Last week, I participated at the “Journée Futur & Ruptures” organized by the fondation which finances half of my PhD (the other half being financed by the CNES).
This year, I was asked to prepare a demo. I did some kind of an interactive class that leads to the model I have been working on in the past months. The goal is to detect water in SWOT images.
You can find it here. Do not hesitate to contact me if you have remarks or if you find a bug.
Last october, I participated to the “Journées CNES Jeunes Chercheurs 2016” (JC2
), where I had the chance to give a short talk and present a poster about the work I have done so far at my PhD. It was a great opportunity for me to present my work to talented scientists from very different fields!
As this poster sum up what I have been up to, I thought it would be nice to put it here.
Unfortunately, it is in French… If you only speak english (or want more details!), feel free to take a look at the updated publiactions page!
Here it is: (if the viewer do not work, please click here
In may 2016, I went through the mid-term evaluation of my PhD. The jury was composed of:
The evaluation is done based on a report and a small defense.
The report is available here. It is a summary of what we have done since the start of my PhD. Feel free to read it and ask questions about it !
I did an oral presentation at RFIA 2016 at the begining of the month.
RFIA is a french conference (held at Clermont-Ferrand this year) about pattern recognition and artificial intelligence. My presentation was on “Un modèle de décomposition pour la détection de changement dans les séries temporelles d’images RSO” and the proceedings can be found in the publication section of this website.
My paper on Multi-temporal SAR image decomposition into strong scatterers, background, and speckle have been accepted at JSTARS.
It will feature a multitemporal decomposition model, that is able to take into account the scatterers that are present in SAR urban images. The model allows for the use of the L0 pseudo-norm for the detection of the scatterers and a prior using the Total Variation (TV) on the image. The optimum solution can be found exactly thanks to Graph-cut optimization. We also show two applications of the model: one for change detection, the other for regularization.
A draft of this paper will be soon available in the publications section.