eprintid: 10136070 rev_number: 20 eprint_status: archive userid: 608 dir: disk0/10/13/60/70 datestamp: 2021-10-11 10:41:14 lastmod: 2024-09-20 14:13:36 status_changed: 2021-10-11 10:41:14 type: article metadata_visibility: show creators_name: Tang, C creators_name: Li, W creators_name: Vishwakarma, S creators_name: Shi, F creators_name: Julier, S creators_name: Chetty, K title: FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 divisions: F52 keywords: Micro-Doppler Spectrogram, Adversarial Autoencoder, Variational Autoencoder, Feature Mapping, Passive WiFi Radar, Deep Learning, Activity Classification note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Micro-Doppler signatures contain considerable information about target dynamics. However, the radar sensing systems are easily affected by noisy surroundings, resulting in uninterpretable motion patterns on the micro-Doppler spectrogram. Meanwhile, radar returns often suffer from multipath, clutter and interference. These issues lead to difficulty in, for example motion feature extraction, activity classification using micro Doppler signatures (µ-DS), etc. In this paper, we propose a latent feature-wise mapping strategy, called Feature Mapping Network (FMNet), to transform measured spectrograms so that they more closely resemble the output from a simulation under the same conditions. Based on measured spectrogram and the matched simulated data, our framework contains three parts: an Encoder which is used to extract latent representations/features, a Decoder outputs reconstructed spectrogram according to the latent features, and a Discriminator minimizes the distance of latent features of measured and simulated data. We demonstrate the FMNet with six activities data and two experimental scenarios, and final results show strong enhanced patterns and can keep actual motion information to the greatest extent. On the other hand, we also propose a novel idea which trains a classifier with only simulated data and predicts new measured samples after cleaning them up with the FMNet. From final classification results, we can see significant improvements. date: 2021-11 date_type: published official_url: https://doi.org/10.1109/TGRS.2021.3121211 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1877159 doi: 10.1109/TGRS.2021.3121211 lyricists_name: Chetty, Kevin lyricists_name: Julier, Simon lyricists_name: Vishwakarma, Shelly lyricists_id: KCHET45 lyricists_id: SJULI23 lyricists_id: SVISH21 actors_name: Chetty, Kevin actors_id: KCHET45 actors_role: owner full_text_status: public publication: IEEE Transactions on Geoscience and Remote Sensing volume: 60 article_number: 5106612 citation: Tang, C; Li, W; Vishwakarma, S; Shi, F; Julier, S; Chetty, K; (2021) FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram. IEEE Transactions on Geoscience and Remote Sensing , 60 , Article 5106612. 10.1109/TGRS.2021.3121211 <https://doi.org/10.1109/TGRS.2021.3121211>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10136070/1/FMNet%20Paper.pdf