EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Discrepancy-Guided Semantic Segmentation with Boundary Detail Enhancement for Traffic Scenes

Changshun Yu, Xiujian Yang iD, Shiquan Shen

Sensors · 28.04.2026 · 26 (9) · 2738

DOI: 10.3390/s26092738 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.04.2026. Verfasst von Changshun Yu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming 650500, China. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Province Science and Technology Department.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of missing fine-grained objects, blurred boundaries, and the suppression of shallow details by deep semantic features during cross-scale fusion in traffic scene semantic segmentation, this paper proposes a discrepancy-guided semantic segmentation method with boundary detail enhancement. First, to improve the semantic completeness of fine-grained regions, a Gated Collaborative Context Module (GCCM) is introduced between the encoder and decoder. By leveraging gating-guided channel selection and multi-scale contextual modeling, GCCM adaptively captures semantic dependencies across different scales. Second, to alleviate boundary ambiguity and detail loss, a Frequency–Edge Guided Enhancement Module (FEGE) is designed in the decoder. This module explicitly models low-frequency structural information and high-frequency edge components via frequency decomposition, and further enhances high-frequency details using the Scharr operator and lightweight convolution, thereby improving the structural representation of object contours and boundary regions. Furthermore, to mitigate the suppression of shallow details during cross-scale feature fusion, a Discrepancy-aware Pixel-Adaptive Gating Fusion module (D-PagFM) is proposed. By jointly modeling feature similarity and local discrepancy, the module adaptively regulates pixel-wise fusion, enhancing detail integration in structurally consistent regions while suppressing misleading fusion in inconsistent regions, thereby improving the robustness of feature fusion and boundary consistency. Experimental results on the Cityscapes and CamVid datasets demonstrate that the proposed method achieves mIoU scores of 80.08% and 82.97%, respectively. Moreover, it shows more significant improvements in boundary-sensitive fine-grained categories such as road boundaries, poles, and traffic signs, indicating its effectiveness and application potential for high-precision semantic segmentation in traffic scenes.

Schlagwörter

Stichwörter der Autor:innen

boundary detail enhancementdeep learningdiscrepancy-aware fusionsemantic segmentationtraffic scene understanding

Autor:innen und Institutionen

  • Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming 650500, China.
  • Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China.

ORCID-Profile: Xiujian Yang

Förderung

  • Yunnan Province Science and Technology Department

Zitieren

APA

Yu, C., Yang, X., & Shen, S. (2026). Discrepancy-Guided Semantic Segmentation with Boundary Detail Enhancement for Traffic Scenes. Sensors, 26(9), 2738. https://doi.org/10.3390/s26092738

Vancouver

Yu C, Yang X, Shen S. Discrepancy-Guided Semantic Segmentation with Boundary Detail Enhancement for Traffic Scenes. Sensors. 2026;26(9):2738. doi:10.3390/s26092738

BibTeX
@article{Yu2026,
  author = {Yu, Changshun and Yang, Xiujian and Shen, Shiquan},
  title = {Discrepancy-Guided Semantic Segmentation with Boundary Detail Enhancement for Traffic Scenes},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2738},
  doi = {10.3390/s26092738}
}
Kostenlos starten →