跳到主要导航 跳到搜索 跳到主要内容

Frequency-Spatial Dual-Path Modeling for Remote Sensing Image Semantic Segmentation

  • Zhen Wang
  • , Shen Ao Yuan
  • , Jiayuan Li
  • , Ruixiang Li
  • , Nan Xu
  • , Zhuhong You
  • , Deshuang Huang
  • Xijing University
  • Northwestern Polytechnical University Xian
  • Xidian University
  • Hohai University
  • Guangxi Academy of Agricultural Sciences

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Semantic segmentation of remote sensing images (RSIs) faces persistent challenges in high-frequency information degradation, boundary ambiguity, and structural inconsistency. To address these issues, we present a Frequency-Spatial Dual-Path Modeling (FSDPNet) paradigm that achieves holistic structural enhancement and fine-grained detail preservation. Specifically, we introduce a Frequency-Reduction Mamba Mechanism (FRMM), which explicitly disentangles and adaptively retains critical high-frequency and directional representations during encoding. In the decoding stage, a Multi-Scale Frequency-Driven Reconstruction Module (MFRM) leverages frequency-domain enhancement and dilated convolutions for progressive resolution recovery and precise texture compensation. Furthermore, a SAM (Segment Anything Model)-constrained Semantic Consistency Fusion Module (SCFM) harnesses structural priors to reinforce boundary delineation and suppress semantic ambiguity across scales. The overall training is guided by a composite objective that jointly optimizes global semantic consistency and local structural fidelity. Extensive experiments on multiple remote sensing benchmarks demonstrate that our approach consistently outperforms state-of-the-art segmentation methods, setting a new standard for structural integrity and fine-detail preservation in remote sensing image segmentation.

学术指纹

探究 'Frequency-Spatial Dual-Path Modeling for Remote Sensing Image Semantic Segmentation' 的科研主题。它们共同构成独一无二的学术指纹。

引用此