SOUSSE
I am currently a postdoctoral researcher (Deep Learning for Autonomous Vehicles) at the University of Clermont Auvergne, Clermont-Ferrand, France. I have received the engineer degree in Computer Science and the master degree in Intelligent and Communicating Systems from the National Engineering School of Sousse, University of Sousse, Tunisia, in 2012 and 2013, and the Ph.D. degree in Computer Sciences from the National Engineering School of Tunis, University of Tunis El Manar, Tunisia, in 2016. My research interests are in the areas of machine learning/Deep learning, Computer Vision, Signal, Image and Video Processing, Augmented Reality, Artificial Intelligence and Neural Networks.
During my first postdoctoral position in Institut Pascal lab, I have worked on two projects: Deep Learning for autonomous vehicles and Deep Learning for Brain MRI Segmentation. Deep learning has revolutionized the self-driving technology space along the last years. In particular, the perception capabilities of autonomous cars have been dramatically boosted by Deep Learning techniques, leading to a much better understanding of traffic scenes from vision, LiDAR and information. Object detection and semantic segmentation are two fundamental problems for scene understanding in computer vision.
In the tRuSTING project "Deep Learning for autonomous vehicles: Reliable and Safe long-term
auTonomy for Intelligent Navigation based on Generic approach (tRuSTING)", the goal is to design
and develop a perception-based self-driving system for urban scenarios. We have proposed a deep
architecture that jointly performs object detection and semantic segmentation in one forward pass
allowing real-time computations. Besides the computational gain of having a single network to
perform several tasks, we show that object detection and semantic segmentation benefit from each
other in terms of accuracy.
After this project I joined the DEEP-BLearning project (“Segmentation of brain MRI structures with deep learning: DEEP BRAIN LEARNING ”) which focused on the development of innovative methods for segmentation of brain MRI structures with deep machine learning. In this project, we propose to contribute to improving automatic deep brain segmentation by using 3D and fully convolutional neural network (3D-FCNN) on a unique dataset composed of expert labelling in different imaging modalities. Specifically, inspired by the recent success of dense networks, we propose an approach to 3D deep brain segmentation based on a volumetric FCNN.
In the next years I plan to continue my efforts in the broad field of artificial intelligence, machine learning/deep learning and Augmented Reality research. On the one hand, I want to focus on deep learning for self-driving cars. Autonomous learning, which is a variant of self-supervised learning involving deep learning and unsupervised methods, has also been applied to robot and control tasks.
By adding more intelligence, machines can move beyond the ability to perform repetitive tasks, and
it opens up more areas where they can be used. On the other hand, I want to focus on Deep
Learning for Medical Image Analysis(Medical Image segmentation.
Mes compétences :
Video Processing
Vision
Réalité augmentée
Machine Learning
Intelligence artificielle
Deep learning
