EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

U-Net-Based Model Design for Semantic Segmentation of Class-Imbalanced Semi-Synthetic Roads

Artur Morys-Magiera, Marek Długosz, Paweł Skruch

Electronics · 09.05.2026 · 15 (10) · 2008

DOI: 10.3390/electronics15102008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 09.05.2026. Verfasst von Artur Morys-Magiera und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate semantic segmentation of roads and overlaid markings is essential for multi-camera multi-robot visual localization systems, yet lane markings occupy a tiny fraction of the image area, making them difficult to segment reliably. This paper presents a U-Net design study for semantic segmentation of imbalanced segmentation of a dominant class and two similar, minority classes, that occur on top of the dominant class. We analyze the problem of designing a multi-head U-Net for segmenting semi-synthetic Duckietown model road map images into roads, stop-line markings, and lane-line markings. The multi-head design decomposes the task into a binary road segmentation head and a ternary marking segmentation head, connected through a road-aware loss that restricts marking supervision to predicted road regions. Our work assesses the nine loss functions to approach the class imbalance problem in the marking head—including cross-entropy, focal loss, Tversky loss, Lovász-softmax, and a subset of combinations thereof. These configurations are systematically evaluated on a dataset of semi-synthetic map images generated using an evolutionary algorithm described in a previous work of the authors, where road marking classes are a minority. The Tversky–Lovász combination achieves the highest per-class IoU across all segmentation targets, being statistically significantly better than other configurations. The results demonstrate that the Tversky loss combined with a direct IoU surrogate, Lovász-softmax, is particularly effective for small-object segmentation under severe class imbalance.

Förderung

  • European Council

Zitieren

APA

Morys-Magiera, A., Długosz, M., & Skruch, P. (2026). U-Net-Based Model Design for Semantic Segmentation of Class-Imbalanced Semi-Synthetic Roads. Electronics, 15(10), 2008. https://doi.org/10.3390/electronics15102008

Vancouver

Morys-Magiera A, Długosz M, Skruch P. U-Net-Based Model Design for Semantic Segmentation of Class-Imbalanced Semi-Synthetic Roads. Electronics. 2026;15(10):2008. doi:10.3390/electronics15102008

BibTeX
@article{MorysMagiera2026,
  author = {Morys-Magiera, Artur and Długosz, Marek and Skruch, Paweł},
  title = {U-Net-Based Model Design for Semantic Segmentation of Class-Imbalanced Semi-Synthetic Roads},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {10},
  pages = {2008},
  doi = {10.3390/electronics15102008}
}
Kostenlos starten →