Search for: All records

COVID-19, caused by SARS-CoV-2, is now a global pandemic disease. This outbreak has affected every aspect of life including work, leisure, and interaction with technology. Governments around the world have issued orders for travel bans, social distancing, and lockdown to control the spread of the virus and prevent strain on hospitals. This paper explores potential applications for radar-based non-contact remote respiration sensing technology that may help to combat the COVID-19 pandemic, and outlines potential advantages that may also help to reduce the spread of the virus. Applications arising from recent developments in the state of the art for transceiver and signal processing technologies will be discussed along associated technical implications. These applications include remote breathing rate monitoring, continuous identity authentication, occupancy detection, and hand gesture recognition. This paper also highlights future research directions that must be explored further to bring this innovative non-contact sensor technology into real-world implementation. 

Deep neural networks have become increasingly popular in radar micro-Doppler classification; yet, a key challenge, which has limited potential gains, is the lack of large amounts of measured data that can facilitate the design of deeper networks with greater robustness and performance. Several approaches have been proposed in the literature to address this problem, such as unsupervised pre-training and transfer learning from optical imagery or synthetic RF data. This work investigates an alternative approach to training which involves exploitation of “datasets of opportunity” – micro-Doppler datasets collected using other RF sensors, which may be of a different frequency, bandwidth or waveform - for the purposes of training. Specifically, this work compares in detail the cross-frequency training degradation incurred for several different training approaches and deep neural network (DNN) architectures. Results show a 70% drop in classification accuracy when the RF sensors for pre-training, fine-tuning, and testing are different, and a 15% degradation when only the pre-training data is different, but the fine-tuning and test data are from the same sensor. By using generative adversarial networks (GANs), a large amount of synthetic data is generated for pre-training. Results show that cross-frequency performance degradation is reduced by 50% when kinematically-sifted GAN-synthesized signatures are used in pre-training.