基于MPI的大规模栅格影像并行瓦片化算法
|
摘要
当前主流GIS软件以及互联网地图应用在Web GIS(网络地理信息系统)解决方案中都广泛采用地图切片(又称瓦片),切片处理服务是实现影像在Web GIS上快速无缝浏览的关键技术。针对目前传统算法以及商业GIS软件在大数据量栅格影像快速瓦片化方面的不足,提出一种名为ParaTile的高效栅格影像快速瓦片化方法,ParaTile基于MPI共享外存的并行技术,利用多进程对原始栅格影像进行数据划分,每个进程对其所划分的区域进行独立读写和计算,而后再按照TMS或者Google Tile定义的标准将瓦片进行编码输出。实验采用不同级别大小的遥感影像进行测试,结果表明ParaTile在面对不同规模的数据时,无论从速度还是算法稳定性上都较现有算法和工具具有显著优势,特别是当数据量越大时,这种优势愈加明显。
The map tiles technology are widely used in Web GIS solutions of the current mainstream GIS software and the Internet map applications, tile processing service is the key technology to realize the fast and seamless browsing on Web GIS. Traditional algorithms and commercial GIS software cannot meet the demand of fast processing large data size raster image tiling. In view of these shortcomings and problems, this paper summarizes the current parallel tiling technology and then puts forward a new parallel raster image tile method which named"ParaTile". ParaTile adopts the shared disk parallel technology, using multi-process to divide the source raster image. Each process of ParaTile is read and written independently to the area that it is owned based on MPIparallel IO function. Finally, each process saves the output tile results independently according to the TMS(Tile Map Service)or the standard made by Google Tile. Experiments are tested by different level size of the remote sensing image, the results show that no matter in speed or stability ParaTile algorithm has a great improvement in the same parallel level compared to Arc GIS software, especially the larger size of data the more advantages are.
The map tiles technology are widely used in Web GIS solutions of the current mainstream GIS software and the Internet map applications, tile processing service is the key technology to realize the fast and seamless browsing on Web GIS. Traditional algorithms and commercial GIS software cannot meet the demand of fast processing large data size raster image tiling. In view of these shortcomings and problems, this paper summarizes the current parallel tiling technology and then puts forward a new parallel raster image tile method which named"ParaTile". ParaTile adopts the shared disk parallel technology, using multi-process to divide the source raster image. Each process of ParaTile is read and written independently to the area that it is owned based on MPIparallel IO function. Finally, each process saves the output tile results independently according to the TMS(Tile Map Service)or the standard made by Google Tile. Experiments are tested by different level size of the remote sensing image, the results show that no matter in speed or stability ParaTile algorithm has a great improvement in the same parallel level compared to Arc GIS software, especially the larger size of data the more advantages are.
引文
[1]李德仁,朱欣焰,龚健雅.从数字地图到空间信息网格——空间信息多级网格理论思考[C]//中国地理信息系统协会年会,2003:642-650.
[2]刘晰,张轶,杨军,等.利用并行技术的海量数据瓦片快速构建[J].测绘科学,2016,41(1):144-150.
[3]赵大龙,孙恒宇.地图切片技术分析与简单实现[J].测绘与空间地理信息,2010,33(1):116-118.
[4]Turner N,Fernandez C,Lessin M.Image tile server:US,US8244770[P].2012.
[5]刘帅.一种基于CPU+GPU的地图切片的快速生成方法:中国,CN104267940A[P].2015-01-07.
[6]Yi L.Parallel batch-building remote sensing images tile pyramid with Map Reduce[J].Geomatics&Information Science of Wuhan University,2013,38(3):278-282.
[7]杜波.基于Map Reduce的栅格地图切片系统[D].西安:西安电子科技大学,2014.
[8]Battersby S E,Finn M P,Usery E L,et al.Implications of Web Mercator and its use in online mapping[J].Cartographica the International Journal for Geographic Information&Geovisualization,2014,49(2):85-101.
[9]Fran?ula N.Web Mercator projection[J].Geodetski List Glasilo Hrvatskoga Geodetskog Dru?tva,2014(1).
[10]关雷,刘蕾,郭慧宇.基于瓦片技术的高分辨率遥感影像快速访问技术在测绘生产中的应用研究[J].测绘与空间地理信息,2016,39(2):78-79.
[11]李长春,蔡伯根,上官伟,等.基于Web墨卡托投影的地图算法研究与实现[J].计算机应用研究,2012,29(12):4793-4796.
[12]刘世永,吴秋云,陈荦,等.基于高层级地图瓦片的低层级瓦片并行合成技术[J].地理信息世界,2015,22(6):51-55.
[13]刘镇.遥感影像瓦片金字塔模型[J].科技创新导报,2008(6):199-200.
[14]葛亮,何涛,王均辉,等.基于GDAL的瓦片切割技术研究[J].测绘与空间地理信息,2014(7):130-132.
[2]刘晰,张轶,杨军,等.利用并行技术的海量数据瓦片快速构建[J].测绘科学,2016,41(1):144-150.
[3]赵大龙,孙恒宇.地图切片技术分析与简单实现[J].测绘与空间地理信息,2010,33(1):116-118.
[4]Turner N,Fernandez C,Lessin M.Image tile server:US,US8244770[P].2012.
[5]刘帅.一种基于CPU+GPU的地图切片的快速生成方法:中国,CN104267940A[P].2015-01-07.
[6]Yi L.Parallel batch-building remote sensing images tile pyramid with Map Reduce[J].Geomatics&Information Science of Wuhan University,2013,38(3):278-282.
[7]杜波.基于Map Reduce的栅格地图切片系统[D].西安:西安电子科技大学,2014.
[8]Battersby S E,Finn M P,Usery E L,et al.Implications of Web Mercator and its use in online mapping[J].Cartographica the International Journal for Geographic Information&Geovisualization,2014,49(2):85-101.
[9]Fran?ula N.Web Mercator projection[J].Geodetski List Glasilo Hrvatskoga Geodetskog Dru?tva,2014(1).
[10]关雷,刘蕾,郭慧宇.基于瓦片技术的高分辨率遥感影像快速访问技术在测绘生产中的应用研究[J].测绘与空间地理信息,2016,39(2):78-79.
[11]李长春,蔡伯根,上官伟,等.基于Web墨卡托投影的地图算法研究与实现[J].计算机应用研究,2012,29(12):4793-4796.
[12]刘世永,吴秋云,陈荦,等.基于高层级地图瓦片的低层级瓦片并行合成技术[J].地理信息世界,2015,22(6):51-55.
[13]刘镇.遥感影像瓦片金字塔模型[J].科技创新导报,2008(6):199-200.
[14]葛亮,何涛,王均辉,等.基于GDAL的瓦片切割技术研究[J].测绘与空间地理信息,2014(7):130-132.