Automatic 3D-reconstruction of buildings using highly resolving video sequences

我们提出了一个完全自动化的原型系统，用于使用地面图像数据来改进城市3D GIS的建筑模型。数字视频序列包含了一个高潜力的摄影测量应用，目前还没有充分利用。射影几何提供了一个有效的数学框架，以获得几何精确的信息，从部分校准相机与不同的参数。目前，该方法正在与对象重构方法相结合，以提高其自动化性能。主要的新颖之处在于空间和时间图像匹配以及几何和反射信息的密集集成。摄影测量模型部分地从三焦相机系统的相邻图像重建，部分地从视频序列的前后图像重建。观察到的建筑由平面、多面体和自由形成的表面组成。我们使用曲面组合的通用模型和特定的场景约束来提取、对齐和分类多边形原语。此外，知识驱动的对象提取用于支持图像方向，并可能取代控制信息。该方法是为离线处理录制的数字视频而设计的，因为处理手持无标记视频流的计算需求超过了当今实时系统的能力。我们希望开发一个数学上同质的框架，将摄影测量模型生成、时间跟踪、反射率分析以及目标提取和分类结合起来。这种从几个三焦点视图生成的系统模型使数字视频系统发挥了全部潜力。

We propose a fully automated prototype system to refine building models of an urban 3D GIS using terrestrial image data. Digital video sequences contain a high potential for such photogrammetric applications which is presently not fully used. Projective geometry provides an effective mathematical framework to obtain geometrically precise information from partially calibrated cameras with varying parameters. Presently, it is being combined with object reconstruction methods improving its performance in automation. The main novelty is an intensive Integration of spatial and temporal image matching as weil as geometric and reflectance information. The photogrammetric model is partially reconstructed from the neighboring images of a trifocal camera system, partially from the preceding and following images of the video sequence. The observed buildings consist of planes, polyhedrons and freely formed surfaces. We use generic models of surface assemblies together with particular scene constraints to extract, align and classify the polygonal primitives. Additionally, the knowledge-driven object extraction is used to support the Image orientation and probably to replace control information. The approach is designed for off-line processing of recorded digital video, because the computational requirements to deal with hand-held markerless video streams exceed the capabilities of today real-time systems. We want to develop a mathematically homogeneous framework which incorporates photogrammetric model generation, temporal tracking, and reflectance analysis as weil as object extraction and classification. Such systematic model generation from several trifocal views gives a digital video system its full potential.