Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Mar 28, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Offshore oil spill detection based on visual information and deep learning.

Rasim Alguliyev¹, Ramiz Aliguliyev¹, Lyudmila Sukhostat¹

¹Institute of Information Technology, 9A, B. Vahabzade Street, Baku, AZ1141, Azerbaijan.

Marine Pollution Bulletin

|March 26, 2026

Summary

This study introduces a novel approach for detecting offshore oil spills using two U-Net models. The advanced models demonstrate high efficiency in identifying oil spills from satellite imagery, crucial for environmental protection.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Graph modelling for tracking the COVID-19 pandemic spread.

Infectious Disease Modelling·2021

Same author

A Comparative Analysis of Pitch Detection Methods Under the Influence of Different Noise Conditions.

Journal of voice : official journal of the Voice Foundation·2015

See all related articles

Area of Science:

Environmental Science
Remote Sensing
Computer Vision

Background:

Offshore oil spills pose significant threats to marine ecosystems.
Synthetic Aperture Radar (SAR) imagery is a key tool for monitoring sea surface conditions.
Early detection of oil spills is vital for mitigating environmental damage.

Purpose of the Study:

To develop and evaluate an effective automated system for offshore oil spill detection.
To leverage deep learning models for enhanced accuracy in identifying oil spills from SAR images.

Main Methods:

A novel approach utilizing two U-Net-based deep learning models.
Integration of EfficientNet-B7 and ResNeXt architectures as backbones for U-Net.
Evaluation performed on PALSAR and Sentinel-1 satellite datasets.

Keywords:

Convolutional neural network Deep neural models Environmental safety Oil spill detection Synthetic aperture radar images

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Mar 28, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Main Results:

The proposed model achieved high performance metrics on both datasets.
Mean IoU scores of 81.62% (PALSAR) and 82.41% (Sentinel-1).
Dice scores of 83.27% (PALSAR) and 84.36% (Sentinel-1).

Conclusions:

The developed U-Net models with EfficientNet-B7 and ResNeXt backbones show high efficiency for oil spill detection.
The approach offers a reliable method for timely identification of marine oil pollution.
Results indicate significant potential for improving environmental safety and response to oil spills.