: Unlike older datasets that focused on specific urban areas, EROS-Thunder covers various terrains, including forests, agricultural lands, and complex urban environments across different seasons.
The paper associated with the dataset file is titled "Thunder: A Large-Scale EROS Dataset for Remote Sensing Image Change Detection" , published in 2024. EROS_-_Thunder.rar
: Binary masks where white pixels (255) represent change and black pixels (0) represent no change. : Unlike older datasets that focused on specific
: Pre-change and post-change satellite images. : Pre-change and post-change satellite images
The dataset and paper focus on advancing change detection (CD) in remote sensing by providing a more diverse and extensive collection of high-resolution satellite imagery than previous benchmarks. Key Details of the Paper
: It specifically targets the "Easy-to-Retrieve and Open-Source" (EROS) philosophy to make high-quality change detection data accessible to the broader research community. Technical Contribution
: It is one of the largest datasets for change detection, containing thousands of high-resolution (0.5m to 2.0m) image pairs.