A deep-learning method for radar micro-doppler spectrogram restoration

Yuan He, Xinyu Li, Runlong Li, Jianping Wang, Xiaojun Jing

Research output: Contribution to journalArticleScientificpeer-review

3 Downloads (Pure)


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.

Original languageEnglish
Article number5007
Pages (from-to)1-15
Number of pages15
JournalSensors (Switzerland)
Issue number17
Publication statusPublished - 2020


  • Fully convolutional network
  • Generative adversarial network
  • Image restoration
  • Radar micro-doppler spectrogram

Fingerprint Dive into the research topics of 'A deep-learning method for radar micro-doppler spectrogram restoration'. Together they form a unique fingerprint.

Cite this