Kayacan, Yavuz EmreErer, Isin2026-01-312026-01-312024979835036560397983503655972835-009Xhttps://doi.org./10.1109/TSP63128.2024.10605982https://hdl.handle.net/20.500.12662/1072447th International Conference on Telecommunications and Signal Processing-TSP-Annual -- JUL 10-12, 2024 -- CZECH REPUBLICThe 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. 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).eninfo:eu-repo/semantics/closedAccessGround Penetrating Radar (GPR)clutter removallow-rank approximationautoencodernonnegative matrix factorization (NMF)Conference Object10.1109/TSP63128.2024.10605982335332WOS:001594113800068N/A