Remote sensing image classification plays a crucial role in mapping and understanding various land types. This project focuses on scene classification using deep learning models. The dataset used for this study contains aerial images from different scenes such as urban areas, forests, water bodies, and agricultural zones. The proposed system uses Convolutional Neural Networks (CNN), MobileNet, DenseNet, and Vision Transformer (ViT) models to extract features and classify scenes. These models are chosen for their ability to process and analyze visual data efficiently, even in complex and large datasets. The project’s objective is to improve the accuracy and efficiency of remote sensing scene classification using these advanced models. The system is developed with a user-friendly web interface where users can upload images and receive scene classifications. The backend uses Flask, while the frontend is built using HTML, CSS, and JavaScript. The system can be deployed and used for automated classification tasks across different applications.

Keywords: Remote sensing, image classification, deep learning, CNN, MobileNet, DenseNet, ViT, feature extraction, aerial images, scene types.