Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention
In engineering practice, ground penetrating radar (GPR) records are often hindered by clutter resulting from uneven underground media distribution, affecting target signal characteristics and precise positioning. To address this issue, we propose a method combining deep learning preprocessing and re...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/7/1729 |
| _version_ | 1797607117663764480 |
|---|---|
| author | Yi Li Pengfei Dang Xiaohu Xu Jianwei Lei |
| author_facet | Yi Li Pengfei Dang Xiaohu Xu Jianwei Lei |
| author_sort | Yi Li |
| collection | DOAJ |
| description | In engineering practice, ground penetrating radar (GPR) records are often hindered by clutter resulting from uneven underground media distribution, affecting target signal characteristics and precise positioning. To address this issue, we propose a method combining deep learning preprocessing and reverse time migration (RTM) imaging. Our preprocessing approach introduces a novel deep learning framework for GPR clutter, enhancing the network’s feature-capture capability for target signals through the integration of a contextual feature fusion module (CFFM) and an enhanced spatial attention module (ESAM). The superiority and effectiveness of our algorithm are demonstrated by RTM imaging comparisons using synthetic and laboratory data. The processing of actual road data further confirms the algorithm’s significant potential for practical engineering applications. |
| first_indexed | 2024-03-11T05:26:43Z |
| format | Article |
| id | doaj.art-5ff5370626bf44ed883328705516721e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:26:43Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5ff5370626bf44ed883328705516721e2023-11-17T17:28:04ZengMDPI AGRemote Sensing2072-42922023-03-01157172910.3390/rs15071729Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial AttentionYi Li0Pengfei Dang1Xiaohu Xu2Jianwei Lei3School of Civil Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Civil Engineering, Guangzhou University, Guangzhou 510006, ChinaGold Leaf Production and Mamufacturing Center, China Tobacco Henan Industrial Co., Ltd., Zhengzhou 450000, ChinaSchool of Water Conservancy and Civil Engineering, Zhengzhou University, Zhengzhou 450001, ChinaIn engineering practice, ground penetrating radar (GPR) records are often hindered by clutter resulting from uneven underground media distribution, affecting target signal characteristics and precise positioning. To address this issue, we propose a method combining deep learning preprocessing and reverse time migration (RTM) imaging. Our preprocessing approach introduces a novel deep learning framework for GPR clutter, enhancing the network’s feature-capture capability for target signals through the integration of a contextual feature fusion module (CFFM) and an enhanced spatial attention module (ESAM). The superiority and effectiveness of our algorithm are demonstrated by RTM imaging comparisons using synthetic and laboratory data. The processing of actual road data further confirms the algorithm’s significant potential for practical engineering applications.https://www.mdpi.com/2072-4292/15/7/1729ground-penetrating radar (GPR)contextual feature fusion module (CFFM)enhanced spatial attention module (ESAM)clutter removalreverse time migration (RTM) |
| spellingShingle | Yi Li Pengfei Dang Xiaohu Xu Jianwei Lei Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention Remote Sensing ground-penetrating radar (GPR) contextual feature fusion module (CFFM) enhanced spatial attention module (ESAM) clutter removal reverse time migration (RTM) |
| title | Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention |
| title_full | Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention |
| title_fullStr | Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention |
| title_full_unstemmed | Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention |
| title_short | Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention |
| title_sort | deep learning for improved subsurface imaging enhancing gpr clutter removal performance using contextual feature fusion and enhanced spatial attention |
| topic | ground-penetrating radar (GPR) contextual feature fusion module (CFFM) enhanced spatial attention module (ESAM) clutter removal reverse time migration (RTM) |
| url | https://www.mdpi.com/2072-4292/15/7/1729 |
| work_keys_str_mv | AT yili deeplearningforimprovedsubsurfaceimagingenhancinggprclutterremovalperformanceusingcontextualfeaturefusionandenhancedspatialattention AT pengfeidang deeplearningforimprovedsubsurfaceimagingenhancinggprclutterremovalperformanceusingcontextualfeaturefusionandenhancedspatialattention AT xiaohuxu deeplearningforimprovedsubsurfaceimagingenhancinggprclutterremovalperformanceusingcontextualfeaturefusionandenhancedspatialattention AT jianweilei deeplearningforimprovedsubsurfaceimagingenhancinggprclutterremovalperformanceusingcontextualfeaturefusionandenhancedspatialattention |