On input formats for radar Micro-Doppler signature processing by convolutional neural networks

Research output: Contribution to conferencePaperpeer-review

38 Downloads (Pure)


Convolutional neural networks have often been proposed for processing radar Micro-Doppler signatures, most commonly with the goal of classifying the signals. The majority of works tend to disregard phase information from the complex time-frequency representation. Here, the utility of the phase information, as well as the optimal format of the Doppler-time input for a convolutional neural network, is analysed. It is found that the performance achieved by convolutional neural network classifiers is heavily influenced by the type of input representation, even across formats with equivalent information. Furthermore, it is demonstrated that the phase component of the Doppler-time representation contains rich information useful for classification and that unwrapping the phase in the temporal dimension can improve the results compared to a magnitude-only solution, improving accuracy from 0.920 to 0.938 on the tested human activity dataset. Further improvement of 0.947 is achieved by training a linear classifier on embeddings from multiple-formats.
Original languageEnglish
Number of pages6
Publication statusPublished - 27 Oct 2022
EventRadar 2022, International Conference on Radar Systems - Murrayfield Stadium, Edinburgh, United Kingdom
Duration: 24 Oct 202227 Oct 2022


ConferenceRadar 2022, International Conference on Radar Systems
Country/TerritoryUnited Kingdom
Internet address


  • automatic target recognition
  • convolutional neural networks
  • classification
  • spectrogram


Dive into the research topics of 'On input formats for radar Micro-Doppler signature processing by convolutional neural networks'. Together they form a unique fingerprint.

Cite this