Rapid geometric modeling for visual simulation using semi-automated reconstruction from single image

This paper presents a novel algorithm that enables the semi-automatic reconstruction of human-made structures (e.g., buildings) into piecewise planar 3D models from a single image. This allows the models to be readily used in virtual or augmented reality visual simulations or for data acquisition in 3D geographic information systems. Contrary to traditional labor-intensive but accurate single view reconstruction (SVR) solutions based purely on geometric constraints, and contrary to recent fully automatic albeit low-accuracy SVR algorithms based on statistical inference, the presented method achieves a compromise between speed and accuracy, leading to less user input and acceptable visual effects. The user input required in the presented approach is primarily a line drawing that represents an outline of the building to be reconstructed. Using this input, the developed method takes advantage of a newly proposed vanishing point (VP) detection algorithm that can simultaneously estimate multiple VPs in an image. With those VPs, the normal direction of planes—which are projected onto the image plane as polygons in the line drawing—can be automatically calculated. Following this step, a linear system similar to the traditional SVR solutions can be used to achieve 3D reconstruction. Experiments that demonstrate the efficacy and visual outcome of the developed method are also described, highlighting the method’s potential use for rapid geometric model building of surrounding structures in visual simulation of engineering processes.     

基于Kinect的旋转刚体三维重建方法

针对在非匀速非定轴旋转条件下利用Kinect进行刚体三维重建问题,提出一种改进的基于Kinect传感器的旋转刚体三维重建方法。首先利用Kinect采集深度图像,然后用改进的加权ICP(Iterative Closest Point)算法在非匀速非定轴旋转条件下进行配准,再将各点云变换到同一坐标系下,最后根据所得点云生成三维模型表面,通过GPU(Graphic Processing Unit)编程技术来提高计算速度以满足实际需求。实验结果表明:该方法具有重建效果良好的特点。     

利用VTK进行三维肠道重建算法的改进

肠道CT的三维重建是提高肠道疾病诊疗准确性的迫切需要。利用可视化工具包VTK并结合VC++,实现了肠道三维重建。经典三维重建Marching Cubes（简称MC）算法会产生二义性,针对常用的渐近线法消除二义性计算量大的问题,提出了一种改进的MC算法：采用线性插值法求出二义性面与等值面的交点,然后分别连接二义性面对边上的交点形成两条相交直线,最后通过判断直线交点的状态值,来唯一地确定等值线的连接方式,从而快速重建出三维肠道。实验结果表明,利用改进的MC算法比起传统MC算法,在三维重建的质量和效率上都得到了很大的提高。     

伪点云修正增强激光雷达数据

目的 激光雷达在自动驾驶中具有重要意义,但其价格昂贵,且产生的激光线束数量仍然较少,造成采集的点云密度较稀疏。为了更好地感知周围环境,本文提出一种激光雷达数据增强算法,由双目图像生成伪点云并对伪点云进行坐标修正,进而实现激光雷达点云的稠密化处理,提高3D目标检测精度。此算法不针对特定的3D目标检测网络结构,是一种通用的点云稠密化方法。方法 首先利用双目RGB图像生成深度图像,根据先验的相机参数和深度信息计算出每个像素点在雷达坐标系下的粗略3维坐标,即伪点云。为了更好地分割地面,本文提出了循环RANSAC （random sample consensus）算法,引入了一个分离平面型非地面点云的暂存器,改进复杂场景下的地面分割效果。然后将原始点云进行地面分割后插入KDTree （k-dimensional tree）,以伪点云中的每个点为中心在KDTree中搜索若干近邻点,基于这些近邻点进行曲面重建。根据曲面重建结果,设计一种计算几何方法导出伪点云修正后的精确坐标。最后,将修正后的伪点云与原始激光雷达点云融合得到稠密化点云。结果 实验结果表明,稠密化的点云在视觉上具有较好的质量,物体具有更加完整的形状和轮廓,并且在KITTI （Karlsruhe Institute of Technology and Toyota Technological Institute）数据集上提升了3D目标检测精度。在使用该数据增强方法后,KITTI数据集下AVOD （aggregate view object detection）检测方法的AP_3D-Easy （average precision of 3D object detection on easy setting）提升了8.25%,AVOD-FPN （aggregate view object detection with feature pyramid network）检测方法的AP_BEV-Hard （average precision of bird’s eye view on hard setting）提升了7.14%。结论 本文提出的激光雷达数据增强算法,实现了点云的稠密化处理,并使3D目标检测结果更加精确。     

医学图像中微细管道结构的表面绘制算法

在医学图像处理中,常常需要提取出特定的组织或者结构,再以提取到的二值体数据为基础,对组织结构进行三维重建。传统的Marching Cube（MC）算法在对微细结构进行三维重建时,可能会产生断裂现象,不能有效保持原始体数据的连通性。以血管体数据为例,针对医学图像中微细管道结构重建提出一种改进的MC算法,以保持重建后组织结构的连通性。     

A fast registration algorithm of rock point cloud based on spherical projection and feature extraction

Point cloud registration is an essential step in the process of 3D reconstruction. In this paper, a fast registration algorithm of rock mass point cloud is proposed based on the improved iterative closest point (ICP) algorithm. In our proposed algorithm, the point cloud data of single station scanner is transformed into digital images by spherical polar coordinates, then image features are extracted and edge points are removed, the features used in this algorithm is scale-invariant feature transform (SIFT). By analyzing the corresponding relationship between digital images and 3D points, the 3D feature points are extracted, from which we can search for the two-way correspondence as candidates. After the false matches are eliminated by the exhaustive search method based on random sampling, the transformation is computed via the Levenberg-Marquardt-Iterative Closest Point (LM-ICP) algorithm. Experiments on real data of rock mass show that the proposed algorithm has the similar accuracy and better registration efficiency compared with the ICP algorithm and other algorithms.     

Improved Iterative Closest Point(ICP) 3D point cloud registration algorithm based on point cloud filtering and adaptive fireworks for coarse registration

ABSTRACT

Aiming at the problem of long computation time and poor registration accuracy in the current three-dimensional point cloud registration problem, this paper presents a k-dimensional Tree(KD-tree) improved ICP algorithm(KD-tree_ICP) that combines point cloud filtering and adaptive fireworks algorithms for coarse registration. On the basis of the typical KD-tree improved ICP algorithm, the point cloud filtering process and adaptive firework coarse registration process are added. Firstly, the point cloud data acquired by the 3D laser scanner is filtered. And then the adaptive fireworks algorithm is used to perform coarse registration on the filtered point cloud data. Next, the KD-tree_ICP algorithm is used to perform accurate registration on the basis of coarse registration, and the obtained translation and rotation relations are applied to the original point cloud data to obtain the result after registration. Finally, 3D point clouds of physical models of five statues are used for experimental verification, including error analysis, stability analysis and comparison with other algorithms. The experimental results show that the method proposed in this paper has greatly improved the calculation speed and accuracy, and the algorithm is stable and reliable, which can also be applied to the reconstruction of 3D building models, restoration of cultural relics, precision machining and other fields.     

3D Reconstruction of Indoor Scenes via Image Registration

With the development of computer vision technologies, 3D reconstruction has become a hotspot. At present, 3D reconstruction relies heavily on expensive equipment and has poor real-time performance. In this paper, we aim at solving the problem of 3D reconstruction of an indoor scene with large vertical span. In this paper, we propose a novel approach for 3D reconstruction of indoor scenes with only a Kinect. Firstly, this method uses a Kinect sensor to get color images and depth images of an indoor scene. Secondly, the combination of scale-invariant feature transform and random sample consensus algorithm is used to determine the transformation matrix of adjacent frames, which can be seen as the initial value of iterative closest point (ICP). Thirdly, we establish the relative coordinate relation between pair-wise frames which are the initial point cloud data by using ICP. Finally, we achieve the 3D visual reconstruction model of indoor scene by the top-down image registration of point cloud data. This approach not only mitigates the sensor perspective restriction and achieves the indoor scene reconstruction of large vertical span, but also develops the fast algorithm of indoor scene reconstruction with large amount of cloud data. The experimental results show that the proposed algorithm has better accuracy, better reconstruction effect, and less running time for point cloud registration. In addition, the proposed method has great potential applied to 3D simultaneous location and mapping.     

A robot hand-eye calibration method of line laser sensor based on 3D reconstruction

In the robotic eye-in-hand measurement system, a hand-eye calibration method is essential. From the perspective of 3D reconstruction, this paper first analyzes the influence of the line laser sensor hand-eye calibration error on the 3D reconstructed point clouds error. Based on this, considering the influence of line laser sensor measurement errors and the need for high efficiency and convenience in robotic manufacturing systems, this paper proposes a 3D reconstruction-based robot line laser hand-eye calibration method. In this method, combined with the point cloud registration technique, the newly defined error-index more intuitively reflects the calibration result than traditional methods. To raise the performance of the calibration algorithm, a Particle Swarm Optimization - Gaussian Process (PSO-GP) method is adopted to improve the efficiency of the calibration. The experiments show that the Root Mean Square Error (RMSE) of the reconstructed point cloud can reach 0.1256 mm when using the proposed method, and the reprojection error is superior to those using traditional hand-eye calibration methods.     

Weak-perspective structure from motion by fast alternation

This paper addresses the problem of moving object reconstruction. Several methods have been published in the past 20 years including stereo reconstruction as well as multi-view factorization methods. In general, reconstruction algorithms compute the 3D structure of the object and the camera parameters in a non-optimal way, and then a nonlinear and numerical optimization algorithm refines the reconstructed camera parameters and 3D coordinates. In this paper, we propose an adjustment method which is the improved version of the well-known Tomasi–Kanade factorization method. The novelty, which yields the high speed of the algorithm, is that the core of the proposed method is an alternation and we give optimal solutions to the subproblems in the alternation. The improved method is discussed here and it is compared to the widely used bundle adjustment algorithm.     

基于鲁棒估计灭点分层重建的研究

灭点是分层重建过程的重要信息,其求解的准确程度直接关系到最后三维重建的效果。提出了一种基于Hough算法的直线聚类检测方法求取图像中的直线信息以及基于RANSAC的由直线信息估计灭点信息的改进算法,以提高估计灭点的鲁棒性。经试验证明,将所提出的算法应用到分层重建的系统中,在仅有两幅图像的情况下能准确地对目标模型进行重建。     

心内膜表面几何模型三维重建算法研究

心内膜三维表面重建是心内膜三维标测系统中的关键问题。为了满足实际应用需求, 根据采集到的散乱点云数据的特点, 提出了一种改进的泊松表面重建算法。在估计表面点云法向量的基础上, 对表面点云法向量进行法向量一致化处理, 有效地控制时间复杂度, 快速重建出平滑的心脏模型。针对泊松表面重建算法中构建MC曲面出现的二义性问题, 提出一种消除二义性的简化改进方法, 可以更加精确地获取模型逼真表面, 提高重建的速度和精度。同时, 可以根据医生的要求, 对重建出的模型实时修正, 满足临床应用。最后, 通过实验验证了算法的有效性和可行性。     

基于Kinect的轴类零件三维重建研究

使用Kinect采集的深度数据,进行了轴类零件三维重建算法的研究。首先借助Kinect获取深度和彩色数据,通过坐标转换将深度信息转换成三维点云数据;其次提取出感兴趣目标的点云数据,根据点云数据的噪声特点,并对其进行滤波降噪处理;然后进行点云分割获得点云集,最后对各点云集进行结构参数化分析。实验结果表明,本文算法能够精确、高效地实现轴类零件的重建。     

基于自适应聚合与深度优化的三维重建算法

针对现有基于多视图的三维重建方法未充分考虑像素点在其余视图的可见性,从而导致重建完整度不足,且在弱纹理和遮挡区域重建困难等问题,提出了一种应用于高分辨率的三维重建网络。首先提出了一种引入可见性感知的自适应成本聚合方法用于成本量的聚合,通过网络获取视图中像素点的可见性,可以提高遮挡区域重建完整性;采用基于方差预测每像素视差范围,构建空间变化的深度假设面用于分阶段重建,在最后一阶段提出了基于卷积空间传播网络的深度图优化模块,以获得优化的深度图;最后采用改进深度图融合算法,结合所有视图的像素点与3D点的重投影误差进行一致性检查,得到密集点云。在DTU 数据集上与其他方法的定量定性比较结果表明,提出的方法可以重建出细节上表现更好的场景。     

面向三维重建的自适应列文伯格-马夸尔特点云配准方法

针对三维重建时点云配准过程易受环境噪声、点云曝光、光照、物体遮挡等因素的影响,以及传统ICP配准算法配准精度低、耗时长等问题,提出一种基于自适应列文伯格-马夸尔特迭代式的点云配准方法。首先,对初始点云数据采用统计滤波和体素栅格滤波相结合的方式进行降噪预处理;然后,对滤波后的点云进行分层,剔除位于层外的外点数据,以提高后续点云配准的精度;针对传统点云特征描述方法计算量大的问题,使用平滑度参数提取点云特征,以提升点云配准的效率;最后,根据点云特征建立帧间点到线及点到面的约束关系,采用改进的列文伯格-马夸尔特(Levenberg-Marquardt)方法完成点云配准,构建较理想的三维重建模型。实验结果表明,提出的点云配准方法适用于室内及室外场景的三维重建,环境适应性强,且点云配准精度和效率都有较大提升。     

散乱点云数据的高阶平滑隐式曲面重建

针对三维扫描或三维重建获取的散乱点云数据曲面重建问题, 提出基于拉普拉斯规则化的高阶平滑算法。首先, 计算点云数据的包围盒并离散化得到体素空间; 其次, 在体素空间根据隐式曲面的梯度和点云位置、法向信息建立目标函数, 并通过对目标函数的拉普拉斯规则化达到控制重建曲面光顺效果的目的; 再次, 根据最优化原理将重建问题转换为一个稀疏线性方程组求解问题; 最后, 通过步进立方体算法得到重建曲面的三角网格表示。定性和定量的实验结果表明, 该方法重建曲面绘制效果和精确度优于常用的Poisson方法。     

自适应步长的Alpha‑shape表面重建算法

三维物体表面重建在现代临床医学、场景建模和林业测量等方面有着重要应用价值。为了更好地理解三维物体表面形状,本文先介绍了三维空间离散点集的Alpha形状的相关概念。在分析表面重建的Alpha?shape算法的基础上,本文提出一种自适应步长的Alpha?shape算法。通过kd?tree和k近邻平均距离来动态更新α值,使得算法在处理点集密度较大的区域时也能以较少的遍历次数进行表面重建,从而改善了重建效果并提高了算法运行效率。大量随机数据和现实三维采样数据的实验结果表明,本文提出的改进算法与原始算法相比,能大幅度地提高运行效率。     

基于特征点和改进ICP的三维点云数据配准算法

在光学非接触三维测量中,复杂对象的重构需要多组测量数据的配准。最近点迭代(ICP)算法是三维激光扫描数据处理中点云数据配准的一种经典的数学方法,为了获得更好的配准结果,在ICP算法的基础之上,提出了结合基于特征点的等曲率预配准方法和邻近搜索ICP改进算法的精细配准,自动进行点云数据配准的算法,经对牙齿点云模型实验发现,点云数据量越大,算法的配准速度优势越明显,采用ICP算法的运行时间(194.58 s)远大于本算法的运行时间(89.13 s)。应用实例表明:该算法具有速度快、精度高的特点,算法效果良好。     

空地融合的城市道路基础设施数字化技术研究

城市道路基础设施三维模型的重构,在城市道路BIM应用与数字化领域具有重大意义;针对城市交通基础设施数字化重构的需求,对车载激光扫描与无人机倾斜摄影采集技术进行综合运用,提出一套从信息采集、空地点云配准、点云分割到三维重构的完整技术方法;首先使用车载激光扫描技术和无人机倾斜摄影技术对交通基础设施信息进行采集,并使用运动恢复结构算法(SfM,structure from motion)生成基础设施空地点云;其次使用迭代最近点法(ICP,iterative closest point)对空地点云进行精配准,然后利用基于PointNet网络的方法对融合点云进行语义分割;最后对分割出的交通基础设施对象进行三维重构;提出的空地融合的城市交通基础设施数字化技术能够高效地实现交通基础设施重构,为城市交通基础设施数字化提供基础、为后续交通专业领域的应用研究提供便利.