Frequency-Domain Enhancement Road Extraction Network for Remote Sensing Images
Lists
Only you see this
Abstract
Road extraction from remote sensing (RS) images is inherently challenging due to spatial–spectral dual complexities. Spatial complexity stems from irregular and diverse topological structures and large-scale variations, whereas spectral complexity arises from clouds, shadows, and surface reflections. Existing spatial-domain methods excel at modeling geometric structures but often fail under severe spectral interference, while emerging frequency-domain approaches provide enhanced discriminability yet insufficiently capture road geometry. To fully exploit their complementarity, this letter proposes a frequency-domain enhancement network (FDENet), which improves road discrimination and geometric modeling through spatial-frequency joint design and complementary fusion. First, a convolutional neural network (CNN)–transformer hybrid backbone named TransXNet is adopted to capture rich multiscale spatial features. Then, a frequency enhancement module (FEM) based on strip convolution (SC) is proposed to differentially process wavelet subbands, with large kernels modeling low-frequency geometry and direction-aware (DA) kernels sharpening high-frequency edges. Finally, an adaptive fusion module (AFM) is developed to bridge the spatial-frequency representation gaps through adjusting channel weights of fusion dynamically. Experiments on DeepGlobe and Jilin-1 show that FDENet outperforms six state-of-the-art (SOTA) methods in F1 and IoU with fewer parameters. Code is available at https://github.com/oybk8/FDENet
BibTeX
@article{ouyang2025frequency,
author = {Baokang Ouyang and Fen Xiao and Han Xiang and Xieping Gao and Jie Zhang},
title = {{Frequency-Domain Enhancement Road Extraction Network for Remote Sensing Images}},
journal = {IEEE Geosci. Remote. Sens. Lett.},
year = {2025},
url = {https://openreview.net/forum?id=U1OnNaOQZY},
}Loading related content...