In March, we concluded the SpaceNet Road Detection and Routing Challenge hosted by CosmiQ Works, Radiant Solution and NVIDIA. Read more about how accurate road networks are an important map feature that is required for everything from logistics planning to turn-by-turn directions.
The You Only Look Twice (YOLT) framework extends the popular YOLO algorithm to rapidly handle the extremely large file sizes of satellite imagery. In this blog we are pleased to announce the release of YOLT codebase and the YOLT arXiv paper.
IQT Labs have developed a tool called Comet Time Series (CometTS) that facilitates analysis and visualization of a time series of satellite imagery in order to enable population estimation research, change detection, or natural disaster monitoring using a range of data types.
CosmiQ Works explores methods to derive road segmentation masks from SpaceNet satellite imagery and demonstrate techniques to mitigate deep learning hardware limitations in order to infer maps over large areas.
CosmiQ Works details the steps to get started working with the roads dataset, with attendant code hosted on the APLS github page.
The SpaceNet Road Detection and Routing Challenge is designed to assist the development of techniques for generating road networks from satellite imagery.