A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909179878309888 |
|---|---|
| author | Czerkawski, Mikolaj Ilioudis, Christos Clemente, Carmine Michie, Craig Andonovic, Ivan Tachtatzis, Christos |
| author_facet | Czerkawski, Mikolaj Ilioudis, Christos Clemente, Carmine Michie, Craig Andonovic, Ivan Tachtatzis, Christos |
| contents | Deep learning techniques are subject to increasing adoption for a wide range of micro-Doppler applications, where predictions need to be made based on time-frequency signal representations. Most, if not all, of the reported applications focus on translating an existing deep learning framework to this new domain with no adjustment made to the objective function. This practice results in a missed opportunity to encourage the model to prioritize features that are particularly relevant for micro-Doppler applications. Thus the paper introduces a micro-Doppler coherence loss, minimized when the normalized power of micro-Doppler oscillatory components between input and output is matched. The experiments conducted on real data show that the application of the introduced loss results in models more resilient to noise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15346 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications Czerkawski, Mikolaj Ilioudis, Christos Clemente, Carmine Michie, Craig Andonovic, Ivan Tachtatzis, Christos Signal Processing Computer Vision and Pattern Recognition Machine Learning Deep learning techniques are subject to increasing adoption for a wide range of micro-Doppler applications, where predictions need to be made based on time-frequency signal representations. Most, if not all, of the reported applications focus on translating an existing deep learning framework to this new domain with no adjustment made to the objective function. This practice results in a missed opportunity to encourage the model to prioritize features that are particularly relevant for micro-Doppler applications. Thus the paper introduces a micro-Doppler coherence loss, minimized when the normalized power of micro-Doppler oscillatory components between input and output is matched. The experiments conducted on real data show that the application of the introduced loss results in models more resilient to noise. |
| title | A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications |
| topic | Signal Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.15346 |