Abstract
Traditional clutter removal methods struggle with complex clutter and multiple targets in Ground-Penetrating Radar images. This study proposes using B-spline activation functions in the deep-learning models to improve clutter removal in GPR. Experimental results demonstrate that B-spline-enhanced models outperform their ReLU-based counterparts, with improvements of up to 2.20% in PSNR, 0.035% in MS-SSIM, and 15.83% in SCR, showcasing their potential for real-world GPR applications.
| Original language | English |
|---|---|
| Title of host publication | 2024 32nd Telecommunications Forum, TELFOR 2024 - Proceedings of Papers |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9798350391053 |
| DOIs | |
| Publication status | Published - 2024 |
| Event | 32nd Telecommunications Forum, TELFOR 2024 - Belgrade, Serbia Duration: 26 Nov 2024 → 27 Nov 2024 |
Publication series
| Name | 2024 32nd Telecommunications Forum, TELFOR 2024 - Proceedings of Papers |
|---|
Conference
| Conference | 32nd Telecommunications Forum, TELFOR 2024 |
|---|---|
| Country/Territory | Serbia |
| City | Belgrade |
| Period | 26/11/24 → 27/11/24 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
Keywords
- B-splines
- Clutter removal
- deep learning
- ground-penetrating radar