EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Graph Neural Reasoning for Semantic Understanding of Traffic Signs in Intelligent Transportation Systems

Zongcheng Zuo, Mengjia Liu, Yutong Yan, Yi Lu, Zhuoyue Ma, Yichao Ma

Applied System Innovation · 31.10.2026 · 9 (11) · 233

DOI: 10.3390/asi9110233 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied System Innovation, online erschienen am 31.10.2026. Verfasst von Zongcheng Zuo und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Jiao Tong University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the domain of intelligent transportation systems, interpreting informative traffic signs requires more than recognizing isolated objects. Our study is dedicated to Traffic Sign Semantic Understanding (TSSU), with the goal of examining diverse traffic signs and producing structured semantic descriptions. To accomplish this, we propose an integrated hybrid framework encompassing element identification, content inference, and semantic description generation. The first module detects text, symbols, and arrowheads. The second module uses an Edge-weighted Graph Attention Mechanism (EGAT) to jointly refine node and edge representations, infer component relations, and incorporate local and global layout information. The final module organizes the inferred content into relation groups and generates key–value descriptions using attributes and a dynamic prediction transformer. Experiments on the 5000-image CASIA–Tencent CTSU dataset attain a component F1 of 0.9676, a detection-conditioned relation F1 of 0.9198, and Information Matching F1 of 0.8016. Generation-input ablations show sensitivity to relational information, semantic attributes, and layout input. The framework links visual components and their relations to explicit, structured traffic information.

Förderung

  • Shanghai Jiao Tong University

Zitieren

APA

Zuo, Z., Liu, M., Yan, Y., Lu, Y., Ma, Z., & Ma, Y. (2026). Graph Neural Reasoning for Semantic Understanding of Traffic Signs in Intelligent Transportation Systems. Applied System Innovation, 9(11), 233. https://doi.org/10.3390/asi9110233

Vancouver

Zuo Z, Liu M, Yan Y, Lu Y, Ma Z, Ma Y. Graph Neural Reasoning for Semantic Understanding of Traffic Signs in Intelligent Transportation Systems. Applied System Innovation. 2026;9(11):233. doi:10.3390/asi9110233

BibTeX
@article{Zuo2026,
  author = {Zuo, Zongcheng and Liu, Mengjia and Yan, Yutong and Lu, Yi and Ma, Zhuoyue and Ma, Yichao},
  title = {Graph Neural Reasoning for Semantic Understanding of Traffic Signs in Intelligent Transportation Systems},
  journal = {Applied System Innovation},
  year = {2026},
  volume = {9},
  number = {11},
  pages = {233},
  doi = {10.3390/asi9110233}
}
Kostenlos starten →