Machine-Learned 3D Building Vectorization from Satellite Imagery

Abstract

We propose a machine learning based approach for automatic 3D building reconstruction and vectorization. Taking a single-channel photogrammetric digital surface model (DSM) and a panchromatic (PAN) image as input, we first filter out non-building objects and refine the building shapes of the 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 refined DSM is processed and 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.

Cite

Text

Wang et al. "Machine-Learned 3D Building Vectorization from Satellite Imagery." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00118

Markdown

[Wang et al. "Machine-Learned 3D Building Vectorization from Satellite Imagery." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/wang2021cvprw-machinelearned/) doi:10.1109/CVPRW53098.2021.00118

BibTeX

@inproceedings{wang2021cvprw-machinelearned,
  title     = {{Machine-Learned 3D Building Vectorization from Satellite Imagery}},
  author    = {Wang, Yi and Zorzi, Stefano and Bittner, Ksenia},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {1072-1081},
  doi       = {10.1109/CVPRW53098.2021.00118},
  url       = {https://mlanthology.org/cvprw/2021/wang2021cvprw-machinelearned/}
}