RFI_AI4QC dataset

This dataset was used in the AI4QC project (Artificial Intelligence for Quality Control), in the context of RFI detection through an object detection task. It consists of a set of labeled RFIs (radio frequency interferences). These interferences are caused by man-made sources and can lead to an artefact in the satellite image, typically a bright rectangular pattern. Bounding boxes were defined around RFI artefacts in 3940 Sentinel-1 quick-looks (png images). 

 

The labeled RFIs are available in three formats: PASCAL VOC (xml files), COCO (json files) and YOLO (txt files). Each is contained in a different zip file. The last zip file contains the 3940 S1 images (quick-looks). One can combine the label files (in a chosen format) with the S1 images to train object detection algorithms to automatically detect RFIs in a satellite image.