Enhancing Satellite Imagery with GAN Based Cloud Removal

Title

Enhancing Satellite Imagery with GAN Based Cloud Removal

Creator

Varghese, Aleena; Sudhakar, T.; Joy, Helen K.

Description

Satellite imaging is one of the most common uses for applications agricultural, urban planning and environmental monitoring to mention a few. Unfortunately, even the best-laid plans for aerial photography can be decimated by one thing: cloud cover. The novel way of cloud extraction from the satellite data that is demonstrated in this article, use a Generative Adversarial Network (GAN). For the betterment of cloud removal, ResNet based discriminator and a UNet-based generator are utilized in the suggested approach. To accurately train the networks, a new technique was also developed to introduce noise that resembles natural cloud patterns. The PSNR score, as a qualitative and quantitative index card that uses the PyTorch- based GAN methodology to verify different performances in traditional methods based on EuroSat. 2025 IEEE.

Source

2nd International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2025;

Date

01-01-2025

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

Cloud Removal; Generative Adversarial Networks (GANs); Image Reconstruction; Peak Signal-to-Noise Ratio (PSNR); Perlin Noise; ResNet; Satellite Imagery; UNet

Coverage

Varghese A., CHRIST University, Department of Computer Science, Bangalore, India; Sudhakar T., CHRIST University, Department of Computer Science, Bangalore, India; Joy H.K., CHRIST University, Department of Computer Science, Bangalore, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 979-833152162-2;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICECCC65144.2025.11063844

https://www.scopus.com/pages/publications/105012027174?origin=resultslist