Cloud Detection and Removal from RGB Images using U-Net Semantic Segmentation and CloudGAN Models
Mennatall Essam, Hassan Ekpo, Sunday Alyami, Ghadah S. Elias, Fanuel Salah, Ibrahim Mabrook, M Mourad
Mennatall Essam, Hassan
Ekpo, Sunday
Alyami, Ghadah S.
Elias, Fanuel
Salah, Ibrahim
Mabrook, M Mourad
Type
Supervisor
Date
2024-11-28
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Satellite-based imagery provides an indispensable tool for many applications, ranging from environmental surveillance to urban development and managing natural disasters. Nevertheless, the presence of clouds can often impede the useful-ness of these images by veiling significant details. In the current study, we proposed an innovative strategy for identify-ing and eliminating clouds within RGB satellite images employing deep learning techniques. This involves using a Cloud Generative Adversarial Network (CloudGAN) to carry out image inpainting tasks and U-Net for semantic segmentation. The proposed methodology yields encouraging outcomes, showcasing its ability to discern and eradicate clouds effective-ly, thereby enhancing the clarity and practicality of satellite imagery. The proposed approach demonstrates superior cloud removal compared to traditional methods, achieving a remarkable overall accuracy of 95\% in both cloud detec-tion and removal. This underscores its effectiveness in enhancing image quality and utility. The qualitative assessment confirms the models' ability to produce high-quality, cloud-free images, preserving essential features and details faithfully. Additionally, the inpainted images closely resemble the ground truth, affirming the accuracy of the models in cloud removal.