EUVIMEDEUVIMED entdecken
Crossref

SonoLF-ASPPNet: A Low-Frequency Focused Multiscale Network for Speckle Denoising in Forward-Looking Sonar Images

Wenkai Wang, Shuaizheng Yan, Zhaoju Zhu, Bingwei He

IEEE Geoscience and Remote Sensing Letters · 2026 · 23 · 1-5

DOI: 10.1109/lgrs.2026.3673897 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Geoscience and Remote Sensing Letters, 2026. Verfasst von Wenkai Wang und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Two-dimensional forward-looking sonar (FLS) images are often severely degraded by speckle noise, impairing human interpretation and computer vision tasks. Existing denoising methods, including traditional multiplicative noise models and deep learning approaches, suffer from over-suppression of high-frequency information, leading to residual artifacts, incomplete noise removal, and blurred edges. To address these challenges, this letter proposes SonoLF-ASPPNet, a novel sonar image denoising network, along with a new simulated dataset construction method. The network incorporates three key contributions: the low-frequency structure-edge focusing module combines the traditional speckle reducing anisotropic diffusion (SRAD) with a Laplacian kernel to enable simultaneous low-frequency denoising and high-frequency edge preservation; the low-frequency attention module incorporates an atrous spatial pyramid pooling module to enhance contextual awareness and suppress high-frequency interference. The training utilizes a composite loss function to enhance denoising in smooth areas, suppress color spots, and homogenize backgrounds. The experimental results indicate that on the simulated dataset, sono low-frequency atrous spatial pyramid pooling network (SonoLF-ASPPNet) achieved peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values of 27.76 dB and 0.817, respectively, along with excellent visual performance. On the real FLS dataset, the model outperformed comparative algorithms in terms of visual outcomes, demonstrating superior noise suppression and texture preservation. Moreover, it attained competitive quantitative scores in equivalent number of looks (ENL), edge preservation index (EPI), and M-score.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, W., Yan, S., Zhu, Z., & He, B. (2026). SonoLF-ASPPNet: A Low-Frequency Focused Multiscale Network for Speckle Denoising in Forward-Looking Sonar Images. IEEE Geoscience and Remote Sensing Letters, 23, 1-5. https://doi.org/10.1109/lgrs.2026.3673897

Vancouver

Wang W, Yan S, Zhu Z, He B. SonoLF-ASPPNet: A Low-Frequency Focused Multiscale Network for Speckle Denoising in Forward-Looking Sonar Images. IEEE Geoscience and Remote Sensing Letters. 2026;23:1-5. doi:10.1109/lgrs.2026.3673897

BibTeX
@article{Wang2026,
  author = {Wang, Wenkai and Yan, Shuaizheng and Zhu, Zhaoju and He, Bingwei},
  title = {SonoLF-ASPPNet: A Low-Frequency Focused Multiscale Network for Speckle Denoising in Forward-Looking Sonar Images},
  journal = {IEEE Geoscience and Remote Sensing Letters},
  year = {2026},
  volume = {23},
  pages = {1--5},
  doi = {10.1109/lgrs.2026.3673897}
}
Kostenlos starten →