Earth Observation

Earth Observation (EO) refers to the use of remote sensing technologies to monitor land, marine (seas, rivers, lakes) and atmosphere. Satellite-based EO relies on the use of satellite-mounted payloads to gather imaging data about the Earth’s characteristics. The images are then processed and analyzed in order to extract different types of information that can serve a very wide range of applications and industries.

Benchmarks

Libraries

Datasets

Subtasks

Most implemented papers

EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification

Content

DOTA: A Large-Scale Dataset for Object Detection in Aerial Images

Proximity Forest: an effective and scalable distance-based classifier for time series

Fully Convolutional Siamese Networks for Change Detection

End-to-end learning of energy-based representations for irregularly-sampled signals and images

Cloud Removal in Satellite Images Using Spatiotemporal Generative Networks

SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation

Self-Attention for Raw Optical Satellite Time Series Classification

Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery