基于海量点云数据的大雁塔三维重建

Three dimensional reconstruction of the Great Wild Goose Pagoda based on massive point cloud data

古建筑三维重建已成为历史遗迹保护与修复的重要内容。为了探讨三维激光扫描数据的获取流程、数据处理方法,以三维激光扫描获取的大雁塔海量点云数据为例,研究了古建筑三维重建中点云数据获取与处理的详细过程。联合Cyclone、AutoCAD和3D-Max软件的优点构建了大雁塔真实的横面、剖面、立面模型,其中重点研究了海量点云数据在Cyclone软件中分块建模的方法。结果表明:将拼接好的大雁塔海量点云数据分块建模,不仅加快了数据处理的速度,而且符合精度要求。在点云数据拼接时采用标靶拼接和同名点拼接相结合及测站间两两拼接之后再整体拟合平差的方法,减少了拼接中的误差,使每站拼接误差都不超过3cm。在建模过程中的墙体拟合是上万个点云经过平差计算得到,精度高达2mm。最后在3D-Max软件中组合、渲染和贴图,真实地构建了大雁塔三维立体模型。为古建筑数字化存档和后期的修缮工作提供了重要的依据。

3D reconstruction of ancient buildings has become an important aspect of the protection and restoration of historic sites. Three - dimensional laser scanning data of the Great Wild Goose Pagoda was taken as an example in order to study in detail the process of obtaining and processing point cloud data for the 3D reconstruction of ancient buildings. The advantages of Cyclone, AutoCAD and 3D - Max software to build a real horizontal, profile and vertical section model of the Great Wild Goose Pagoda were combined. The method of block modeling of mas-sive point cloud data in Cyclone was briefly studied. This study showed that block modeling of spliced mass point cloud data for the Great Wild Goose Pagoda not only accelerated the speed of data processing, but also met accura-cy requirements. The methods of target splicing and corresponding point joining together and the method of each stand splicing between the stations were combined, and then whole fitting adjustment to reduce the error was made. In the end, each station splicing error is no more than 3cm. In the process of modeling, the wall fitting is calculat-ed ,after adjustment of thousands of points, bringing the precision to 2mm. Finally, rendered and textured the mod-el in the 3D - Max software was combined, and a 3D model of the Great Wild Goose Pagoda was constructed. This work provides an important reference for the repair and digital archiving of the ancient architecture.