Description du sujet de thèse

The goal of this PhD thesis is to contribute to BNN (Binarized Neural Networks) applied to event data. To this end, we are looking first to build light BNN architectures, with abilities such as focalisation and partial inference. Second, to validate various manners to represent the events as an input tensor for the network, with and without memory abilities. Proposed architectures will be validated and evaluated on several dataset in order to compare them with the state-of-the-art. Real experiments with lab's vehicles can be done.

Contexte de travail

Our laboratory is specialized in mobile robots control, such as intelligent cars and drones. We focus on problems that cover command, localization, communication, perception, as well as virtual reality. The laboratory has robotized vehicles equipped with various sensors, a track, simulators, and an aviary. Our team is involved in the SIVALab common laboratory between UTC, CNRS and Renault (Ampere).
Our team develops strong knowledge in event-based vision since 2000, with results on applications such as calibration, optical flow, depth estimation, and mobile objects segmentation.

Le poste se situe dans un secteur relevant de la protection du potentiel scientifique et technique (PPST), et nécessite donc, conformément à la réglementation, que votre arrivée soit autorisée par l'autorité compétente du MESR.