大规模遥感影像全球金字塔并行构建方法

金字塔模型是大规模遥感影像可视化的基础,是在保证精度的前提下,采用不同分辨率的数据来提高渲染速度,从而在网络环境下实现大规模数据共享、服务和辅助决策支持。在构造金字塔的过程中,由于遥感数据经常会突破内存的容量,同时会产生大量的小瓦片,小瓦片存贮非常耗时,传统的串行算法很难满足应用需求。本文提出了一种并行大规模遥感影像的全球金字塔构造算法,利用图形处理器(graphics processing unit,GPU)的高带宽完成费时的重采样计算,使用多线程实现数据的输入和输出,在普通的计算机上实现大规模影像的全球金字塔的快速构建。首先,采用二级分解策略突破GPU、CPU和磁盘的存储瓶颈;然后,利用多线程策略加速数据在内存和磁盘之间的传输,并采用锁页内存来消除GPU全局延迟的影响;最后,用GPU完成大规模的并行重采样计算,并利用四叉树策略提高显存中数据的重复利用率。实验结果表明,本文方法可以明显地提高全球金字塔的构造速度。     

一种基于GPU Tessellation的地形渲染方法

为了在大规模地形实时渲染过程中提高渲染效率和得到更平滑逼真的地形,该文提出了一种基于GPU Tessellation技术的地形可视化方法。该方法首先对地形预处理构建四叉树;使用视锥体裁剪和LOD选择降低CPU-GPU数据传输量;在三角化阶段利用GPU代替传统的CPU进行三角化方法极大地减轻CPU的负担并且提高了渲染速率;同时引入地形粗糙度计算GPU Tessellation算法内部细分因子,达到平滑而又不失细节的地形表面渲染效果;以数据细节层次动态设置GPU Tessellation算法的外部细分因子消除了T型裂缝。实验结果表明,该方法CPU利用率低,能够以较小计算代价消除T型裂缝,在地形实时交互式漫游系统中能以较高的渲染帧率输出平滑、逼真的三维虚拟数字地形。该文方法可运用到大规模地形可视化系统中。     

一种利用SSE2多重纹理混合的大范围虚拟地形可视化技术

目的 大规模三维地形的真实感可视化对于表现战场自然环境具有重要意义,OpenGL、D3D等主流三维图形引擎需要将多层纹理数据发送到GPU端进行多重纹理融合操作。对于瘦客户机,在显卡位宽和显存有限的资源下,大量的多重纹理融合操作常会导致GPU和带宽负载过大,出现绘制画面不流畅、渲染效率低等问题。为此,提出了一种基于SSE2的多重纹理混合技术,通过在CPU端进行混合纹理混合操作,降低GPU负载,减少数据传送时间。实验证明,该方法在保证CPU计算效率的前提下,有效地降低了大范围虚拟战场环境可视化过程中GPU和带宽负载,显著提升了瘦客户机中大范围虚拟战场数据的渲染效率。     

基于GPU的全球海平面高度异常数据渲染

提出了基于GPU的全球真实海平面高度异常数据的三维水面渲染,并分析了海平面高度异常变化与大洋环流之间的关系。首先把DEM格式的海平面高度异常数据通过图形渲染的方式生成纹理数据,将数据量进行压缩并且提高了渲染效率;然后基于自主研发的VV-Ocean海洋虚拟现实与可视化平台,将全球范围的海平面高度异常变化以虚拟现实的方式绘制到三维球面当中,生成动态海平面,直观形象地表达了全球海平面高度在1年内的变化情况;最后将全球海平面高度异常的可视化结果与大洋环流运动进行对照分析,符合洋流运动规律。     

3维数字地球快速缓冲区分析算法

提出一种应用在3维数字地球中的通过图形处理器(GPU)快速实现矢量数据缓冲区分析的算法。使用一张4通道的纹理图作为容器将地理实体的矢量数据传入GPU,利用GPU的高效并行特性,将目标缓冲区纹理中的每个像素所对应的矢量坐标与原实体进行距离量算,在一次渲染中得到缓冲区纹理,最后提取出缓冲区纹理的边界。选择中国的流域和湖泊矢量数据,将本文算法与两种传统的CPU算法进行了缓冲区分析计算、测试和对比。结果显示,本文算法相对于传统矢量算法效率提高了9—16倍,相对于传统栅格算法效率提高11—20倍。实验证明,该算法计算简单,效果明显,特别是随着数据量增大,缓冲区计算速度显著优于传统算法,并能有效解决传统矢量法缓冲区分析中的数据自相交问题。     

基于GPU的遥感影像加速处理算法

随着图形处理器(GPU)计算功能的日益强大,人们不再满足仅仅用它来做图形处理,而是越来越多地将其应用在通用计算方面。在遥感影像融合的很多算法中,影像数据都可以被并行的处理。本文针对融合处理中的遥感影像数据源为GPU设计了具有数据级并行性的输入流,介绍了利用OpenGL着色语言在GPU中实现融合算法的过程,实验结果表明基于GPU的IHS融合算法的处理速度在数据量较大时较之基于CPU的算法有明显的优势,而且这种优势随图像数据量的增加而越来越明显。     

基于图像处理单元的古建筑构件快速绘制

针对大规模古建筑三维模型场景渲染效率低的问题,该文提出了一种基于图像处理单元(GPU)的古建筑构件快速绘制的方法:根据复杂古建筑可分解为若干建筑构件的构造特点,把构件作为建模与绘制单元,以具有可编程的DirectX 11作为三维图形引擎,通过GPU物理层的曲面细分技术,实现旋转体建筑构件的精细表达;利用实例化技术,通过一次性创建构件几何缓存,实现大规模三维场景中重复建筑对象的高速绘制。实验结果表明:对于复杂古建筑物的大数据绘制,该方法与传统的CPU渲染方法相比,在渲染速度、可视化效果、大数据承载能力方面都具有显著的优势。     

基于GPU的三维地下管网实时构建与可视化

城市地下管网是城市地下空间表达不可或缺的一部分。然而,传统基于CPU的大规模地下管线实时建模再送入显卡进行绘制的模式,效率非常低,并且在管线精细建模时,绘制帧率往往达不到实时渲染的需求。对此,本文提出了一种基于GPU的三维地下管网实时构建与可视化策略,该策略以传统二维矢量管线为数据基础,对CPU端进行实时切块,把需要实时构建的管网的管径和管线节点坐标传入GPU,利用GPU提供的几何着色器完成顶点坐标的计算、管线顶点数据自动生成及管线三角网的自动构建。实验结果表明,该策略能够在保证管网拟合逼真度的基础上达到实时构建及多尺度的表达。     

基于Web的大规模三维空间模型高效可视化关键技术

在网络环境下客户端对大规模的三维空间模型进行可视化时仍存在着渲染时间长、计算量大等诸多问题,表现为模型遮挡剔除计算效率低、模型数据传输效率低以及渲染不同模型时存在性能和质量不平衡问题等方面。针对上述问题,提出了针对不同的空间模型剔除粒度的优化选择策略、基于WebGPU计算管线的遮挡剔除算法和基于多线程的大规模三维空间模型数据快速调度方案,降低了离线遮挡剔除方法的预处理时间消耗,提高了模型切换的效率和场景渲染的速率。开发了基于Web的大规模三维空间模型可视化原型系统,开展了不同尺度的三维模型加载与可视化实验,结果表明,本文方法可以有效减少网络环境下大规模三维空间模型数据可视化的加载和渲染时间,增强用户体验。     

分布式地理数据高效可视化技术研究

传统借助于专业软件浏览地理数据的方式,不仅增加了本地磁盘的占用,而且当数据量较大时浏览效率很低。针对地理数据直接浏览不便的问题,提出了基于Spark的影像文件分布式并行切片方案,并利用Leaflet实现了影像瓦片在线高效可视化。实验结果表明,针对地理大文件的浏览效率明显高于目前常用的GIS软件。     

An efficient data organization and scheduling strategy for accelerating large vector data rendering

Rendering large volumes of vector data is computationally intensive and therefore time consuming, leading to lower efficiency and poorer interactive experience. Graphics processing units (GPUs) are powerful tools in data parallel processing but lie idle most of the time. In this study, we propose an approach to improve the performance of vector data rendering by using the parallel computing capability of many‐core GPUs. Vertex transformation, largely a mathematical calculation that does not require communication with the host storage device, is a time‐consuming procedure because all coordinates of each vector feature need to be transformed to screen vertices. Use of a GPU enables optimization of a general‐purpose mathematical calculation, enabling the procedure to be executed in parallel on a many‐core GPU and optimized effectively. This study mainly focuses on: (1) an organization and storage strategy for vector data based on equal pitch alignment, which can adapt to the GPU's calculating characteristics; (2) a paging‐coalescing transfer and memory access strategy for vector data between the CPU and the GPU; and (3) a balancing allocation strategy to take full advantage of all processing cores of the GPU. Experimental results demonstrate that the approach proposed can significantly improve the efficiency of vector data rendering.     

集群环境下基于视点移动的三维城市模型快速显示方法

大范围三维城市模型数据在现有的单机运行环境下,因数据量大导致运行速度慢、计算耗时等难题。为解决该问题,本文结合集群并行运算,提出了一种基于视点移动规则的大范围三维城市模型的快速显示方法。采用静态细节层次简化算法将三维城市模型简化为4个分辨率层次,根据视点移动规律,利用距离和偏心率选择不同层次的细节层次模型,逐级加载不同分辨率层次模型,并在集群系统中并行显示,从而有效地解决了大范围三维城市模型加载显示过慢、场景效果跳跃等问题,实现了对大范围三维城市模型的快速可视化。试验结果表明：随视点变化分层逐级加载不同等级LOD模型,采用PC集群并行绘制,可以快速有效地对大范围三维城市模型进行渲染处理,在兼顾效率的同时,并行地显示模型的细节,具有良好的可视化效果,对智慧城市的建设具有重要的指导意义。     

A Parallel Scheme for Large‐scale Polygon Rasterization on CUDA‐enabled GPUs

This research develops a parallel scheme to adopt multiple graphics processing units (GPUs) to accelerate large‐scale polygon rasterization. Three new parallel strategies are proposed. First, a decomposition strategy considering the calculation complexity of polygons and limited GPU memory is developed to achieve balanced workloads among multiple GPUs. Second, a parallel CPU/GPU scheduling strategy is proposed to conceal the data read/write times. The CPU is engaged with data reads/writes while the GPU rasterizes the polygons in parallel. This strategy can save considerable time spent in reading and writing, further improving the parallel efficiency. Third, a strategy for utilizing the GPU's internal memory and cache is proposed to reduce the time required to access the data. The parallel boundary algebra filling (BAF) algorithm is implemented using the programming models of compute unified device architecture (CUDA), message passing interface (MPI), and open multi‐processing (OpenMP). Experimental results confirm that the implemented parallel algorithm delivers apparent acceleration when a massive dataset is addressed (50.32 GB with approximately 1.3 × 10⁸ polygons), reducing conversion time from 25.43 to 0.69 h, and obtaining a speedup ratio of 36.91. The proposed parallel strategies outperform the conventional method and can be effectively extended to a CPU‐based environment.     

基于Spark的GNSS网基线向量并行化处理

针对传统单机处理大规模复杂GNSS观测数据效率低的问题,引入了Spark大数据集群,利用子网划分思想并调用GAMIT软件对GNSS网基线向量进行解算,实现了并行化计算。实验结果表明,在保证解算精度与整体解算在同一量级上的同时,提高了执行效率,性能优于整体解算,较好地满足了大规模复杂GNSS数据处理需求。      

A binocular parallel rendering method for VR globes

ABSTRACT

The scene-rendering mechanism based on binocular vision is one of the key techniques for the VR globe to achieve immersion-type visualization of global 3D scenes. However, this special rendering mechanism also requires that the 3D scene is continuously drawn twice within one frame, which significantly affects the rendering efficiency of VR globes. Therefore, we propose a binocular parallel rendering method. This method first improves the current rendering process of VR globes by assigning the rendering tasks for the left and right camera of VR to be processed on different CPU cores, thereby achieving parallel rendering of binocular scenes. Second, due to the problem of inconsistent resolution of binocular scenes caused by different viewpoints for the left and right cameras, we propose a resolution synchronize algorithm. this algorithm conducts real-time synchronization on the resolution of scene in the rendering process and thus avoids the problem of erroneous binocular stereo matching. Finally, we validate the effectiveness of the method in this paper through experiments. The results of experiments indicate that while the method in this paper can ensure the consistency of binocular scene resolution, it can decrease the frame time of VR globes by approximately 27% on average.     

基于HTML5 Canvas的态势符号标绘系统设计与实现

针对在线态势符号标绘系统如何快速渲染大数据量态势符号的难题,本文设计了在线态势符号标绘系统框架,研究了基于Canvas的态势符号库、态势符号的模型算法和多层Canvas绘制方法等关键技术,提高了在线态势符号标绘系统的渲染运行效率。将以上方法应用于实际,建设了浙江省在线态势符号标绘系统,并设计对比实验,验证该系统的运行效率,结果表明:本系统的运行速度优于传统态势符号标绘系统;随着绘制对象数据量的增大,该系统运行速度的优势更加明显。     

An effective spherical panoramic LoD model for a mobile street view service

Street view (panoramic view) services have begun to shift from PC platforms to mobile smart devices. Considering the capabilities of smart terminal devices, a 360° spherical level of detail (LoD) model for mobile street view services that renders panoramic images on the inner surface of a sphere via LoD is proposed in this article. Panoramic images are segmented into tiles and organized in a pyramid tile structure for LoD rendering to improve the rendering efficiency of the proposed model. A projection model between panoramic images and the spherical surface is presented to map the panoramic tiles on the spherical graticule. A street view‐rendering algorithm of panoramic images is proposed with the rendering function of OpenGL for Embedded Systems (OpenGL ES). A street view service app running on Android, based on the proposed approach, is implemented to assess two aspects of the panoramic view model, namely visualization effect and efficiency. Experiment results reveal that the 360° spherical LoD model of the panoramic image can display 3D street view scenes better than the cubic panoramic view model. The proposed model also has an excellent 3D visualization effect and high‐efficiency rendering ability for mobile street view services. Therefore, it is applicable in large‐scale mobile street view services both online and offline and in augmented reality navigation.     

A distributed approach for calculating inundation height based on Dijkstra's algorithm

This research proposed a parallelized approach to scaling up the calculation of inundation height, the minimum sea‐level rise required to inundate a cell on a digital elevation model, which is based on Dijkstra's algorithm for shortest‐path calculations on a graph. Our approach is based on the concepts of spatial decomposition, calculate‐and‐correct, and a master/worker parallelization paradigm. The approach was tested using the U.S. Coastal Relief Model (CRM) dataset from the National Geophysical Data Center on a multicore desktop computer and various supercomputing resources through the U.S. Extreme Science and Engineering Discovery Environment (XSEDE) program. Our parallel implementation not only enables computations that were larger than previously possible, but also significantly outperforms serial implementations with respect to running time and memory footprint as the number of processing cores increases. The efficiency of the scalability seemed to be tied to tile size and flattened out at a certain number of workers.     

基于瓦片数据结构的大规模地形构建与显示

地形漫游在仿真、模拟、虚拟现实、游戏等领域都有广泛的应用，但其大规模地形实时动态绘制的速度和质量一直是一个难点。文章主要分析了地形场景数据管理与实时调度、视相关多层次细节模型与可见性判断以及分层数据组织与瓦片数据绘制等关键问题。在研究多种层次算法的基础上，提出了一种实时高帧率绘制大规模地形的瓦片重组数据结构的方法，并改进了视景体裁切重组地形数据的方法。实验结果表明该方法在保持地形逼真的情况下，有很好的绘制网格帧率和实时动态交互的效果。     

利用PixelGrid系统处理多源遥感影像方法研究

随着科学技术的快速发展,人们对于高性能计算技术的需求日益迫切,大规模数据并行处理的集群式系统实现技术开始逐步成熟。我国已对该项技术进行了深入研究,并将其应用到遥感影像处理技术当中,形成了集群式数字摄影测量系统Pixel Grid。相对于传统的摄影测量及遥感影像处理过程,集群式系统整合资源、集成技术,大大提高了数字摄影测量以及遥感影像数据处理乃至空间信息提取的处理效率。这也是目前遥感影像处理技术发展的重要方向之一。