Object-detection

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

This repository contains the code for a novel interactive annotation method for multiple instances of tiny objects from multiple classes, based on a few point-based user inputs.

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

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.

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

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.

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

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.

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.

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.