We propose a machine learning based approach for automatic 3D building reconstruction and vectorization. Taking a single-channel photogrammetric digital surface model (DSM) and panchromatic (PAN) image as input, we first filter out non-building objects and refine the building shapes of input DSM with a conditional generative adversarial network (cGAN). The refined DSM and the input PAN image are then used through a semantic segmentation network to detect edges and corners of building roofs. Later, a set of vectorization algorithms are proposed to build roof polygons. Finally, the height information from the refined DSM is added to the polygons to obtain a fully vectorized level of detail (LoD)-2 building model. We verify the effectiveness of our method on large-scale satellite images, where we obtain state-of-the-art performance.
翻译:我们提出了自动3D建筑重建与矢量化的机器学习方法。以单通道光度光度数字表面模型(DSM)和全色图像(PAN)作为输入,我们首先过滤非建筑物体,用一个有条件的基因化对抗网络(cGAN)完善输入 DSM的建筑形状,然后通过语义分割网将改良的DSM和输入的PAN图像用于探测建筑物屋顶的边缘和角。随后,提出了一套建造屋顶多边形的矢量算法。最后,将完善的DSM的高度信息添加到多边形中,以获得一个完全矢量的详细度(LoD)-2建筑模型。我们核查了我们在大规模卫星图像上的方法的有效性,我们在那里获得了最先进的性能。