AeroNet Lab

The laboratory was organized to develop and apply Machine learning algorithms for intelligent analysis of Earth observation data. It was supported by the National Technological Initiative and is partnering with the University of Innopolis.

The project has two components:

  1. Creation of an open benchmark for remote sensing data  – a set of images with the labels of different classes, obtained from various aircrafts, in particular satellite imagery, UAV and MA survey.
  2. Development of the commercialized services based on remote sensing data for various application areas, including monitoring of security zones for linear industrial objects, agriculture forecasts and dynamics, digital terrain model applications, etc.

 

The results of the project should be:

  1. Qualitative labelling of highly detailed images of satellite and aerial imagery that will allow to build adaptation procedures of modern intelligent algorithms for data analysis, and also to develop fundamentally new approaches to the processing and fusion of multidimensional remote sensing data (semantic segmentation, classification, detection of changes, consolidation of heterogeneous data, etc.).
  2. Program implementation of the ML algorithms will be provided via a cloud platform to the wide range of the end users. Potential consumers of services are governmental and business entities in the market areas of Land management, Building and Construction, security and intelligence, in particular, those having a geographically distributed infrastructure and maintaining data monitoring workflows.

 

If you are interested in working with us, check our current openings.