EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TransitNet: A lightweight semantic segmentation network for urban traffic scene understanding

Haiyan Zhang iD, Zining Zhao, Xiang Chu, Yilin Liu

PLOS One · 22.05.2026 · 21 (5) · e0348843

DOI: 10.1371/journal.pone.0348843 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 22.05.2026. Verfasst von Haiyan Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Huaiyin Institute of Technology, Huaian, China. Hauptthemen laut MEDLINE: Semantics, Neural Networks, Computer. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing semantic segmentation networks often suffer from large parameter sizes and high computational complexity, making it difficult to deploy them on resource-constrained in-vehicle systems or edge devices. Additionally, these networks lack sufficient cross-domain adaptability, limiting their performance across diverse scenarios such as traffic and remote sensing. To address these issues, this paper proposes a lightweight semantic segmentation network, TransitNet, with enhanced Cross-Domain Adaptation capability. Based on the PSPNet architecture, TransitNet introduces a Rectangular Context Calibration Attention (RCCA) module to adaptively model the long-range spatial dependencies of road structures and traffic flow distributions. It also incorporates a Bidirectional Fusion Attention (BFA) module to enhance hierarchical feature interaction, thereby preserving fine-grained details. Furthermore, StarNet is adopted as the novel backbone network, leveraging star-shaped operations and depthwise separable convolutions to reduce model parameters. By improving the forward propagation mechanism, it outputs low-level spatial features and upsampled high-level features to support multi-scale feature fusion. Experiments demonstrate that TransitNet achieves an mIoU of 86.98% on the VOC2012 dataset, outperforming PSPNet by 1.58%. On the LoveAD remote sensing dataset, it achieves an mIoU of 61.04%, surpassing CM-UNet by 8.87%. Additionally, TransitNet achieves an mIoU of 76.11% on the OST300 dataset, further verifying its strong generalization and Cross-Domain Adaptation capabilities. By balancing efficiency and accuracy, TransitNet provides a high-performance semantic segmentation solution for real-time environmental perception in autonomous driving systems. It also holds significant potential for applications in fine classification of roads and buildings in remote sensing imagery. The code is available at https://github.com/Eric-863/TransitNet .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SemanticsNeural Networks, ComputerAlgorithmsHumans

Autor:innen und Institutionen

  • Huaiyin Institute of Technology, Huaian, China.

ORCID-Profile: Haiyan Zhang

Zitieren

APA

Zhang, H., Zhao, Z., Chu, X., & Liu, Y. (2026). TransitNet: A lightweight semantic segmentation network for urban traffic scene understanding. PLOS One, 21(5), e0348843. https://doi.org/10.1371/journal.pone.0348843

Vancouver

Zhang H, Zhao Z, Chu X, Liu Y. TransitNet: A lightweight semantic segmentation network for urban traffic scene understanding. PLOS One. 2026;21(5):e0348843. doi:10.1371/journal.pone.0348843

BibTeX
@article{Zhang2026,
  author = {Zhang, Haiyan and Zhao, Zining and Chu, Xiang and Liu, Yilin},
  title = {TransitNet: A lightweight semantic segmentation network for urban traffic scene understanding},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0348843},
  doi = {10.1371/journal.pone.0348843}
}
Kostenlos starten →