Underground Target Classification From Full-Polarimetric GPR Data Using Deep Convolutional Neural Network With Channel Attention Module

被引:0
作者
Li, Jingxia [1 ]
Li, Jiasu [1 ]
Huang, Zheng [1 ]
Qu, Yanlin [1 ]
Liu, Li [1 ]
Xu, Hang [1 ]
Wang, Bingjie [1 ]
机构
[1] Taiyuan Univ Technol, Coll Elect Informat & Opt Engn, Key Lab Adv Transducers & Intelligent Control Syst, Minist Educ & Shanxi Prov, Taiyuan 030024, Peoples R China
基金
中国国家自然科学基金;
关键词
Feature extraction; Convolution; Geoscience and remote sensing; Plastic products; Convolutional neural networks; Classification algorithms; Vectors; Channel attention module (CAM); deep convolution neural network; full-polarimetric data; ground penetrating radar (GPR); underground target classification;
D O I
10.1109/LGRS.2024.3400275
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Traditional single-polarimetric ground penetrating radar (GPR) has been widely used for the detection and classification of cavities, pipes, cables, and other subsurface objects. However, as these subsurface objects show similar hyperbolic patterns in B-scan images, their data interpretation remains a challenge. In this letter, we propose an underground target classification method based on full-polarimetric GPR data and a multibranch deep convolutional neural network (CNN) with channel attention modules (CAMs). Here, the full-polarimetric GPR data as input are separately sent into each branch of the network for feature extraction. The CAM is used to improve the network's sensitivity and processing of key features. After fusing these full-polarimetric features, underground target classification is achieved with high accuracy. Our experiments demonstrate that more target information can be obtained by applying full-polarimetric GPR data, which is beneficial for improving target classification accuracy.
引用
收藏
页码:1 / 5
页数:5
相关论文
共 20 条
[11]   Underground Object Classification Using Deep 3-D Convolutional Networks and Multiple Mirror Encoding for GPR Data [J].
Liu, Li ;
Yu, Hang ;
Xu, Hang ;
Wang, Bingjie ;
Li, Jingxia .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
[12]   GPR Data Interpretation Approaches in Archaeological Prospection [J].
Manataki, Merope ;
Vafidis, Antonis ;
Sarris, Apostolos .
APPLIED SCIENCES-BASEL, 2021, 11 (16)
[13]   Automatic Classification of Ground-Penetrating-Radar Signals for Railway-Ballast Assessment [J].
Shao, Wenbin ;
Bouzerdoum, Abdesselam ;
Son Lam Phung ;
Su, Lijun ;
Indraratna, Buddhima ;
Rujikiatkamjorn, Cholachat .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (10) :3961-3972
[14]   A Data Pair-Labeled Generalized Hough Transform for Radar Location of Buried Objects [J].
Windsor, C. G. ;
Capineri, L. ;
Falorni, P. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2014, 11 (01) :124-127
[15]   CBAM: Convolutional Block Attention Module [J].
Woo, Sanghyun ;
Park, Jongchan ;
Lee, Joon-Young ;
Kweon, In So .
COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :3-19
[16]   Pavement Distress Detection Using Three-Dimension Ground Penetrating Radar and Deep Learning [J].
Yang, Jiangang ;
Ruan, Kaiguo ;
Gao, Jie ;
Yang, Shenggang ;
Zhang, Lichao .
APPLIED SCIENCES-BASEL, 2022, 12 (11)
[17]  
Yang Zongkai, 2023, Proceedings of 2023 Chinese Intelligent Systems Conference: Volume III. Lecture Notes in Electrical Engineering (1091), P81, DOI 10.1007/978-981-99-6886-2_8
[18]  
Youn HS, 2004, PROCEEDINGS OF THE TENTH INTERNATIONAL CONFERENCE ON GROUND PENETRATING RADAR, VOLS 1 AND 2, P303
[19]   Full-Polarization Target Classification Using Single-Polarization Ground Penetrating Radars [J].
Yu, Yue ;
Chen, Chi-Chih .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[20]  
Zhou H., 2020, P 18 INT C GROUND PE, P408