Remote Sensing for Earth Observation
Remote sensing based on multimodal images has a great value today, since we have more and more cameras on the boards of airplanes (including UAVs) and satellites. Application areas include surveillance, observation of protected natural reserves, traffic monitoring and automatic mapping and change detection.
In complex Geographic Information Systems (GIS) space borne, airborne and terrestrial RS data is jointly utilized. The processed sources are mostly multimodal optical imagery (in visible or infrared spectrum), Synthetic Aperture Radar (SAR), Digital Evaluation Model (DEM) synthesis, or LIght Detection And Ranging (LIDAR) scanning. Real-world challenges need an efficient collaboration of many approaches coming from diverse domains. To enable such integration, appropriate data description and handling models are required.
The different image sources can be joined in Markov Random Field approach, where this MRF model is segmented on the multiple sources by stochastic optimization, resulting in a fused model of MRF.
The proposed task of the applicant includes:
· Basic image processing and pattern recognition methodology
· Structuring Multilayer Markov Random Field models
· Machine Learning approaches, deep Neural Network solutions
· Semantic interpretation of image contents and change detection through image samples of different time instants
· The applicant should have good knowledge in image processing a machine learning;
· Good math, programming in MATLAB and C/C++.