Opto-Electronic Engineering, Volume. 50, Issue 6, 230017(2023)
Sonar image denoising method based on residual and attention network
Figures & Tables(11)
Fig. 4. Simulated forward-looking sonar images. (a) Original image; (b) Noisy image
Fig. 5. Simulated forward-looking sonar image denoising results. (a) (b) (c) Represents three different images
Fig. 6. Real forward-looking sonar image denoising results. (a) (b) (c) Represents three different images
Table 1. simulated sonar image denoising results
View tableView in ArticleTable 1. simulated sonar image denoising results
方法 PSNR SSIM Brisque BM3D[ 10 ]29.84 0.7693 104.18 DnCNN[ 13 ]34.25 0.8168 95.27 CBDNet[ 27 ]34.66 0.7852 98.82 CNCL[ 36 ]34.54 0.7817 94.68 DeamNet[ 37 ]35.57 0.7751 95.70 本文 36.54 0.8450 91.13
Table 2. Real sonar image denoising evaluation index results
View tableView in ArticleTable 2. Real sonar image denoising evaluation index results
方法 Brisque BM3D[ 10 ]53.81 DnCNN[ 13 ]43.57 CBDNet[ 27 ]42.58 CNCL[ 36 ]45.27 DeamNet[ 37 ]47.21 本文 40.28
Table 3. Comparison of different attention mechanisms
View tableView in ArticleTable 3. Comparison of different attention mechanisms
模型 模拟数据集 真实数据集 PSNR SSIM Brisque Brisque 单路注意力 35.68 0.8276 94.19 41.61 DCA 36.54 0.8450 91.13 40.28
Table 4. Comparison of different residual block
View tableView in ArticleTable 4. Comparison of different residual block
模型 模拟数据集 真实数据集 PSNR SSIM Brisque Brisque 普通残差块 35.98 0.8367 95.26 41.34 DIR 36.54 0.8450 91.13 40.28
Table 5. Comparison of ablation results
View tableView in ArticleTable 5. Comparison of ablation results
方法 模拟数据集 真实数据集 PSNR SSIM Brisque Brisque CBDNet 34.66 0.7852 98.82 42.58 CBDNet+DCA 35.87 0.7961 97.48 41.89 CBDNet+DIR 35.43 0.8257 98.31 42.04 CNCL 34.54 0.7817 94.68 45.27 CNCL+DCA 34.84 0.7746 94.42 44.35 CNCL+DIR 35.02 0.7993 92.88 43.79 本文 36.54 0.8450 91.13 40.28
Tools
Get Citation
Copy Citation Text
Dongdong Zhao, Yifei Ye, Peng Chen, Ronghua Liang, Tiancheng Cai, Xinxin Guo. Sonar image denoising method based on residual and attention network[J]. Opto-Electronic Engineering, 2023, 50(6): 230017
Paper Information
Category: Article
Received: Jan. 20, 2023
Accepted: Apr. 11, 2023
Published Online: Aug. 9, 2023
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20