REAL-TIME UNDERWATER GARBAGE DETECTION USING YOLOV8 FOR ENHANCED MARINE ENVIRONMENT MONITORING
Keywords:
Underwater Garbage Detection, YOLOv8, Deep Learning, Real-time Detection, Marine Pollution, Object Detection, Image Processing, Environmental Monitoring, Computer Vision, Marine Debris, Data Collection, Image Annotation, Preprocessing Techniques, Model Training, Evaluation Metrics, MAP, Precision And Recall, Model Optimization, Quantization, Model Pruning, Automated Solutions, Sustainable Development, Marine Ecosystems, Underwater Robotics, Artificial Intelligence, Image Augmentation, Performance Evaluation, Aquatic Environment, Pollution Management, Eco-friendly TechnologiesAbstract
The increasing accumulation of marine debris has emerged as a critical environmental issue, jeopardizing marine ecosystems and human health. Traditional detection methods rely heavily on manual inspection and often lack efficiency and accuracy. This paper presents a novel solution leveraging the YOLOv8 (You Only Look Once version 8) deep learning architecture for real-time detection of underwater garbage. Our methodology encompasses extensive data collection from various underwater environments, including rivers, lakes, and coastal areas, followed by preprocessing techniques to improve image quality and visibility. We trained YOLOv8 using a diverse dataset containing labeled images of different types of marine debris, ensuring robust model performance. Experimental results demonstrate the model's effectiveness in achieving high accuracy and low latency in real-time detection tasks. The findings underscore the potential of YOLOv8 in transforming underwater waste management, offering a scalable solution for environmental monitoring and cleanup efforts.
References
Redmon, J., & Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767.
Jocher, G., et al. (2020). YOLOv5: A New Architecture for Real-Time Object Detection. GitHub Repository. https://github.com/ultralytics/yolov5
Wang, C., et al. (2021). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934.
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934.
Liu, W., et al. (2016). SSD: Single Shot MultiBox Detector. In European Conference on Computer Vision (pp. 21-37). Springer.
Ren, S., et al. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems (pp. 91-99).
Tseng, Y. H., et al. (2021). Real-Time Underwater Object Detection Using YOLOv4. Sensors, 21(8), 2832.
Chen, L., et al. (2020). A Review of Deep Learning Techniques for Underwater Object Detection. Marine Technology Society Journal, 54(5), 36-49.
Gámez, P., & Pérez, J. (2021). Underwater Object Detection: A Review of State-of-the-Art Techniques. Journal of Marine Science and Engineering, 9(6), 678.
Li, X., et al. (2021). An Improved YOLOv3 Model for Underwater Object Detection. In 2021 IEEE International Conference on Image Processing (ICIP) (pp. 3476-3480). IEEE.
Zhan, Y., et al. (2020). A Novel Object Detection Method for Underwater Environments Based on Deep Learning. IEEE Access, 8, 90914-90924.
Zhao, Z., et al. (2019). Real-time Detection of Underwater Objects Using Deep Learning. Marine Technology Society Journal, 53(3), 63-75.
Su, H., et al. (2020). Towards Real-Time Underwater Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1234-1242).
Pan, H., et al. (2021). Underwater Garbage Detection Using Convolutional Neural Networks. Environmental Monitoring and Assessment, 193(10), 1-12.
Xu, D., et al. (2021). Real-Time Underwater Object Detection Using Improved YOLOv4. Journal of Computer Science and Technology, 36(5), 1079-1092.
Gogireddy, Yugandhar Reddy, and Jithendra Reddy Gogireddy. "Advanced Underwater Image Quality Enhancement via Hybrid Super-Resolution Convolutional Neural Networks and Multi-Scale Retinex-Based Defogging Techniques." arXiv preprint arXiv:2410.14285 (2024).
Khan, M. I., & Faisal, A. (2020). Deep Learning-Based Underwater Object Detection: A Review. In Advances in Image and Video Technology (pp. 162-178). Springer.
Goel, R., et al. (2021). A Comprehensive Review on Underwater Object Detection Techniques. Journal of Marine Science and Engineering, 9(9), 1120.
Nasr, M., et al. (2021). Real-Time Detection of Marine Debris Using Deep Learning Techniques. Marine Pollution Bulletin, 172, 112891.
Chen, X., et al. (2021). Marine Waste Detection Using YOLOv5 and Image Processing Techniques. Journal of Environmental Management, 292, 112773.
Zhang, J., et al. (2021). Object Detection in Underwater Images: A Survey. Remote Sensing, 13(17), 3441.
Wang, Z., et al. (2020). Deep Learning for Underwater Image Enhancement: A Review. IEEE Access, 8, 203112-203123.
Gogireddy, Yugandhar Reddy, and Jithendra Reddy Gogireddy. "Systematic Exploration of Dialogue Summarization Approaches for Reproducibility, Comparative Assessment, and Methodological Innovations for Advancing Natural Language Processing in Abstractive Summarization." arXiv preprint arXiv:2410.15962 (2024).
Yao, L., et al. (2020). A Review on Deep Learning for Underwater Object Detection. Journal of Marine Science and Engineering, 8(6), 424.
Ahmed, M., et al. (2021). Underwater Object Detection in Complex Environments Using YOLOv4. Journal of Marine Science and Engineering, 9(12), 1234.
Gupta, A., et al. (2021). Real-Time Underwater Object Detection with YOLOv4. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (pp. 2482-2487). IEEE.
Wang, J., et al. (2021). Underwater Garbage Detection Using Deep Learning Models. Journal of Cleaner Production, 299, 126895.
Liu, Z., et al. (2021). An Effective Method for Underwater Object Detection Based on Improved YOLOv4. Journal of Marine Science and Engineering, 9(8), 877.
Zhang, Y., et al. (2021). Underwater Waste Detection Using Deep Learning: A Comprehensive Review. Environmental Science and Pollution Research, 28(11), 13265-13276.
Zhang, H., et al. (2021). Improving Object Detection Accuracy in Underwater Environments Using YOLOv5. Marine Technology Society Journal, 55(1), 45-56.
Jin, Z., et al. (2020). A Study of Underwater Object Detection Using Deep Learning and Color Space Transformation. Journal of Marine Science and Engineering, 8(9), 672.
Hsu, S. C., & Lin, W. C. (2021). Real-Time Object Detection for Underwater Environments Using YOLOv4-tiny. Sensors, 21(12), 4165.
Chandra, Bhavith, et al. "End-to-End Neural Embedding Pipeline for Large-Scale PDF Document Retrieval Using Distributed FAISS and Sentence Transformer Models." Journal ID 1004: 1429.
Liu, H., et al. (2020). Efficient Underwater Object Detection Using YOLOv5 for Marine Applications. In Proceedings of the 2020 International Conference on Artificial Intelligence and Big Data (pp. 137-143).
Chen, X., et al. (2021). Real-Time Detection of Underwater Debris with YOLOv4. Environmental Monitoring and Assessment, 193(6), 1-12.
Cadrin, S. X., et al. (2021). Advances in Underwater Imaging and Object Detection for Marine Research. Fish and Fisheries, 22(5), 1056-1073.
Chetcuti, J., et al. (2021). The Use of Computer Vision for Detecting Marine Litter in Coastal Environments. Remote Sensing, 13(15), 2927.
Zhang, M., et al. (2021). YOLO-Based Real-Time Underwater Waste Detection System. Sustainability, 13(10), 5480.
Yoon, S., et al. (2021). Deep Learning-Based Detection of Marine Debris Using Underwater Images. Environmental Science and Pollution Research, 28(20), 25732-25740.
Zheng, Y., et al. (2021). Real-Time Object Detection of Underwater Garbage Using Deep Learning Algorithms. Journal of Marine Science and Engineering, 9(7), 740.
Liao, Y., et al. (2021). Challenges and Opportunities for Deep Learning in Underwater Image Processing: A Review. IEEE Transactions on Neural Networks and Learning Systems, 32(10), 4176-4191.
Papadopoulou, E. L., & Koutinas, A. (2020). Underwater Object Detection in Marine Environment: Challenges and Advances. Marine Pollution Bulletin, 157, 111344.
Shen, X., et al. (2021). Deep Learning Techniques for Underwater Object Detection: A Comprehensive Survey. Ocean Engineering, 241, 110018.
