[2020-21, with Thales NL] Target tracking and classification based on kinematic information using recurrent neural networks

In the framework of target classification using kinematic information, targets’ states available during the tracking phase represent the main information available. Besides existing tracking techniques, new approaches based on machine learning techniques are acquiring more and more attention.
Specifically neural networks have shown to have large potential in dealing with complex problems associated with tracking and classification. Especially specific neural networks have the capability to preserve relevant information that is contained in a sequence of data.
The goal of the assignment consists in the definition and assessment of target tracking and classification techniques based on neural networks, especially for those cases that are particularly challenging for model-based approaches.

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