|MURDACA GIANLUCA||Cycle: XXXVI|
Advisor: PRATI CLAUDIO MARIA
Tutor: MONTI-GUARNIERI ANDREA VIRGILIO
Major Research topic:
Deep Learning for multi-temporal SAR data processing
Begin a coherent system, Synthetic Aperture Radar (SAR) record both amplitude and phase of the backscattered echoes. Thus, the starting point of the proposed research project will be the investigation of the neural networks potential, with particular attention to Convolutional Neural Network (CNN), in the complex domain data processing. In order to compute multi-temporal SAR data-stack analysis, architectures able to process intensity image, interferograms and coherence images are required. For this purpose, Complex-Valued Convolutional Neural Network (CV-CNN) will be investigated as it allows to exhibit temporal dynamic behaviour of the network inputs .Then, an in-depth study will be done to exploit Deep Learning techniques in order to perform classical DSP task such as choerence estimation, phase filtering and phase linking. The results obtained will be compared, highlighting the advantages or disadvantages of the deep learning approach respect to the classic one and exploring the possibility to combine the two.;
These cookies are not optional. They are needed for the website to function.
In order for us to improve the website's functionality and structure, based on how the website is used.
In order for our website to perform as well as possible during your visit. If you refuse these cookies, some functionality will disappear from the website.
By sharing your interests and behavior as you visit our site, you increase the chance of seeing personalized content and offers.