Exploring Deep Learning for Underwater Plastic Debris Detection and Monitoring

• Autorzy: Khriss Abdelaadim , Elmiad Aissa Kerkour , Badaoui Mohammed , Barkaoui Alae-Eddine , Zarhloule Yassine

Identyfikatory

DOI

10.12911/22998993/187970

• Języki publikacji: EN

Abstrakty

EN

In this paper, a comparative evaluation of state-of-the-art deep learning models for object detection in underwater environments focusing on marine debris detection was presented. The performance of four prominent object detection models was investigated, including: Faster R-CNN, SSD, YOLOv8, and YOLOv9, using two different datasets: TrashCAN and DeepTrash. Through quantitative analysis, the accuracy, precision, recall, and mean average precision (mAP) of each model across different object classes and environmental conditions were evaluated. The obtained results show that YOLOv9 consistently outperforms the other models, demonstrating superior precision, recall, and mAP values on both datasets. Furthermore, the stability and convergence behavior of the models during training were analyzed, highlighting the excellent stability and adaptability of YOLOv9. The obtained results underscore the effectiveness of deep learning-based approaches in marine debris detection and highlight the potential of YOLOv9 as a robust solution for environmental monitoring and intervention efforts in underwater ecosystems.

Słowa kluczowe

EN

marine debris monitoring; deep learning; YOLOv9; YOLOv8; faster rcnn; ssd

• Wydawca: Polskie Towarzystwo Inżynierii Ekologicznej ; Lublin University of Technology
• Czasopismo: Journal of Ecological Engineering
• Rocznik: 2024
• Tom: Vol. 25, nr 7
• Strony: 58--69
• Opis fizyczny: Bibliogr. 29 poz., rys., tab.

Twórcy

autor

Khriss Abdelaadim

• Laboratory LARI, FSO, Mohammed Premier University, Oujda, Morocco

autor

Elmiad Aissa Kerkour

• Laboratory LARI, FSO, Mohammed Premier University, Oujda, Morocco

autor

Badaoui Mohammed

• Laboratory MSD, ESTO, Mohammed Premier University, Oujda, Morocco

• https://orcid.org/0000-0002-5296-5117

autor

Barkaoui Alae-Eddine

• Laboratory 2GPMH Lab., FSO, Mohammed Premier University, Oujda, Morocco

autor

Zarhloule Yassine

• Laboratory 2GPMH Lab., FSO, Mohammed Premier University, Oujda, Morocco

Bibliografia

• 1. Khriss, A., Elmiad, K.A., Badaoui M., Barkaoui A. and Zarhloule, Y. 2024. Advances in machine learning and deep learning approaches for plastic litter detection in marine environments. Journal of Theoretical and Applied Information Technology, 102(5).
• 2. Markic A., Gaertner J.-C., Gaertner-Mazouni N. and Koelmans A.A. 2020. Plastic ingestion by marine fish in the wild. Critical Reviews in Environmental Science and Technology, 50(7), 657–697.
• 3. Aleem, A., Tehsin S., Kausar S. and Jameel A. 2022. Target classification of marine debris using deep learning. Intelligent Automation & Soft Computing, 32(1).
• 4. Bhanumathi, M., Dhanya, S., Gugan, R. and Kirthika, K.G. 2022. Marine Plastic Detection Using Deep Learning. 11.
• 5. Corrigan, B.C., Tay, Z.Y. and Konovessis, D. 2023. Real-time instance seg- mentation for detection of underwater litter as a plastic source. Journal of Marine Science and Engineering, 11(8), 1532.
• 6. Wang, C.-Y., Yeh, I.-H. and Liao, H.-Y.M. 2024. Yolov9: Learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616.
• 7. McLean, D.L., Parsons, M.J.G., Gates, A.R., Benfield, M.C., Bond, T., Booth, D.J., Bunce, M., Fowler, A.M, Harvey, E.S, Macreadie, P.I., Charitha, B. Pattiaratchi, Rouse, S., Thomson, P.G., Partridge, J.C., Todd, V.L.G., Jones, D.O.B. 2020. Enhancing the scientific value of industry remotely operated vehicles (rovs) in our oceans. Frontiers in Marine Science, 7, 220.
• 8. Tata, G., Royer, S.-J., Poirion, O. and Lowe, J. 2021. Deepplastic: A novel approach to detecting epipelagic bound plastic using deep visual models. arXiv preprint arXiv: 2105.01882.
• 9. Jocher, G., Chaurasia, A. and Qiu, J. 2023. Ultralytics yolov8.
• 10. Japan Agency for Marine-Earth Science and Technology (JAMSTEC). JAMSTEC deep-sea debris database, 2012.
• 11. Walia, J.S. and Seemakurthy, K. 2023. Optimized custom dataset for efficient detection of underwater trash. arXiv e-prints, pages arXiv–2305.
• 12. Jesus, A., Zito, C., Tortorici, C., Roura, E., De Masi, G. 2022. Underwater object classification and detection: first results and open challenges. In OCEANS 2022-Chennai. 1–6. IEEE.
• 13. Jothikrishna, K., Rithika, S.M., Swetha, S.V. and Kavitha, K. 2023. Remotely operated underwater vehicle (rov). In 2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), 1–4.
• 14. Hong, J., Fulton, M.S. and Sattar, J. 2020. Trashcan 1.0 an instance-segmentation labeled dataset of trash observations.
• 15. Watanabe, J.-I., Shao, Y. and Miura, N. 2019. Underwater and airborne monitoring of marine ecosystems and debris. Journal of Applied Remote Sensing, 13(4), 044509.
• 16. Anjana, K., Hinduja, M., Sujitha, K., Dharani, G. 2020. Review on plastic wastes in marine environment biodegradation and biotechnological solutions. Marine Pollution Bulletin, 150, 110733.
• 17. Lavers, J.L., Oppel, S., Bond, A.L. 2016. Factors influencing the detection of beach plastic debris. Marine Environmental Research, 119, 245–251. Elsevier.
• 18. Tan, L., Huangfu, T., Wu, L. and Chen, W. 2021. Comparison of yolo v3, faster r-cnn, and ssd for real-time pill identification.
• 19. Belioka, M.-P. and Achilias, D.S. 2023. Microplastic pollution and monitoring in seawater and harbor environments: A meta-analysis and review. Sustainability, 15(11), 9079.
• 20. Fulton, M., Hong J., Islam, Md J. and Sattar, J. 2019. Robotic detection of marine litter using deep visual detection models. In 2019 international conference on robotics and automation (ICRA), pages 5752–5758. IEEE.
• 21. Alabi, O.A., Ologbonjaye, K.I., Awosolu, O. and Alalade, O.E. 2019. Public and environmental health effects of plastic wastes disposal: a review. J Toxicol Risk Assess, 21, 1–13.
• 22. Aguirre-Castro, O.A., Inzunza-Gonz ́alez, E., Garc ́ıa-Guerrero, E.E., Tlelo-Cuautle, E., L ́opez-Bonilla, O.R., Olgu ́ın-Tiznado, J.E. and C ́ardenas-Valdez, J.R. 2019. Design and construction of an rov for underwater exploration. Sensors, 19(24), 5387.
• 23. Qiao, G., Yang, M., Wang, H. 2022. A Detection Approach for Floating Debris Using Ground Images Based on Deep Learning. Remote Sensing, 14(17), 4161.
• 24. Ren S., He K., Girshick R. and Sun J. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28.
• 25. Krause, S., Molari, M., Gorb, E.V., Gorb, S.N., Kossel, E. and Haeckel, M. 2020. Per- sistence of plastic debris and its colonization by bacterial communities after two decades on the abyssal seafloor. Scientific reports, 10(1), 9484.
• 26. Nava, V., Chandra, S., Aherne, J., Alfonso, M.B., Ant ̃ao-Geraldes, A.M., Attermeyer, K., Bao, R., Bartrons, M., Berger, S.A., Biernaczyk, M. 2023. Plastic debris in lakes and reservoirs. Nature, 619(7969), 317–322.
• 27. Li, W.C., Tse, H.F. and Fok, L. 2016. Plastic waste in the marine environment: A review of sources, occurrence and effects. Science of the total environment, 566, 333–349.
• 28. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu C.-Y. and Berg, A.C. 2016. Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, 21–37. Springer.
• 29. Zhang, H., Fu, W., Li, D., Wang, X., Xu, T. 2024. Improved small foreign object debris detection network based on YOLOv5. Journal of Real-Time Image Processing, 21(1), 21.