Archive: Object-detection

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

Million-AID is a large-scale benchmark dataset containing a million instances for remote sensing scene classification.

This dataset is collected from the German TerraSAR-X satellite, which is working in x-band and HH polarization mode with image resolutions ranging from 0.5m to 3m.

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.

YOLTv5 rapidly detects objects in arbitrarily large aerial or satellite images that far exceed the ~600×600 pixel size typically ingested by deep learning object detection frameworks.

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

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.

Here is a graph-in-graph (GiG) model and a related GiG convolutional network (GiGCN) for HSI classification from a superpixel viewpoint.

This method aims to detect buildings and roads from pre-event satellite imagery while determining for each object instance whether it is affected by a recent flood event in post-event imagery.

SARfish is a program designed to help Open Source Intelligence (OSINT) researchers investigate maritime traffic. Learn more here.