EUVIMEDEUVIMED entdecken
Crossref

FSCM-Net: Frequency-Spatial Collaborative Modeling for Traffic Scene Semantic Segmentation

Wei Zhao, Yi Dong, Lingchao Wang, Qiang Ai

International Journal of Advanced Computer Science and Applications · 2026 · 17 (7)

DOI: 10.14569/ijacsa.2026.0170769 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Computer Science and Applications, 2026. Verfasst von Wei Zhao und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of insufficient global semantic modeling and blurred boundaries in urban traffic scene segmentation, this study proposes a frequency-spatial collaborative framework based on DeepLabV3+. A Spectral Decoupling Adaptive Modulation (SDAM) module enhances low-frequency semantics and high-frequency details in the frequency domain. A Hierarchical Spatial Dependency Modeling (HSDM) module captures local consistency and global semantic dependencies, while a Structure-guided Adaptive Multi-scale Fusion (SAMF) module dynamically integrates multi-scale features using structural priors. Experiments on Cityscapes and CamVid demonstrate improvements of 3.6% and 1.6% over DeepLabV3+, respectively, while maintaining real-time performance.

Zitieren

APA

Zhao, W., Dong, Y., Wang, L., & Ai, Q. (2026). FSCM-Net: Frequency-Spatial Collaborative Modeling for Traffic Scene Semantic Segmentation. International Journal of Advanced Computer Science and Applications, 17(7). https://doi.org/10.14569/ijacsa.2026.0170769

Vancouver

Zhao W, Dong Y, Wang L, Ai Q. FSCM-Net: Frequency-Spatial Collaborative Modeling for Traffic Scene Semantic Segmentation. International Journal of Advanced Computer Science and Applications. 2026;17(7). doi:10.14569/ijacsa.2026.0170769

BibTeX
@article{Zhao2026,
  author = {Zhao, Wei and Dong, Yi and Wang, Lingchao and Ai, Qiang},
  title = {FSCM-Net: Frequency-Spatial Collaborative Modeling for Traffic Scene Semantic Segmentation},
  journal = {International Journal of Advanced Computer Science and Applications},
  year = {2026},
  volume = {17},
  number = {7},
  doi = {10.14569/ijacsa.2026.0170769}
}
Kostenlos starten →