DATNet: Dynamic Adaptive Transformer Network for SAR Image Denoising

Aiming at the problems of detail blurring and structural distortion caused by speckle noise, additive white noise and hybrid noise interference in synthetic aperture radar (SAR) images, this paper proposes a Dynamic Adaptive Transformer Network (DAT-Net) integrating a dynamic gated attention module...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Remote sensing (Basel, Switzerland) Jg. 17; H. 17; S. 3031
Hauptverfasser: Shen, Yan, Chen, Yazhou, Wang, Yuming, Ma, Liyun, Zhang, Xiaolu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.09.2025
Schlagworte:
Artificial satellites in remote sensing
attention encoder–decoder network
Design
Efficiency
Electric transformers
Embedding
Feature extraction
Fourier transforms
Frequency dependence
Frequency domain analysis
Heterogeneity
image denoising
Innovations
Learning strategies
Medical imaging equipment
Methods
Modules
Noise
Noise reduction
Parameter estimation
Radar imaging
Spatial heterogeneity
Synthetic aperture radar
Transformer
Wavelet transforms
White noise
ISSN:2072-4292, 2072-4292
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Aiming at the problems of detail blurring and structural distortion caused by speckle noise, additive white noise and hybrid noise interference in synthetic aperture radar (SAR) images, this paper proposes a Dynamic Adaptive Transformer Network (DAT-Net) integrating a dynamic gated attention module and a frequency-domain multi-expert enhancement module for SAR image denoising. The proposed model leverages a multi-scale encoder–decoder framework, combining local convolutional feature extraction with global self-attention mechanisms to transcend the limitations of conventional approaches restricted to single noise types, thereby achieving adaptive suppression of multi-source noise contamination. Key innovations comprise the following: (1) A Dynamic Gated Attention Module (DGAM) employing dual-path feature embedding and dynamic thresholding mechanisms to precisely characterize noise spatial heterogeneity; (2) A Frequency-domain Multi-Expert Enhancement (FMEE) Module utilizing Fourier decomposition and expert network ensembles for collaborative optimization of high-frequency and low-frequency components; (3) Lightweight Multi-scale Convolution Blocks (MCB) enhancing cross-scale feature fusion capabilities. Experimental results demonstrate that DAT-Net achieves quantifiable performance enhancement in both simulated and real SAR environments. Compared with other denoising algorithms, the proposed methodology exhibits superior noise suppression across diverse noise scenarios while preserving intrinsic textural features.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2072-4292
2072-4292
DOI:10.3390/rs17173031