SUM: A benchmark dataset of Semantic Urban Meshes

Weixiao Gao*, Liangliang Nan, Bas Boom, Hugo Ledoux

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)
42 Downloads (Pure)

Abstract

Recent developments in data acquisition technology allow us to collect 3D texture meshes quickly. Those can help us understand and analyse the urban environment, and as a consequence are useful for several applications like spatial analysis and urban planning. Semantic segmentation of texture meshes through deep learning methods can enhance this understanding, but it requires a lot of labelled data. The contributions of this work are three-fold: (1) a new benchmark dataset of semantic urban meshes, (2) a novel semi-automatic annotation framework, and (3) an annotation tool for 3D meshes. In particular, our dataset covers about 4 km2 in Helsinki (Finland), with six classes, and we estimate that we save about 600 h of labelling work using our annotation framework, which includes initial segmentation and interactive refinement. We also compare the performance of several state-of-the-art 3D semantic segmentation methods on the new benchmark dataset. Other researchers can use our results to train their networks: the dataset is publicly available, and the annotation tool is released as open-source.

Original languageEnglish
Pages (from-to)108-120
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume179
DOIs
Publication statusPublished - 2021

Keywords

  • Benchmark dataset
  • Mesh annotation
  • Over-segmentation
  • Semantic segmentation
  • Texture meshes
  • Urban scene understanding

Fingerprint

Dive into the research topics of 'SUM: A benchmark dataset of Semantic Urban Meshes'. Together they form a unique fingerprint.

Cite this