S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications
This provides a new public dataset for shadow detection in remote sensing, addressing a specific need in applications like 3D reconstruction, but it is incremental as it builds on existing methods and datasets.
The authors introduced the S-EO dataset, a large-scale resource with 702 georeferenced tiles and approximately 20,000 images for geometry-aware shadow detection in remote sensing, and demonstrated its utility by training a shadow detector and improving 3D reconstructions with EO-NeRF.
We introduce the S-EO dataset: a large-scale, high-resolution dataset, designed to advance geometry-aware shadow detection. Collected from diverse public-domain sources, including challenge datasets and government providers such as USGS, our dataset comprises 702 georeferenced tiles across the USA, each covering 500x500 m. Each tile includes multi-date, multi-angle WorldView-3 pansharpened RGB images, panchromatic images, and a ground-truth DSM of the area obtained from LiDAR scans. For each image, we provide a shadow mask derived from geometry and sun position, a vegetation mask based on the NDVI index, and a bundle-adjusted RPC model. With approximately 20,000 images, the S-EO dataset establishes a new public resource for shadow detection in remote sensing imagery and its applications to 3D reconstruction. To demonstrate the dataset's impact, we train and evaluate a shadow detector, showcasing its ability to generalize, even to aerial images. Finally, we extend EO-NeRF - a state-of-the-art NeRF approach for satellite imagery - to leverage our shadow predictions for improved 3D reconstructions.