Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.6
3.2
Journals
JMSE
Special Issues
Application of Deep Learning in Underwater Image Processing—2nd Edition
share announcement

Application of Deep Learning in Underwater Image Processing—2nd Edition

A special issue of Journal of Marine Science and Engineering (ISSN 2077-1312). This special issue belongs to the section "Physical Oceanography".

Deadline for manuscript submissions: 20 December 2026 | Viewed by 3722

Editors

Prof. Dr. Chia-Hung Yeh

E-Mail Website
Guest Editor
1. Department of Electrical Engineering, National Taiwan Normal University, Taipei 106, Taiwan
2. Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan
Interests: image/video processing; 3D reconstruction; underwater imaging; video understanding; radar sensing
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Chua-Chin Wang

E-Mail Website
Guest Editor
Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung 80424, Taiwan
Interests: underwater communication chip design and optimization; low-power underwater integrated circuit development; AUV chip design; integrated circuit design
Special Issues, Collections and Topics in MDPI journals
Dr. Guo-Shiang Lin

E-Mail Website
Guest Editor
Department of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung 402, Taiwan
Interests: image/video processing; machine learning; computer vision; multimedia applications
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Underwater image processing is one of the key technologies driving advancements in fields such as marine biology, oceanography, underwater exploration, and many more. Serving as a carrier of information, the quality of underwater images significantly impacts various applications. However, capturing high-quality underwater images is challenging due to complex and uncontrollable conditions. Common issues include color distortion, blurred details, low contrast and brightness, and noise. These problems hinder both human perception and practical applications. Furthermore, the unique properties of underwater imaging, such as its selective light absorption and scattering, make it difficult to achieve satisfactory results with the existing in-air methods or traditional underwater image processing techniques.

In recent years, deep learning technologies have emerged as a game-changer in addressing these challenges and improving underwater image quality. These technologies provide new opportunities and insights, enhancing their applicability and reliability in real-world scenarios. This Special Issue aims to bring together leading researchers and practitioners from around the world to showcase their latest research findings and future directions in this dynamic field. We particularly welcome the submissions responding to the call for proposals on underwater image processing and analysis that leverage advanced deep learning techniques.

The scope of this Special Issue is to cover all aspects that relate to underwater image processing. Topics of interest include, but are not limited to, the following:

  • Underwater image enhancement and restoration;
  • Underwater image denoising;
  • Underwater object detection and classification;
  • Underwater object tracking;
  • Underwater object recognition;
  • Underwater semantic segmentation;
  • Underwater scene understanding;
  • Underwater image depth estimation;
  • Underwater 3D modeling;
  • Underwater image synthesis and generation;
  • Generative AI for underwater image processing;
  • Underwater image quality assessment methods, including full-reference assessment metrics, non-reference assessment metrics, etc.

Prof. Dr. Chia-Hung Yeh
Prof. Dr. Chua-Chin Wang
Dr. Guo-Shiang Lin
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Marine Science and Engineering is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • deep learning
  • machine learning
  • underwater image processing
  • underwater vision
  • underwater drones
  • autonomous underwater vehicles (AUVs)
  • ocean information engineering
  • ocean observation technologies
  • artificial intelligence in the underwater environment

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Related Special Issue

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

22 pages, 14106 KB  
Article
Combining Deep Learning and Ecological Monitoring for BRUV Coral Reef Megafauna Assessment
by Astrid Vinterberg Frandsen, Raja Aditya Sahala Siagian, Cino Pertoldi, Georgia Coward, Filippo Varini, Niels Madsen and Kara Majerus
J. Mar. Sci. Eng. 2026, 14(15), 1409; https://doi.org/10.3390/jmse14151409 - 31 Jul 2026
Viewed by 1127
Abstract
Coral reef ecosystems are increasingly threatened by climate change, pollution, and overfishing, causing major declines in marine megafauna and high-trophic-level fishes. Monitoring these species is vital for conservation, yet traditional survey methods are slow and resource intensive. This study presents a semi-automated monitoring [...] Read more.
Coral reef ecosystems are increasingly threatened by climate change, pollution, and overfishing, causing major declines in marine megafauna and high-trophic-level fishes. Monitoring these species is vital for conservation, yet traditional survey methods are slow and resource intensive. This study presents a semi-automated monitoring pipeline that integrates deep learning (DL) with human-in-the-loop validation to streamline Baited Remote Underwater Video (BRUV) analyses in the Gita Nada Marine Protected Area (MPA), Indonesia. A total of 244 BRUV deployments from SORCE’s long-term monitoring program in the Gita Nada MPA, comprising 328 h of footage, collected 2023–2025 under Indonesian research oversight through Yayasan SORCE Konservasi Indonesia, were processed using a DL workflow. To address long-tailed species distributions, focal taxa were grouped into six Morphological Groups and detected using a YOLOv12x model trained via transfer learning from the Community Fish Detector. A custom temporal-tracking framework extracted ecological metrics including N, Time to First Visit (T1st), and Visit Duration (Tvisit). The pipeline achieved moderate to high detection and tracking performance for several Morphological Groups, achieving object detection F1-scores of up to 0.873 and an overall tracker recall and precision of 0.80 and 0.76, respectively, although performance varied substantially among groups and was substantially limited for data-deficient taxa. As a proof-of-concept, we applied the framework to assess ecological shifts in Cheloniidae and Carangidae across coral-cover gradients. Overall, this semi-automated approach reduces BRUV processing effort and provides a scalable foundation for generating the large datasets needed to detect subtle ecological change. Full article
(This article belongs to the Special Issue Application of Deep Learning in Underwater Image Processing—2nd Edition)
►▼ Show Figures

Figure 1

17 pages, 12666 KB  
Article
Efficient Underwater Image Super-Resolution via Learnable Color Conversion and Dual-Branch Mamba Network
by Yu-Yang Lin, Wan-Jen Huang, Chia-Hung Yeh, Yi-Shiuan Yang and Chua-Chin Wang
J. Mar. Sci. Eng. 2026, 14(13), 1210; https://doi.org/10.3390/jmse14131210 - 30 Jun 2026
Viewed by 344
Abstract
Underwater image super-resolution plays an important role in marine exploration, as it aims to recover clearer and higher-resolution images from degraded low-resolution observations. However, in underwater environments, this task is particularly challenging due to non-uniform spectral attenuation and particle scattering. Underwater, red light [...] Read more.
Underwater image super-resolution plays an important role in marine exploration, as it aims to recover clearer and higher-resolution images from degraded low-resolution observations. However, in underwater environments, this task is particularly challenging due to non-uniform spectral attenuation and particle scattering. Underwater, red light fades quickly, leading to color distortion and loss of details. To address this while keeping the model lightweight, we propose a dynamic color-space network for single-image super-resolution. Traditional methods use fixed color conversion and cannot handle non-uniform attenuation well. We instead use a learnable module to adaptively obtain luminance (Y) and chrominance (CbCr) representations. Building upon this representation, we employ a highly efficient dual-branch architecture where the Y-channel features are processed using light Mamba blocks to capture spatial dependencies with linear complexity, while the CbCr-channel features are restored by a lightweight convolutional neural network. Finally, a lightweight residual model utilizing depth-wise separable convolutions (DSC), deformable convolutions, and pixel attention mechanisms is introduced to refine the features and suppress artifacts. Experimental results demonstrate that while achieving competitive restoration quality, the proposed method drastically reduces computational complexity and parameter count compared to other large-scale models. This balance between visual quality and computational efficiency makes the proposed method well-suited for real-time deployment on resource-constrained autonomous underwater vehicles (AUVs). Full article
(This article belongs to the Special Issue Application of Deep Learning in Underwater Image Processing—2nd Edition)
►▼ Show Figures

Figure 1

30 pages, 17700 KB  
Article
Cross-Expedition Domain Adaptation for Polymetallic Nodule Detection: A Multi-Model Pseudo-Labelling Approach
by Gabriel Loureiro, André Dias and Eduardo Silva
J. Mar. Sci. Eng. 2026, 14(11), 1048; https://doi.org/10.3390/jmse14111048 - 3 Jun 2026
Viewed by 449
Abstract
The automated detection of deep-sea polymetallic nodules is critical for processing large volumes of benthic imagery. However, its scalability faces challenges from cross-expedition covariate shifts, such as changes in lighting, altitude, and camera payloads, which lower zero-shot model performance. While semi-supervised pseudo-labelling presents [...] Read more.
The automated detection of deep-sea polymetallic nodules is critical for processing large volumes of benthic imagery. However, its scalability faces challenges from cross-expedition covariate shifts, such as changes in lighting, altitude, and camera payloads, which lower zero-shot model performance. While semi-supervised pseudo-labelling presents a potential alternative to time-consuming re-annotation, simple implementations can quickly lead to confirmation bias. This study identifies two primary sources of this degradation: spatial noise from tiling fragmentation at tile borders and an architecture-agnostic interior false positive floor caused by semantic domain shift. This work proposes using a multi-model ensemble for pseudo-labelling to reduce the noise impact. Using a spatial border filter and confidence stratification, three architecturally distinct teacher models (YOLOv8, Faster R-CNN, and DINO) are employed to determine a reliable and domain-invariant subspace. Under a strict anti-leakage Leave-One-Partition-Out protocol, the proposed approach surpasses the supervised fine-tuning baseline at 100-tile pseudo-label budget across four random seeds (macro mAP50:95 of 0.4745±0.0042 versus 0.4467±0.0079), with gains concentrated in the most domain-shifted fold. Beyond this budget, our findings highlight two important adaptation trends: a pool-size degradation trend where excessive pseudo-label volume actively degrades generalisation, and the observation that the fine-tuned models reduce pseudo-label fidelity despite higher precision, providing evidence for the advantage of using frozen source checkpoints for cross-domain adaptation. Full article
(This article belongs to the Special Issue Application of Deep Learning in Underwater Image Processing—2nd Edition)
►▼ Show Figures

Figure 1

23 pages, 5417 KB  
Article
A Method for Underwater Image Enhancement Utilizing Polarization Inspired by the Mantis Shrimp’s Multi-Dimensional Visual Imaging Mechanism
by Qingyu Liu, Ruixin Li, Congcong Li, Canrong Chen, Yifan Huang, Huayu Yang and Fei Yuan
J. Mar. Sci. Eng. 2026, 14(6), 582; https://doi.org/10.3390/jmse14060582 - 21 Mar 2026
Cited by 1 | Viewed by 964
Abstract
Optical attenuation caused by absorption and scattering in turbid water significantly degrades underwater image quality, making reliable underwater imaging a challenging problem. Underwater polarization imaging has attracted increasing attention because of its ability to suppress scattered light and provide additional polarization cues. However, [...] Read more.
Optical attenuation caused by absorption and scattering in turbid water significantly degrades underwater image quality, making reliable underwater imaging a challenging problem. Underwater polarization imaging has attracted increasing attention because of its ability to suppress scattered light and provide additional polarization cues. However, existing polarization-based enhancement approaches often adapt conventional underwater image enhancement strategies, and the multi-dimensional characteristics of polarization information are not always fully utilized, which may limit detail restoration in complex underwater environments. To address this issue, this paper proposes a bio-inspired underwater polarization image enhancement framework motivated by the polarization vision mechanism of marine organisms. Specifically, a two-stage architecture consisting of a Polarization Adversarial Network (PAN) and a Polarization Enhancement Network (PEN) is designed. The PAN incorporates a Bionic Antagonistic Module (BAM) to exploit complementary information among polarization channels, while Salient Feature Extraction (SFE) is introduced to reduce redundant feature interference. The subsequent PEN integrates a frequency-aware Mamba-based structure to enhance feature representation and improve detail reconstruction. Experiments on simulated underwater polarization datasets indicate that the proposed framework can effectively suppress backscattering and improve structural detail visibility in challenging underwater scenes, demonstrating competitive performance compared with representative traditional and learning-based methods. Full article
(This article belongs to the Special Issue Application of Deep Learning in Underwater Image Processing—2nd Edition)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop