MSc thesis project proposal

[2020-21] Change of perspective: from images to sequences for radar classification

Radar is investigated for the classification of human activities and movements, as knowing what activities someone performs, when, where, and how often, can be a powerful indicator of his/her health status, both in terms of physical mobility and cognitive wellbeing.
As for any classification problem, recent techniques developed by the deep learning community are also of great interest to the radar researchers to process the radar data as images (using convolutional networks) or as time series of samples (using some form of recurrent networks).
However, a fundamental issue is that radar data are intrinsically different from optical images, video, audio, or language data. Radar data encode in their pixels and/or samples kinematic information about the targets, their position, their velocity, their bearing. Hence, simply “recycling” networks and algorithms designed for different types of data may not be the winning strategy. This project and its companion project investigate two interesting outstanding questions out of the many!

Project 2->When people move about, they perform activities and movements in a continuous manner: one walks, sits down, stand up, walk somewhere, does something with their hands and so on. Reality is continuous in time and so is the sequence of radar data collected. However, many approaches to analyse radar data for classification take “snapshots” of separate activities (see the spectrograms below). These are some of the research questions to tackle in this project. How to process and characterise a continuous sequence of radar data separating and classifying the different activities? Deep learning tools for sequence processing include recurrent neural networks of different kinds (LSTM, GRU), and the recent TCN, but how well do they work with radar data, and is there anything that we can do to make them work better? Is there anything in their architecture or training that we can change to be adapted to radar problems?

Requirements

Radar basics, MATLAB, Python (very desirable), basis of pattern recognition & AI

Contact

dr. Francesco Fioranelli

Microwave Sensing, Signals and Systems Group

Department of Microelectronics

Last modified: 2021-01-19