GPR Data Reconstruction Using Residual Feature Distillation Block U-Net

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing 2023-01, Vol.16, p.1-11
• Main Authors: Dai, Qianwei, He, Yue, Lei, Yi, Lei, Jianwei, Wang, Xiangyu, Zhang, Bin
• Format: Article
• Language: English
• Subjects: Convolution; Data models; Deep learning; Distillation; Distilling; Feature extraction; Geology; GPR; Ground penetrating radar; ground penetrating radar (GPR); Image reconstruction; Missing traces; Radar; Reconstruction; residual feature distillation block U-Net (RFDB-U-net); RFDB-U-Net; Signal to noise ratio; Surveys; Synthetic data; Training; Transmission loss; Unevenness
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2023.3276161

Due to the unevenness of ground surface, mismatch between trig interval and sampling speed, or other electromagnetic interferences, traces missing is a quite typical occurrence during the on-ground ground penetrating radar (GPR) testing. Effective reconstruction of GPR missing traces has been regarded a crucial link to improve both the signal-to-noise ratio of raw data and the resolution of GPR imaging. In this paper, we propose a novel deep-learning framework based on the residual feature distillation block U-Net (RFDB-U-Net) to mitigate the transmission loss problem of the conventional U-Net. To be specific, by employing the information distillation network based on the multiple feature extraction connections, RFDB is capable of utilizing the adequate residual information of each layer for feature learning. Moreover, a skip connection is additional patched on the residual units to properly compensate the missing features in the convolution process. In particular, the merging of lightweight U-Net ensures the lightness of RFDB. The outperformance of the proposed framework is verified in detail through the reconstruction accuracy and evaluation metrics in the test of synthetic data, laboratorial data and in-site field data.