Civil works monitoring using satellite imagery and machine learning

Using up-to-date satellite imagery is nowadays mandatory to the decision-making process in many areas: agriculture, environment, water resources … Checking present and historical views of a site can be of great importance to improve management and reduce inspection costs. Adding artificial intelligence (AI) and machine learning (ML) to this equation enhances the power of this technologies to the point that virtually any measurable parameter can be detected and tracked from space.

Siemens Gamesa Renewable Energies hired Taniwa and Geomatico to build an innovative product from scratch to monitor windmill civil works automatically. This project was develop under the BIND4.0 program. The goal was to track build progress, based on satellite imagery, automatic object detection and AI.

Geomatico was in charge of automatic processing of satellite imagery (all steps, from acquisition to analysis) and providing training (around 20.000 images); Taniwa was responsible for the ML algorythms to identify state, the development of the web interface and the high scalability deployment via Azure Cloud.

Technologies: Image Processing, Deep learning, GIS, React, Kubernetes

Photo by Master Wen on Unsplash

Do you have a project idea and want to turn it into reality? We would like to hear from you, tell us about it

The facts define us