SIGAN: A Multi-Scale Generative Adversarial Network for Underwater Sonar Image Super-Resolution
Open Access
- 24 June 2024
- journal article
- research article
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (7) , 1057
Abstract
Super-resolution (SR) is a technique that restores image details based on existing information, enhancing the resolution of images to prevent quality degradation. Despite significant achievements in deep-learning-based SR models, their application in underwater sonar scenarios is limited due to the lack of underwater sonar datasets and the difficulty in recovering texture details. To address these challenges, we propose a multi-scale generative adversarial network (SIGAN) for super-resolution reconstruction of underwater sonar images. The generator is built on a residual dense network (RDN), which extracts rich local features through densely connected convolutional layers. Additionally, a Convolutional Block Attention Module (CBAM) is incorporated to capture detailed texture information by focusing on different scales and channels. The discriminator employs a multi-scale discriminative structure, enhancing the detail perception of both generated and high-resolution (HR) images. Considering the increased noise in super-resolved sonar images, our loss function emphasizes the PSNR metric and incorporates the L2 loss function to improve the quality of the output images. Meanwhile, we constructed a dataset for side-scan sonar experiments (DNASI-I). We compared our method with the current state-of-the-art super-resolution image reconstruction methods on the public dataset KLSG-II and our self-built dataset DNASI-I. The experimental results show that at a scale factor of 4, the average PSNR value of our method was 3.5 higher than that of other methods, and the accuracy of target detection using the super-resolution reconstructed images can be improved to 91.4%. Through subjective qualitative comparison and objective quantitative analysis, we demonstrated the effectiveness and superiority of the proposed SIGAN in the super-resolution reconstruction of side-scan sonar images.Keywords
This publication has 34 references indexed in Scilit:
- A deep recursive multi-scale feature fusion network for image super-resolutionJournal of Visual Communication and Image Representation, 2022
- Underwater Multitarget Tracking With Sonar Images Using Thresholded Sequential Monte Carlo Probability Hypothesis Density AlgorithmIEEE Geoscience and Remote Sensing Letters, 2022
- Side-Scan Sonar Image Segmentation Based on Multi-Channel Fusion Convolution Neural NetworksIEEE Sensors Journal, 2022
- Multi-scale attention network for image super-resolutionJournal of Visual Communication and Image Representation, 2021
- Matching Color Aerial Images and Underwater Sonar Images Using Deep Learning for Underwater LocalizationIEEE Robotics and Automation Letters, 2020
- A Local Region-Based Level Set Method With Markov Random Field for Side-Scan Sonar Image Multi-Level SegmentationIEEE Sensors Journal, 2020
- Underwater Object Classification in Sidescan Sonar Images Using Deep Transfer Learning and Semisynthetic Training DataIEEE Access, 2020
- Multi-Resolution Space-Attended Residual Dense Network for Single Image Super-ResolutionIEEE Access, 2020
- Single image super-resolution reconstruction based on multi-scale feature mapping adversarial networkSignal Processing, 2020
- Learning Low-Level VisionInternational Journal of Computer Vision, 2000