Buchumschlag

A Novel Oil Spill Dataset Augmentation Framework Using Object Extraction and Image Blending Techniques

Gespeichert in:
Veröffentlicht in:Remote Sensing vol. 17, no. 2 (2025), p. 336
1. Verfasser: Akhmedov, Farkhod
Weitere Verfasser: Khujamatov, Halimjon, Abdullaev, Mirjamol, Heung-Seok Jeon
Veröffentlicht:
MDPI AG
Schlagworte:
Uzbekistan
Persian Gulf
Gulf of Mexico
Oil spills
Feature extraction
Environmental cleanup
Deep learning
Datasets
Ocean models
Applications programs
Satellite imagery
Marine ecosystems
Environmental impact
Machine learning
Pollution detection
Local economy
Data augmentation
Blending
Remote sensing
Environmental conditions
Biodiversity
Image quality
Surveillance
Object recognition
Coastal ecosystems
Satellites
Online-Zugang:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!
Abstract:Oil spills pose significant threats to marine and coastal ecosystems, biodiversity and local economies, necessitating efficient and accurate detection systems. Traditional detection methods, such as manual inspection and satellite imaging, are often resource-intensive and time consuming. This study addresses these challenges by developing a novel approach to enhance the quality and diversity of oil spill datasets. Several studies have mentioned that the quality and size of a dataset is crucial for training robust vision-based deep learning models. The proposed methodology combines advanced object extraction techniques with traditional data augmentation strategies to generate high quality and realistic oil spill images under various oceanic conditions. A key innovation in this work is the application of image blending techniques, which ensure seamless integration of target oil spill features into diverse environmental ocean contexts. To facilitate accessibility and usability, a Gradio-based web application was developed, featuring a user-friendly interface that allows users to input target and source images, customize augmentation parameters, and execute the augmentation process effectively. By enriching oil spill datasets with realistic and varied scenarios, this research aimed to improve the generalizability and accuracy of deep learning models for oil spill detection. For this, we proposed three key approaches, including oil spill dataset creation from an internet source, labeled oil spill regions extracted for blending with a background image, and the creation of a Gradio web application for simplifying the oil spill dataset generation process.
ISSN:2072-4292
DOI:10.3390/rs17020336
Quelle:Advanced Technologies & Aerospace Database