Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and Tracking
Underwater computer vision plays a vital role in ocean research, enabling autonomous navigation, infrastructure inspections, and marine life monitoring. However, the underwater environment presents unique challenges, including color distortion, limited visibility, and dynamic light conditions, which...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10852283/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576738835562496 |
|---|---|
| author | Mahmoud Elmezain Lyes Saad Saoud Atif Sultan Mohamed Heshmat Lakmal Seneviratne Irfan Hussain |
| author_facet | Mahmoud Elmezain Lyes Saad Saoud Atif Sultan Mohamed Heshmat Lakmal Seneviratne Irfan Hussain |
| author_sort | Mahmoud Elmezain |
| collection | DOAJ |
| description | Underwater computer vision plays a vital role in ocean research, enabling autonomous navigation, infrastructure inspections, and marine life monitoring. However, the underwater environment presents unique challenges, including color distortion, limited visibility, and dynamic light conditions, which hinder the performance of traditional image processing methods. Recent advancements in deep learning (DL) have demonstrated remarkable success in overcoming these challenges by enabling robust feature extraction, image enhancement, and object recognition. This review provides a comprehensive analysis of cutting-edge deep learning architectures designed for underwater object detection, segmentation, and tracking. State-of-the-art (SOTA) models, including AGW-YOLOv8, Feature-Adaptive FPN, and Dual-SAM, have shown substantial improvements in addressing occlusions, camouflaging, and small underwater object detection. For tracking tasks, transformer-based models like SiamFCA and FishTrack leverage hierarchical attention mechanisms and convolutional neural networks (CNNs) to achieve high accuracy and robustness in dynamic underwater environments. Beyond optical imaging, this review explores alternative modalities such as sonar, hyperspectral imaging, and event-based vision, which provide complementary data to enhance underwater vision systems. These approaches improve performance under challenging conditions, enabling richer and more informative scene interpretation. Promising future directions are also discussed, emphasizing the need for domain adaptation techniques to improve generalizability, lightweight architectures for real-time performance, and multi-modal data fusion to enhance interpretability and robustness. By critically evaluating current methodologies and highlighting gaps, this review provides insights for advancing underwater computer vision systems to support ocean exploration, ecological conservation, and disaster management. |
| format | Article |
| id | doaj-art-18ecdeff21e44b2dbba904715f284bdf |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-18ecdeff21e44b2dbba904715f284bdf2025-01-31T00:00:51ZengIEEEIEEE Access2169-35362025-01-0113178301786710.1109/ACCESS.2025.353409810852283Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and TrackingMahmoud Elmezain0Lyes Saad Saoud1https://orcid.org/0000-0003-4445-3135Atif Sultan2https://orcid.org/0009-0002-6110-5554Mohamed Heshmat3https://orcid.org/0000-0002-0153-8131Lakmal Seneviratne4Irfan Hussain5https://orcid.org/0000-0003-2759-0306Khalifa University Center for Autonomous and Robotic Systems, Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous and Robotic Systems, Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous and Robotic Systems, Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous and Robotic Systems, Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous and Robotic Systems, Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous and Robotic Systems, Khalifa University, Abu Dhabi, United Arab EmiratesUnderwater computer vision plays a vital role in ocean research, enabling autonomous navigation, infrastructure inspections, and marine life monitoring. However, the underwater environment presents unique challenges, including color distortion, limited visibility, and dynamic light conditions, which hinder the performance of traditional image processing methods. Recent advancements in deep learning (DL) have demonstrated remarkable success in overcoming these challenges by enabling robust feature extraction, image enhancement, and object recognition. This review provides a comprehensive analysis of cutting-edge deep learning architectures designed for underwater object detection, segmentation, and tracking. State-of-the-art (SOTA) models, including AGW-YOLOv8, Feature-Adaptive FPN, and Dual-SAM, have shown substantial improvements in addressing occlusions, camouflaging, and small underwater object detection. For tracking tasks, transformer-based models like SiamFCA and FishTrack leverage hierarchical attention mechanisms and convolutional neural networks (CNNs) to achieve high accuracy and robustness in dynamic underwater environments. Beyond optical imaging, this review explores alternative modalities such as sonar, hyperspectral imaging, and event-based vision, which provide complementary data to enhance underwater vision systems. These approaches improve performance under challenging conditions, enabling richer and more informative scene interpretation. Promising future directions are also discussed, emphasizing the need for domain adaptation techniques to improve generalizability, lightweight architectures for real-time performance, and multi-modal data fusion to enhance interpretability and robustness. By critically evaluating current methodologies and highlighting gaps, this review provides insights for advancing underwater computer vision systems to support ocean exploration, ecological conservation, and disaster management.https://ieeexplore.ieee.org/document/10852283/Underwater computer visiondeep learningunderwater roboticsocean researchunderwater image enhancementobject tracking |
| spellingShingle | Mahmoud Elmezain Lyes Saad Saoud Atif Sultan Mohamed Heshmat Lakmal Seneviratne Irfan Hussain Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and Tracking IEEE Access Underwater computer vision deep learning underwater robotics ocean research underwater image enhancement object tracking |
| title | Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and Tracking |
| title_full | Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and Tracking |
| title_fullStr | Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and Tracking |
| title_full_unstemmed | Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and Tracking |
| title_short | Advancing Underwater Vision: A Survey of Deep Learning Models for Underwater Object Recognition and Tracking |
| title_sort | advancing underwater vision a survey of deep learning models for underwater object recognition and tracking |
| topic | Underwater computer vision deep learning underwater robotics ocean research underwater image enhancement object tracking |
| url | https://ieeexplore.ieee.org/document/10852283/ |
| work_keys_str_mv | AT mahmoudelmezain advancingunderwatervisionasurveyofdeeplearningmodelsforunderwaterobjectrecognitionandtracking AT lyessaadsaoud advancingunderwatervisionasurveyofdeeplearningmodelsforunderwaterobjectrecognitionandtracking AT atifsultan advancingunderwatervisionasurveyofdeeplearningmodelsforunderwaterobjectrecognitionandtracking AT mohamedheshmat advancingunderwatervisionasurveyofdeeplearningmodelsforunderwaterobjectrecognitionandtracking AT lakmalseneviratne advancingunderwatervisionasurveyofdeeplearningmodelsforunderwaterobjectrecognitionandtracking AT irfanhussain advancingunderwatervisionasurveyofdeeplearningmodelsforunderwaterobjectrecognitionandtracking |