Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis
Underwater waste detection is a critical challenge for preserving aquatic ecosystems, particularly due to inherent underwater distortions such as light refraction, occlusion, and scattering. In this study, we present a novel deep learning framework for real-time underwater waste detection by evaluat...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11002515/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850269668875436032 |
|---|---|
| author | Jaskaran Singh Walia Kavietha Haridass L. K. Pavithra |
| author_facet | Jaskaran Singh Walia Kavietha Haridass L. K. Pavithra |
| author_sort | Jaskaran Singh Walia |
| collection | DOAJ |
| description | Underwater waste detection is a critical challenge for preserving aquatic ecosystems, particularly due to inherent underwater distortions such as light refraction, occlusion, and scattering. In this study, we present a novel deep learning framework for real-time underwater waste detection by evaluating state-of-the-art object detection algorithms on a manually annotated custom dataset comprising images across various water bodies to represent real-world turbidity, illumination, and occlusion. Our approach incorporates robust feature extraction and specialized data augmentation techniques that effectively mitigate the adverse effects of underwater distortions. We investigate multiple architectures, including YOLOv8n, YOLOv7, YOLOv6s, YOLOv5s, Faster R-CNN, and Mask R-CNN, analyzing key parameters such as mean average precision (mAP), inference speed, and computational efficiency. Our results demonstrate that YOLO-based models achieve faster & accurate performance, with YOLOv8n and YOLOv7 reaching a detection accuracy of 96%, compared to 81% and 83% for Faster R-CNN and Mask R-CNN, respectively. Computationally, YOLOv8n achieves 76 ms (milliseconds) per frame, while YOLOv5s runs at 14 ms per frame, confirming real-time viability for AUV deployment. The proposed approach offers significant advantages over existing methods by enabling rapid, accurate detection with low computational overhead, thereby paving the way for integration with autonomous underwater vehicles (AUVs) for environmental monitoring and waste management. |
| format | Article |
| id | doaj-art-9708ab50c19a4369820366490c70260e |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-9708ab50c19a4369820366490c70260e2025-08-20T01:53:00ZengIEEEIEEE Access2169-35362025-01-0113889178892910.1109/ACCESS.2025.356934411002515Deep Learning Innovations for Underwater Waste Detection: An In-Depth AnalysisJaskaran Singh Walia0https://orcid.org/0000-0002-9255-5446Kavietha Haridass1L. K. Pavithra2https://orcid.org/0000-0003-3042-0068School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaCentre for Human Movement Analytics, Vellore Institute of Technology, Chennai, IndiaUnderwater waste detection is a critical challenge for preserving aquatic ecosystems, particularly due to inherent underwater distortions such as light refraction, occlusion, and scattering. In this study, we present a novel deep learning framework for real-time underwater waste detection by evaluating state-of-the-art object detection algorithms on a manually annotated custom dataset comprising images across various water bodies to represent real-world turbidity, illumination, and occlusion. Our approach incorporates robust feature extraction and specialized data augmentation techniques that effectively mitigate the adverse effects of underwater distortions. We investigate multiple architectures, including YOLOv8n, YOLOv7, YOLOv6s, YOLOv5s, Faster R-CNN, and Mask R-CNN, analyzing key parameters such as mean average precision (mAP), inference speed, and computational efficiency. Our results demonstrate that YOLO-based models achieve faster & accurate performance, with YOLOv8n and YOLOv7 reaching a detection accuracy of 96%, compared to 81% and 83% for Faster R-CNN and Mask R-CNN, respectively. Computationally, YOLOv8n achieves 76 ms (milliseconds) per frame, while YOLOv5s runs at 14 ms per frame, confirming real-time viability for AUV deployment. The proposed approach offers significant advantages over existing methods by enabling rapid, accurate detection with low computational overhead, thereby paving the way for integration with autonomous underwater vehicles (AUVs) for environmental monitoring and waste management.https://ieeexplore.ieee.org/document/11002515/Computer visionimage processingroboticsobject detectionunderwater trashimage segmentation |
| spellingShingle | Jaskaran Singh Walia Kavietha Haridass L. K. Pavithra Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis IEEE Access Computer vision image processing robotics object detection underwater trash image segmentation |
| title | Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis |
| title_full | Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis |
| title_fullStr | Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis |
| title_full_unstemmed | Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis |
| title_short | Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis |
| title_sort | deep learning innovations for underwater waste detection an in depth analysis |
| topic | Computer vision image processing robotics object detection underwater trash image segmentation |
| url | https://ieeexplore.ieee.org/document/11002515/ |
| work_keys_str_mv | AT jaskaransinghwalia deeplearninginnovationsforunderwaterwastedetectionanindepthanalysis AT kaviethaharidass deeplearninginnovationsforunderwaterwastedetectionanindepthanalysis AT lkpavithra deeplearninginnovationsforunderwaterwastedetectionanindepthanalysis |