GPU Based Implementation for the Pre-Processing of Radar-Based Human Activity Recognition

The correlation between an ageing population globally and the increased risk of falling is a real challenge for healthcare infrastructures. This calls for the development of new ways to monitor the elderly at home. The confidentiality of radar data coupled with its richness of information can address weaknesses of existing technologies, namely, privacy and acceptance. The radar data produce a large quantity of data that needs to be processed in real-time to ensure a timely detection of fall/critical events necessary for the well-being of the elderly. We introduce a new embedded architecture using a GPU allowing a gain in processing time compared to CPU alone. We used an off-the-shelf frequency-modulated continuous-wave (FMCW) radar (Ancortek model SDR 980AD2). It is followed by a pre-processing chain consisting of a Fast Fourier Transform, Filter and Short Time Fourier Transform (STFT) to obtain time-velocity maps or spectrograms to extract characteristics of human activities such as walking. An implementation with cuFFT on Jetson Xavier increases the performance margin for the downstream of the processing chain, the acceleration factor being 10.49 compared to state-of-the-art CPU architecture. Continuous monitoring of the subject will save lives, minimize injuries, reduce anxiety and prevent post-fall syndrome (PDS).