Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198504,
        author = {Imteyaz Shahzad and Sabiha Ansari and Punam Rathod and Atufa Afreen and Samiksha Bambode and Kamran Hossain},
        title = {Plastic Finder Underwater plastic detection system},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {9557-9565},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198504},
        abstract = {Plastic pollution in marine ecosystems has become one of the most pressing environmental concerns of our era. Annual estimates suggest that close to eight million metric tons of plastic waste find their way into the world's oceans, and a significant portion—around 70%—eventually settles on the seabed. Traditional detection methods such as diver-led inspections and trawl-based sampling are resource-intensive, spatially limited, and unable to scale with the magnitude of the problem. This study surveys recent progress in applying deep learning to the automated identification of submerged plastic materials. Through a critical review of eleven peer-reviewed studies published between 2023 and 2025, we assess eight object detection architectures—covering multiple generations of YOLO and Faster R-CNN—using benchmark datasets including TrashCAN 1.0 and DeepTrash. Findings indicate that YOLOv9 and YOLOv12l deliver the strongest detection accuracy, while YOLOv10-s strikes the most favorable trade-off between precision and computational cost. Water turbidity is identified as the principal environmental constraint, with detection performance deteriorating significantly beyond 100 NTU. We conclude by outlining a proposed unified research framework to close existing gaps in microplastic detection and turbidity-aware modeling.},
        keywords = {Underwater Plastic Detection; Deep Learning; YOLO; CNN; Marine Pollution; Edge Computing; ROV; TrashCAN},
        month = {April},
        }