Three-Dimensional Building Reconstruction Using Images Obtained by Unmanned Aerial Vehicles
Three-Dimensional Building Reconstruction Using Images Obtained by Unmanned Aerial Vehicles
复制标题
利用无人机获得的图像进行三维建筑重建
DOI：
10.5194/isprsarchives-xxxviii-1-c22-183-2011
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
O. Hellwich
中科院分区：
文献类型：
--
作者：
Cornelius Wefelscheid;R. Hänsch;O. Hellwich
无人机 (UAV) 在广泛的应用中提供了多种新的可能性。建筑物的 3D 重建就是一个例子。在以前，这要么受到地面车辆的限制，无法重建立面，要么受到机载传感器的限制，只能生成非常粗糙的建筑模型。本文描述了一种使用无人机对建筑物进行全自动基于图像的 3D 重建的方法。无人机能够观察整个 3D 场景并从完全不同的角度捕获感兴趣物体的图像。这项工作使用的平台是 Ascending Technologies 的 Falcon 8 八轴飞行器。经过稍微修改的高分辨率消费级相机可用作数据采集的传感器。最终的 3D 重建是在图像采集后离线计算的，并遵循最初为地球车辆获得的图像序列开发的重建过程。在基准数据集上对所描述方法的性能进行了评估，结果表明所达到的精度很高，甚至可以与光探测和测距（LIDAR）相媲美。此外，还介绍并讨论了从图像采集开始到密集表面网格结束的完整处理链的应用结果。
Unmanned Aerial Vehicles (UAVs) offer several new possibilities in a wide range of applications. One example is the 3D reconstruction of buildings. In former times this was either restricted by earthbound vehicles to the reconstruction of facades or by air-borne sensors to generate only very coarse building models. This paper describes an approach for fully automatic image-based 3D reconstruction of buildings using UAVs. UAVs are able to observe the whole 3D scene and to capture images of the object of interest from completely different perspectives. The platform used by this work is a Falcon 8 octocopter from Ascending Technologies. A slightly modified high-resolution consumer camera serves as sensor for data acquisition. The final 3D reconstruction is computed offline after image acquisition and follows a reconstruction process originally developed for image sequences obtained by earthbound vehicles. The per- formance of the described method is evaluated on benchmark datasets showing that the achieved accuracy is high and even comparable with Light Detection and Ranging (LIDAR). Additionally, the results of the application of the complete processing-chain starting at image acquisition and ending in a dense surface-mesh are presented and discussed.