Vectorizing planar roof structure from very high resolution remote sensing images using transformers

Wufan Zhao, Claudio Persello, Xianwei Lv*, Alfred Stein, Maarten Vergauwen

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

32 Downloads (Pure)

Abstract

Accurately predicting the geometric structure of a building's roof as a vectorized representation from a raster image is a challenging task in building reconstruction. In this paper, we propose an efficient and precise parsing method called Roof-Former, based on a vision Transformer. Our method involves three steps: (1) Image encoder and edge node initialization, (2) Image feature fusion with an enhanced segmentation refinement branch, and (3) Edge filtering and structural reasoning. Our method outperforms previous works on the vectorizing world building dataset and the Enschede dataset, with vertex and edge heat map F1-scores increasing from (Formula presented.), (Formula presented.) to (Formula presented.), (Formula presented.), and from (Formula presented.), (Formula presented.) to (Formula presented.), (Formula presented.), respectively. Furthermore, our method demonstrates superior performance compared to the current state-of-the-art based on qualitative evaluations, indicating its effectiveness in extracting global image information while maintaining the consistency and topological validity of the roof structure.

Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalInternational journal of digital earth
Volume17
Issue number1
DOIs
Publication statusPublished - 2024

Keywords

  • geometry reconstruction
  • Roof structure extraction
  • Transformer
  • very high resolution remote sensing
  • ITC-GOLD
  • ITC-ISI-JOURNAL-ARTICLE

Fingerprint

Dive into the research topics of 'Vectorizing planar roof structure from very high resolution remote sensing images using transformers'. Together they form a unique fingerprint.

Cite this