Radar Signal Processing for Fall Motion Detection
Master thesis, Proseminar, Seminar paper, Bachelor thesis
Detecting falls of elderly persons remains a challenging problem. Here, radar provides a non-obstrusive, safe and reliable technology to detect fall motions. In the near future, radar signal processing for fall motion detection will be a key technology for assisted living. Radar systems as small as the palm of your hand will be installed in apartments to monitor the motions of the elderly person.
Each motion induces characteristic Doppler frequency shifts in the radar return signal. They form the so-called micro-Doppler signatures in the time-frequency domain. These micro-Doppler signatures can be used to classify the motion, i.e. to identify whether a person is walking normally, limping or walking with a cane for example. However, motions such as fast sitting and falling can be mistaken for one another as both motions reveal similar Doppler signatures. Thus, the challenge remains to classify human motions correctly and, in particular, reduce the false alarm rate in fall motion detection.
Students participating in this project will learn about detection and estimation theory focusing on micro- Doppler analysis. In particular, the project is about radar-based human gait analysis and fall motion detection. Students will learn about time-frequency analysis for signal processing. Using real measurement data, we consider the short-time Fourier transform or spectrogram to discriminate different micro-Doppler signatures. In order to classify the motion, features are extracted from the spectrogram and fed to a classifier. Taking the spectrogram as an image, also image processing techniques can be used for feature extraction and classification.
Expected gain of knowledge
Depending on the student’s knowledge and interest, an individual topic for a student project can be discussed.