Print Email Facebook Twitter A deep-learning method for radar micro-doppler spectrogram restoration Title A deep-learning method for radar micro-doppler spectrogram restoration Author He, Yuan (Beijing University of Posts and Telecommunications) Li, Xinyu (Beijing University of Posts and Telecommunications) Li, Runlong (Beijing University of Posts and Telecommunications) Wang, J. (TU Delft Microwave Sensing, Signals & Systems) Jing, Xiaojun (Beijing University of Posts and Telecommunications) Date 2020 Abstract Radio frequency interference, which makes it difficult to produce high-quality radar spectrograms, is a major issue for micro-Doppler-based human activity recognition (HAR). In this paper, we propose a deep-learning-based method to detect and cut out the interference in spectrograms. Then, we restore the spectrograms in the cut-out region. First, a fully convolutional neural network (FCN) is employed to detect and remove the interference. Then, a coarse-to-fine generative adversarial network (GAN) is proposed to restore the part of the spectrogram that is affected by the interferences. The simulated motion capture (MOCAP) spectrograms and the measured radar spectrograms with interference are used to verify the proposed method. Experimental results from both qualitative and quantitative perspectives show that the proposed method can mitigate the interference and restore high-quality radar spectrograms. Furthermore, the comparison experiments also demonstrate the efficiency of the proposed approach. Subject Fully convolutional networkGenerative adversarial networkImage restorationRadar micro-doppler spectrogram To reference this document use: http://resolver.tudelft.nl/uuid:a5ab144e-5f12-4fff-9a98-119bfced7932 DOI https://doi.org/10.3390/s20175007 ISSN 1424-8220 Source Sensors, 20 (17), 1-15 Part of collection Institutional Repository Document type journal article Rights © 2020 Yuan He, Xinyu Li, Runlong Li, J. Wang, Xiaojun Jing Files PDF sensors_20_05007_v2.pdf 10.54 MB Close viewer /islandora/object/uuid:a5ab144e-5f12-4fff-9a98-119bfced7932/datastream/OBJ/view