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

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.

@article{Zhao2026,
  title     = {FSCM-Net: Frequency-Spatial Collaborative Modeling for Traffic Scene Semantic Segmentation},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {7},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Wei Zhao and Yi Dong and Lingchao Wang and Qiang Ai},
  doi       = {10.14569/IJACSA.2026.0170769},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170769}
}