Satellite image processing and analysis


Satellite imaging is a fast-growing market where Earth observation images are routinely used for general-purpose tasks such as land use and land cover analysis, as well as specific tasks as in smart agriculture, fire monitoring, extreme weather forecasting. Image processing tasks involve data selection/reduction, compression, encryption, classification, segmentation, change detection, anomaly detection, as well as image preparation tasks such as deconvolution, super-resolution and denoising.
The research in this field is aiming at improving current satellite image processing algorithms thanks to the recent advances in artificial intelligence, as well as exploring innovative imaging techniques. Traditionally, most tasks are performed after satellite data are transmitted to ground, incurring a high latency before processed images become available. An interesting research direction explores the possibility of performing some image processing tasks directly onboard the satellite, thereby obtaining very low latency in the detection of events of interest (e.g., fires and floods).

ERC sectors 

  • PE7_7 Signal processing
  • PE6_1 Computer architecture, embedded systems, operating systems
  • PE6_5 Security, privacy, cryptology, quantum cryptography
  • PE6_7 Artificial intelligence, intelligent systems, natural language processing
  • PE6_8 Computer graphics, computer vision, multimedia, computer games
  • PE6_11 Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)


  • Earth observation
  • Classification
  • Segmentation
  • Super-resolution
  • Denoising
  • On-board processing