AI-TOD is a dataset for tiny object detection in aerial images. The mean size of objects in AI-TOD is about 12.8 pixels, which is much smaller than in other datasets.

AI-TOD: Tiny Object Detection in Aerial Images

Check out this repository for models using Facebook's Detectron2 to detect parking bays from satellite imagery and synthetic data.

Detecting Parking Bays With Satellite Imagery

ARCO ERA5 atmospheric reanalysis provides hourly estimates of a large number of atmospheric, land, and oceanic climate variables, spanning from 1979 to the present.

ARCO ERA5: Recipes for Reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 Datasets

The Replicable AI for Microplanning (RAMP) project is an open-source deep learning model that accurately digitizes buildings in low- and middle-income countries using satellite imagery.

RAMP Open Buildings Project

This repository provides code for training and evaluating a convolutional neural network (CNN) to detect tree in urban environments with aerial imagery.

Individual Tree Detection in Large-Scale Urban Environments

Radiant Earth has released LandCoverNet, which will enable the creation of high-resolution and up-to-date maps for natural resource management.

LandCoverNet: The First Global Multi-Satellite Training Dataset for Land Cover Classification

The AiTLAS toolbox includes state-of-the-art machine learning methods for exploratory and predictive analysis of satellite imagery as well as repository of AI-ready earth observation datasets.

AiTLAS: AI Methods for Exploratory and Predictive Analysis of Satellite Images

This article analyses the Airbus oil storage dataset which contains over 13,500 annotated POL (petroleum, oil and lubricant) storage objects. This dataset is used to train an oil storage detector.

Oil Storage Detection on Airbus Imagery With YOLOX

This is a single class dataset consisting of tiles of satellite imagery labeled with potential 'targets' to help with search and rescue.

Dataset for Deep Learning Assisted Search and Rescue with Satellite Imagery

LEVIR-Ship is the first public tiny ship detection dataset specific to medium-resolution remote sensing images. Check it out here.

LEVIR-Ship: Tiny Ship Detection Dataset

Determine the location of a given street view image by matching it against a collection of geo-tagged satellite images. Read more about it here.

Satellite-to-Street View Synthesis for Geo-Localization

Check here for a dual stream U-Net architecture method for urban change detection using Sentinel-1 and Sentinel-2 data fusion.

Training-data

AI-TOD: Tiny Object Detection in Aerial Images

Detecting Parking Bays With Satellite Imagery