[2020-21, with Thales NL] Cross-modal techniques with deep neural networks for robust sensor fusion

Deep learning techniques have been already introduced to achieve an efficient sensor fusion in order to enhance functionalities like target tracking and classification.
From a different perspective, the availability of multiple simultaneous information captured by different sensors, might provide an improved robustness of the overall systems, especially in the case of failure of one of the sensing nodes, or whether the captured measurements of one of the sensors do not contain relevant information to accurately perform the desired functionality.
The objective of the assignment consists in the definition of cross-modal techniques based on deep neural networks, specifically focusing on the enhancement of the robustness of system consisting on a camera and a radar, for the problem of human-gait classification.

Requirements

Due to the requirements of the project, nationality of EU or at least NATO country is required

Contact

dr. Francesco Fioranelli

Microwave Sensing, Signals and Systems Group

Department of Microelectronics

Last modified: 2021-01-19