双目视觉的新颖实时局部2维地图构建方法

根据轮式机器人移动的特点,提出一种采用双目视觉的新颖实时局部2维栅格地图构建算法。首先,提出虚拟高度线投影成像原理,将场景均匀栅格化,在栅格中引入虚拟高度线,并将其投影到立体视觉系统的立体图对中产生投影线,将求解场景点高度值的问题转化为在投影线上和水平视差搜索范围内寻找具有最大相似测度的对应点问题;然后,提出一种新颖的局部2维地图构建方法,该方法以机器人所能越过的最大高度为阈值,对高于阈值部分的虚拟高度投影线上的场景点由其在图像对中的相似测度确定其是否为障碍物区域。实验结果表明,该方法满足机器人导航所要求的有效性和实时性,并可应用到构建3维地图。     

基于视觉导航的三维重建算法误差分析及补偿

根据视觉导航应用的特点,提出了由视差图重建三维场景算法的误差分析及误差补偿算法.首先介绍立体视觉三维重建方法.其次针对摄像机透视投影的针孔模型,分析三维重建误差的主要来源.最后针对误差来源提出了误差分析及补偿方法.实验结果证明,此方法计算量适中,完全满足了视觉导航中的实时性、准确性的要求.     

基于地面视差分布的栅格地图建立方法

针对使用立体视觉建立环境地图方法存在信息不完整的问题,提出一种基于地面视差分布的栅格地图建立方法。利用地面视差分布在视差图中进行障碍物和地面点的检测,通过统一但参数值不同的投影模型将障碍物像素和地面点像素投影到栅格地图中,同时考虑立体视觉的量化和匹配误差、地面视差和栅格占据概率的空间分布。通过在非结构化环境中的实验表明,该方法可以实时地建立信息完整且准确的栅格地图。     

VFF^＋：改进的虚拟力场移动机器人避障算法

分析了虚拟力场法采用全局栅格表示环境信息具有累积误差大、信息存储量大的缺点，设计了动态栅格法表示环境信息，使用跟随机器人移动的扇形栅格表示环境信息，使用栅格中心坐标投影的方法存储多次超声测量数据信息，与势场法相结合对机器人进行导航控制。经仿真和实验验证，改进后的虚拟力场法取得了良好的应用效果。     

基于光束法平差的双线阵系统标定技术

针对线阵相机特殊使用场景中所需要的高精度图像,对线阵相机进行高精度标定。提出一种基于光束法平差的双线阵相机标定方法。通过背景差分法获取线阵相机的特征点的像素坐标。再利用已有的直接线性变换方法和非线性优化方法求出相机的内参,外参,畸变参数后,将得到的初始参数与世界坐标作为待优化集合,利用LM法和光束法平差对该集合进行更进一步的优化,使得双线阵系统的重投影误差降到最低。实验表明,该方法与传统的线阵相机标定方法相比重投影误差降低了75.01%。     

基于未标定图像的三维重建算法

提出一种基于多幅未标定图像的三维重建算法。在标记点匹配的基础上进行射影重建,通过施加度量约束将射影重建升级为欧氏重建,即利用未标定的透视图像恢复相机的内、外部参数以及标记点的三维空间坐标,实现场景的三维重建。标记点易于进行点对精确匹配,较手动拾取匹配提高了效率。实验结果表明,利用该算法能够大幅减小再投影误差。     

多投影几何校正误差评估分析

近年来,投影拼接显示技术在展览展示、产品发布、虚拟仿真等领域得到了广泛的应用,但是目前还缺少完整的投影拼接几何校正误差评估方法.在深入分析多投影几何校正特点的基础上提出了一套较为完整的误差评估方法,分为自相关投影拼接误差(投影机自身几何校正之后所产生的误差)以及互相关投影拼接误差(多台投影机之间叠加区域的配准误差);首先提出了自相关投影拼接误差的关键参数——重投影误差(描述了每台投影机投影图像中每个像素点与预期投影位置的接近程度),并使用平均重投影误差、最大重投影误差以及关键点配准误差完善自相关投影拼接误差的评估体系;然后提出了互相关投影拼接误差的关键参数——叠加区域误差(表示投影机之间叠加区域对应像素点之间的匹配程度),并使用平均叠加区域误差、最大叠加区域误差完善互相关投影拼接误差的评估体系;最后使用该方法对平面投影、曲面投影、自由表面投影拼接的几何校正误差进行了分析.理论分析和实验结果表明,提出的误差评估方法能够有效地评估投影几何校正的精度.     

基于栅格模型的双目移动机器人三维场景重建

以投影几何学以及双目立体视觉原理为理论基础,对移动机器人的三维重建技术进行研究,对移动机器人漫道过程中所在的兴趣区域的场景进行较为精确的建模.设计了机器人的快速建模方法,利用迭代最近点算法(ICP),完成了多个局部三维场景模型的融合.同时,结合栅格投射理论,完成了对全局三维场景模型的更新.利用栅格模型重建的三维场景,具有环境信息丰富,模型描述精确的特点,可以应用于移动机器人导航领域.     

基于中心线匹配的导管三维重建技术

针对工业领域中导管的三维重建效率低的问题,提出了一种基于中心线匹配的导管三维重建方法.该方法首先通过导管的平面灰度图像提取出中心线和边缘线,根据立体视觉原理,以非均匀有理 B样条(Non-uniform rational B-spline, NURBS)曲线作为导管中心线的描述工具和匹配基元,利用其透视投影不变性,重建导管的空间中心线,并通过边缘线计算导管的外径,最后利用三维建模技术重建导管的CAD模型.相对于现有导管三维重建方法,该方法具有测量效率高,操作简单的特点.实验结果表明,该方法的导管三维重建时间可控制在1分钟内,重投影误差为0.284像素,导管两端面中心点的测量误差为0.242mm,外径测量误差为0.158mm.     

三维视觉测量中圆中心投影误差分析方法

针对像平面上椭圆的中心不是空间圆中心在像平面上的真正投影中心这一问题,提出了一种圆中心投影误差分析方法。通过建立空间圆平面与像平面之间的映射关系,推导了空间圆中心投影误差的数学模型,并对影响中心投影误差的因素进行了仿真分析。该方法为圆中心的测量误差评估、摄像机网络布局等提供了理论依据,在实际的视觉测量工程中具有一定的应用价值。     

误差云映射的深度融合3维重建

描述了一种应用于视频序列的3维稠密重建方法,主要针对基于多深度图恢复3维物体时存在的多对一映射重复投影问题,提出基于误差云概念的3维定点优化方法.该方法首先通过深度矫正,增加视频序列深度图的一致性;其次利用投影过滤分类算法,把所有投影点按照多对一映射的关系,以3维空间中所有不同点为类型,进行投影点依次映射,将每一点划分在各自的误差云类中以求得投影点与3维点的对应关系;随后采用空间高斯分布求出每个误差云所恢复出来的点坐标.最后通过多边形技术对恢复的点云数据进行网格化,使其重建出精确的目标物体或场景的3维轮廓.从实验结果可以观察到,本文3维重建方法可以有效减少深度图融合多对一映射重复投影问题所带来的负面影响,使重建结果更加接近于真实物体,达到较好的效果.     

3D Echocardiogram Reconstruction Employing a Flip Directional Texture Pyramid

Three dimensional (3D) echocardiogram enables cardiologists to visualize suspicious cardiac structures in detail. In recent years, this three-dimensional echocardiogram carries important clinical value in virtual surgical simulation. However, this 3D echocardiogram involves a trade-off difficulty between accuracy and efficient computation in clinical diagnosis. This paper presents a novel Flip Directional 3D Volume Reconstruction (FD-3DVR) method for the reconstruction of echocardiogram images. The proposed method consists of two main steps: multiplanar volumetric imaging and 3D volume reconstruction. In the creation of multiplanar volumetric imaging, two-dimensional (2D) image pixels are mapped into voxels of the volumetric grid. As the obtained slices are discontinuous, there are some missing voxels in the volume data. To restore the structural and textural information of 3D ultrasound volume, the proposed method creates a volume pyramid in parallel with the flip directional texture pyramid. Initially, the nearest neighbors of missing voxels in the multiplanar volumetric imaging are identified by 3D ANN (Approximate Nearest Neighbor) patch matching method. Furthermore, a flip directional texture pyramid is proposed and aggregated with distance in patch matching to find out the most similar neighbors. In the reconstruction step, structural and textural information obtained from different flip angle directions can reconstruct 3D volume well with the desired accuracy. Compared with existing 3D reconstruction methods, the proposed Flip Directional 3D Volume Reconstruction (FD-3DVR) method provides superior performance for the mean peak signal-to-noise ratio (40.538 for the proposed method I and 39.626 for the proposed method II). Experimental results performed on the cardiac datasets demonstrate the efficiency of the proposed method for the reconstruction of echocardiogram images.     

Design of an improved framework for stratified 3D reconstruction from a pair of images,with reduced ambiguity

Reconstruction of three dimensional (3D) object structure from multiple images is a fundamental problem in computational vision. Many applications in computer vision require the use of structure information of 3D objects. The objective of this work is to develop a stable method of 3D reconstruction of an object, which works without the availability of camera parameters, once the plane at infinity is obtained using the approximate scene information. First, a framework has been designed based on a modification of the auto-calibration procedure for 3D structure computation using singular value decomposition. In the second part of the work, ambiguities present at the various stages of 3D reconstruction have been analysed. Error norms have been proposed, and studied to quantify the ambiguity in the reconstruction process. We attempt to analyse the effect of pose difference between camera views and focal length parameters on the reconstruction process, using experimentation with simulated and real-world data.     

Virtual Archaeologist: assembling the past

We present a complete method, encapsulated in our Virtual Archaeologist system, for the full reconstruction of archaeological finds from 3D scanned fragments. Virtual Archaeologist is designed to assist archaeologists in reconstructing monuments or smaller finds by avoiding unnecessary manual experimentation with fragile and often heavy fragments. An automated procedure cannot completely replace the archaeology expert, but provides a useful estimation of valid fragment combinations, and accurately measures fragment matches. In Virtual Archaeologist, we regard the reconstruction problem from a general, geometric point of view, relying on the broken surface morphology to determine correct matches between fragments     

露天矿生态重建VR仿真系统研究

介绍了用虚拟现实技术开发露天矿生态重建视景仿真系统的几项关键技术。针对露天矿生态重建应用特点,采用层次型与面向对象相结合的三维数据结构,构造露天矿生态重建视景仿真模型;用LOD技术为露天矿虚拟环境中的地形和建筑物构造多层次、多分辨率的细节模型,提出了基于视点的连续LOD算法,对三维地形模型按数据块进行简化,以适应不同硬件平台和视觉特性的分辨率需求;采用Vega软件实现露天矿三维动态全景图显示与实时驱动的基本方法;用实物标图技术在虚拟场景中进行生态重建规划方案的设计方法;提出一种新的用鼠标获取三维虚拟场景中实体模型信息的算法,实现三维动态查询和与外部数据库的链接。     

结合语义分割与模型匹配的室内场景重建方法

目的 由于室内点云场景中物体的密集性、复杂性以及多遮挡等带来的数据不完整和多噪声问题,极大地限制了室内点云场景的重建工作,无法保证场景重建的准确度。为了更好地从无序点云中恢复出完整的场景,提出了一种基于语义分割的室内场景重建方法。方法 通过体素滤波对原始数据进行下采样,计算场景三维尺度不变特征变换（3D scale-invariant feature transform,3D SIFT）特征点,融合下采样结果与场景特征点从而获得优化的场景下采样结果;利用随机抽样一致算法（random sample consensus,RANSAC）对融合采样后的场景提取平面特征,将该特征输入PointNet网络中进行训练,确保共面的点具有相同的局部特征,从而得到每个点在数据集中各个类别的置信度,在此基础上,提出了一种基于投影的区域生长优化方法,聚合语义分割结果中同一物体的点,获得更精细的分割结果;将场景物体的分割结果划分为内环境元素或外环境元素,分别采用模型匹配的方法、平面拟合的方法从而实现场景的重建。结果 在S3DIS （Stanford large-scale 3D indoor space dataset）数据集上进行实验,本文融合采样算法对后续方法的效率和效果有着不同程度的提高,采样后平面提取算法的运行时间仅为采样前的15%;而语义分割方法在全局准确率（overall accuracy,OA）和平均交并比（mean intersection over union,mIoU）两个方面比PointNet网络分别提高了2.3%和4.2%。结论 本文方法能够在保留关键点的同时提高计算效率,在分割准确率方面也有着明显提升,同时可以得到高质量的重建结果。     

基于色彩空间分块匹配的三维动画融合技术

为了提高影视动画制作的三维图像成像质量,需要进行动画图像的动态信息融合处理,提出一种基于二维色彩空间分块匹配的三维动画图像的动态信息融合处理技术,采用虚拟视景重构技术进行三维动画图像采集和特征投影处理,对三维动画图像进行二值拟合和边缘轮廓检测,采用RGB分解技术进行三维动画图像的颜色分量提取,采用颜色模板空间投影算法进行三维动画图像的分块融合处理,提高三维动画图像的边缘像素点的特征配对性能,结合三维动画图像的色彩空间分块融合结果进行像素特征优化配置,计算匹配窗口相关系数,实现三维动画图像的动态信息融合处理。仿真结果表明,采用该方法进行三维动画图像的动态信息融合处理,能提高图像输出峰值信噪比,提高动态成像质量。     

3D finger tracking and recognition image processing for real-time music playing with depth sensors

In this research, we propose a state-of-the-art 3D finger gesture tracking and recognition method. We use the depth sensors for both hands in real time music playing. In line with the development of 3D depth cameras, we implemented a set of 3D gesture-based instruments, such as Virtual Cello and Virtual Piano, which need precise finger tracking in 3D space. For hands tracking, model-based tracking for left hand and appearance-based tracking for right hand techniques are proposed. To detect finger gestures, our approaches consist number of systematic steps as reducing noise in depth map and geometrical processing for Virtual Cello. For Virtual Piano, we introduce the Neural Network (NN) method to detect special hand gestures. It has Multilayer Perceptron (MLP) structure with back propagation training. Literature has few examples using touch screen as medium, with fixed-coordinates, and 2D–gestures to control MIDI input. The end users should no longer carry anything on their hands. We use Senz3D and Leap Motion due to a few technical benefits. Senz3D and Leap Motion use a closer distance to hands, thus detailed finger gestures can be precisely identified. In the past years, we announced a set of virtual musical instruments and the MINE Virtual Band. Our research work is tested on lab environment and professional theatrical stage. More information and demonstrations of the proposed method can be accessed at: http://video.minelab.tw/DETS/VMIB/.     

The automatic height extraction of buildings from shadow region

Height extraction for buildings is a fundamental step of 3D scene reconstruction in many virtual reality applications.In this paper,we propose an automatic method to extract the height of buildings in high resolution satellite imagery based on the length of shadow.Taking into account the limitation of traditional algorithms,we make use of the boundary information of a building to facilitate detecting and matching the shadow regions with higher accuracy.Then,we introduce a shadow-cast model to correct the shadow location in our system.The experimental result shows that when extracting the height of buildings from complex urban regions,our method has better accuracy.