Abstract
The performance of low-rank and sparse decomposition (LRSD) based clutter removal methods which are widely used in GPR systems depends heavily on the regularization parameter. This study proposes a A parameter-free low-rank approach. The low-rank component recovered by an autoencoder (AE) network is subtracted from the raw image to provide a clutter-free image. Simulation and experimental results validate the superiority of the proposed method compared to the low-rank approach Nonnegative Matrix Factorization (NMF) as well as other LRSD methods: Robust Principal Component Analysis (RPCA), Robust NMF (RNMF), and Robust Autoencoder (RAE).
| Original language | English |
|---|---|
| Title of host publication | 2024 47th International Conference on Telecommunications and Signal Processing, TSP 2024 |
| Editors | Norbert Herencsar |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 332-335 |
| Number of pages | 4 |
| ISBN (Electronic) | 9798350365597 |
| DOIs | |
| Publication status | Published - 2024 |
| Event | 47th International Conference on Telecommunications and Signal Processing, TSP 2024 - Virtual, Online, Czech Republic Duration: 10 Jul 2024 → 12 Jul 2024 |
Publication series
| Name | 2024 47th International Conference on Telecommunications and Signal Processing, TSP 2024 |
|---|
Conference
| Conference | 47th International Conference on Telecommunications and Signal Processing, TSP 2024 |
|---|---|
| Country/Territory | Czech Republic |
| City | Virtual, Online |
| Period | 10/07/24 → 12/07/24 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
Keywords
- Ground Penetrating Radar (GPR)
- autoencoder
- clutter removal
- low-rank approximation
- nonnegative matrix factorization (NMF)