EarthLoc: Astronaut Photography Localization by Indexing Earth from Space
This work addresses a critical gap in Earth observations data by automating the localization of astronaut photos, which is currently done manually and is time-consuming.
The paper tackles the problem of automatically localizing astronaut photography from space, which is crucial for scientific and disaster response applications, by introducing EarthLoc, a novel image retrieval approach that achieves superior efficiency and accuracy compared to existing methods.
Astronaut photography, spanning six decades of human spaceflight, presents a unique Earth observations dataset with immense value for both scientific research and disaster response. Despite its significance, accurately localizing the geographical extent of these images, crucial for effective utilization, poses substantial challenges. Current manual localization efforts are time-consuming, motivating the need for automated solutions. We propose a novel approach - leveraging image retrieval - to address this challenge efficiently. We introduce innovative training techniques, including Year-Wise Data Augmentation and a Neutral-Aware Multi-Similarity Loss, which contribute to the development of a high-performance model, EarthLoc. We develop six evaluation datasets and perform a comprehensive benchmark comparing EarthLoc to existing methods, showcasing its superior efficiency and accuracy. Our approach marks a significant advancement in automating the localization of astronaut photography, which will help bridge a critical gap in Earth observations data. Code and datasets are available at https://github.com/gmberton/EarthLoc