real data demonstrate the effectiveness of the approach.An erratum to this article can be found at     

Efficiently computing and representing aspect graphs of polyhedralobjects

An efficient algorithm and a data structure for computing and representing the aspect graph of polyhedral objects under orthographic projection are presented. The aspect graph is an approach to representing 3-D objects by a set of 2-D views, for the purpose of object recognition. In this approach the viewpoint space is partitioned into regions such that in each region the qualitative structure of the line drawing does not change. The viewing data of an object is the partition of the viewpoint space together with a representative view in each region. The algorithm computes the viewing data for line drawings of polyhedral objects under orthographic projection     

Motion and structure from orthographic projections

S. Ullman's classical (1979) results on motion/structure from orthographic views are revisited. Specifically, two results are presented: (1) two orthographic views allow an uncountably infinite number of solutions to motion/structure of a rigid body, and (2) a linear algorithm for solving motion/structure from four point correspondences over three views     

二维视图到三维几何模型转换中的BOX显示法

提出一种从二维视图到三维几何模型转换中视图的BOX显示方法,该方法可以将分离识别后的视图自动按照视图投影的方向放置,即将单一的二维视图平面向多投影面转换,建立视图之间的投影对应关系,从而直观地表达实体的投影视图,帮助用户进行形体想象。给出了两个视图BOX显示的例子。     

Feature point tracking in time-varying images

This paper examines the problem of tracking feature points in dynamic imagery. Two types of imaging geometries are examined: orthographic projection and perspective projection. In each case, the goal is to perform the feature point tracking with a minimal number of images. The feature point tracking problem is shown to be intractable and a grddey heuristic is presented.     

基于三视图的曲面体重建技术

根据空间二次曲线的投影特征，首先利用“五点法”分两步来构造投影曲线，得到投影二次曲线的几何参数表达式，然后应用“点对应匹配法”由各视图相应的投影曲线构造空间二次曲线的坐标式参数方程，并同时构造出空间曲线边的支撑平面，从而建立与三视图相对应的曲面体线框模型，最后，提取线框模型中的面信息，并根据二流形体的性质和莫比乌斯法则（Moebius rule)以及正投影规律，对候选面进行组合判定，将实用面进行装配，得到重建结果的实体模型，这种方法将处理对象拓展到了任意投影方位下的二次曲线。     

View variation of point-set and line-segment features

The variation, with respect to view, of 2D features defined for projections of 3D point sets and line segments is studied. It is established that general-case view-invariants do not exist for any number of points, given true perspective, weak perspective, or orthographic projection models. Feature variation under the weak perspective approximation is then addressed. Though there are no general-case weak-perspective invariants, there are special-case invariants of practical importance. Those cited in the literature are derived from linear dependence relations and the invariance of this type of relation to linear transformation. The variation with respect to view is studied for an important set of 2D line segment features: the relative orientation, size, and position of one line segment with respect to another. The analysis includes an evaluation criterion for feature utility in terms of view-variation. This relationship is a function of both the feature and the particular configuration of 3D line segments. The use of this information in objection recognition is demonstrated for difficult discrimination tasks