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{174267,
        author = {B Lalitha Rajeswari and T Poojitha and P Sruthi and T Nithish Kumar and P Menaja},
        title = {Oil Spill Detection with Deep Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {3323-3329},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174267},
        abstract = {Oil spill detection in marine environments is crucial for mitigating environmental damage and enabling swift response actions. This study presents a deep learning-based app-roach that integrates YOLOv8 for segmentation and DenseNet for classification, providing a robust and efficient solution for detecting and classifying oil spills.
The YOLOv8 segmentation model is trained on a dataset sourced from Roboflow, containing annotated images of different oil spill types, including truecolor, sheen, and rainbow spills. With 50 epochs of training on 640×640 pixel images, YOLOv8 effectively detects and segments oil spills in real-time, generating segmentation masks with confidence scores. The DenseNet model further enhances the system by performing binary classification with an accuracy of 99.67%, distinguishing between oil spill and non-oil spill images.
A user-friendly interface is integrated into the system, featuring OTP-based user registration, profile management, feedback analytics, and an admin authentication module for monitoring and management. The combination of YOLOv8’s real-time seg-mentation capabilities and DenseNet’s high classification accuracy ensures a comprehensive solution for oil spill detection. This approach enables faster response times, improved environ-mental protection, and enhanced decision-making for marine pollution management.},
        keywords = {Oil Spill Detection, YOLOv8, DenseNet, Deep Learning, Image Segmentation, Marine Pollution.},
        month = {March},
        }