PWFNet: Pyramidal Wavelet–Frequency Attention Network for Road Extraction
Furkejuvvon:
| Publikašuvnnas: | Remote Sensing vol. 17, no. 16 (2025), p. 2895-2920 |
|---|---|
| Váldodahkki: | |
| Eará dahkkit: | , , , , |
| Almmustuhtton: |
MDPI AG
|
| Fáttát: | |
| Liŋkkat: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Fáddágilkorat: |
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3244060246 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2072-4292 | ||
| 024 | 7 | |a 10.3390/rs17162895 |2 doi | |
| 035 | |a 3244060246 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231556 |2 nlm | ||
| 100 | 1 | |a Zong Jinkun |u Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China; 2230902168@cnu.edu.cn (J.Z.); 2230902115@cnu.edu.cn (R.W.); 2240902114@cnu.edu.cn (D.X.); 2240902168@cnu.edu.cn (X.Y.) | |
| 245 | 1 | |a PWFNet: Pyramidal Wavelet–Frequency Attention Network for Road Extraction | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Road extraction from remote sensing imagery plays a critical role in applications such as autonomous driving, urban planning, and infrastructure development. Although deep learning methods have achieved notable progress, current approaches still struggle with complex backgrounds, varying road widths, and strong texture interference, often leading to fragmented road predictions or the misclassification of background regions. Given that roads typically exhibit smooth low-frequency characteristics while background clutter tends to manifest in mid- and high-frequency ranges, incorporating frequency-domain information can enhance the model’s structural perception and discrimination capabilities. To address these challenges, we propose a novel frequency-aware road extraction network, termed PWFNet, which combines frequency-domain modeling with multi-scale feature enhancement. PWFNet comprises two key modules. First, the Pyramidal Wavelet Convolution (PWC) module employs multi-scale wavelet decomposition fused with localized convolution to accurately capture road structures across various spatial resolutions. Second, the Frequency-aware Adjustment Module (FAM) partitions the Fourier spectrum into multiple frequency bands and incorporates a spatial attention mechanism to strengthen low-frequency road responses while suppressing mid- and high-frequency background noise. By integrating complementary modeling from both spatial and frequency domains, PWFNet significantly improves road continuity, edge clarity, and robustness under complex conditions. Experiments on the DeepGlobe and CHN6-CUG road datasets demonstrate that PWFNet achieves IoU improvements of 3.8% and 1.25% over the best-performing baseline methods, respectively. In addition, we conducted cross-region transfer experiments by directly applying the trained model to remote sensing images from different geographic regions and at varying resolutions to assess its generalization capability. The results demonstrate that PWFNet maintains the continuity of main and branch roads and preserves edge details in these transfer scenarios, effectively reducing false positives and missed detections. This further validates its practicality and robustness in diverse real-world environments. | |
| 653 | |a Accuracy | ||
| 653 | |a Deep learning | ||
| 653 | |a Urban planning | ||
| 653 | |a Wavelet transforms | ||
| 653 | |a Modelling | ||
| 653 | |a Convolution | ||
| 653 | |a Roads & highways | ||
| 653 | |a Remote sensing | ||
| 653 | |a Frequency ranges | ||
| 653 | |a Decomposition | ||
| 653 | |a Attention | ||
| 653 | |a Frequencies | ||
| 653 | |a Architecture | ||
| 653 | |a Modules | ||
| 653 | |a Frequency dependence | ||
| 653 | |a Robustness | ||
| 653 | |a Background noise | ||
| 653 | |a Machine learning | ||
| 653 | |a Vegetation | ||
| 653 | |a Fourier transforms | ||
| 653 | |a Frequency domain analysis | ||
| 653 | |a Connectivity | ||
| 653 | |a Clutter | ||
| 653 | |a Morphology | ||
| 700 | 1 | |a Sun, Yonghua |u Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China; 2230902168@cnu.edu.cn (J.Z.); 2230902115@cnu.edu.cn (R.W.); 2240902114@cnu.edu.cn (D.X.); 2240902168@cnu.edu.cn (X.Y.) | |
| 700 | 1 | |a Wang Ruozeng |u Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China; 2230902168@cnu.edu.cn (J.Z.); 2230902115@cnu.edu.cn (R.W.); 2240902114@cnu.edu.cn (D.X.); 2240902168@cnu.edu.cn (X.Y.) | |
| 700 | 1 | |a Xu Dinglin |u Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China; 2230902168@cnu.edu.cn (J.Z.); 2230902115@cnu.edu.cn (R.W.); 2240902114@cnu.edu.cn (D.X.); 2240902168@cnu.edu.cn (X.Y.) | |
| 700 | 1 | |a Yang, Xue |u Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China; 2230902168@cnu.edu.cn (J.Z.); 2230902115@cnu.edu.cn (R.W.); 2240902114@cnu.edu.cn (D.X.); 2240902168@cnu.edu.cn (X.Y.) | |
| 700 | 1 | |a Zhao, Xiaolin |u CCCC Xingyu Technology Co., Ltd., Beijing 102200, China; zhaoxiaolin@ccccltd.cn | |
| 773 | 0 | |t Remote Sensing |g vol. 17, no. 16 (2025), p. 2895-2920 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3244060246/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3244060246/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3244060246/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |