Defect segmentation: Mapping tunnel lining internal defects with ground penetrating radar data using a convolutional neural network

This research proposes a Ground Penetrating Radar (GPR) data processing method for non-destructive detection of tunnel lining internal defects, called defect segmentation. To perform this critical step of automatic tunnel lining detection, the method uses a CNN called Segnet combined with the Lovasz softmax loss function to map the internal defect structure with GPR synthetic data, which improves the accuracy, automation and efficiency of defects detection. The novel method we present overcomes several difficulties of traditional GPR data interpretation as demonstrated by an evaluation on both synthetic and real datas -- to verify the method on real data, a test model containing a known defect was designed and built and GPR data was obtained and analyzed.

[1]  Farid Melgani,et al.  Automatic Analysis of GPR Images: A Pattern-Recognition Approach , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Yangkang Chen,et al.  Deep-learning seismic full-waveform inversion for realistic structural models , 2020 .

[3]  D. Mao,et al.  A rapid four-dimensional resistivity data inversion method using temporal segmentation , 2020 .

[4]  Jing Wang,et al.  Application of ground penetrating radar to detect tunnel lining defects based on improved full waveform inversion and reverse time migration , 2019, Near Surface Geophysics.

[5]  Jing Wang,et al.  Automatic Recognition of Highway Tunnel Defects Based on an Improved U-Net Model , 2019, IEEE Sensors Journal.

[6]  Matthew B. Blaschko,et al.  The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[8]  José García Rodríguez,et al.  A Review on Deep Learning Techniques Applied to Semantic Segmentation , 2017, ArXiv.

[9]  Yang Lei,et al.  Railway Subgrade Defect Automatic Recognition Method Based on Improved Faster R-CNN , 2018, Sci. Program..

[10]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[11]  Mohamed A. Meguid,et al.  The effect of erosion voids on existing tunnel linings , 2009 .

[12]  Jie Gao,et al.  Recognition, location, measurement, and 3D reconstruction of concealed cracks using convolutional neural networks , 2017 .

[13]  Patrick van der Smagt,et al.  CNN-based Segmentation of Medical Imaging Data , 2017, ArXiv.

[14]  A. J. Howard.  REPORT ON THE DAMAGING EFFECTS OF WATER ON TUNNELS DURNG THEIR WORKING LIFE , 1991 .

[15]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Pan Li,et al.  GPR identification of voids inside concrete based on the support vector machine algorithm , 2013 .

[17]  Peng Jiang,et al.  Deep-Learning Inversion of Seismic Data , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Young-Jin Cha,et al.  SDDNet: Real-Time Crack Segmentation , 2020, IEEE Transactions on Industrial Electronics.

[19]  Young-Jin Cha,et al.  Subsurface damage detection of a steel bridge using deep learning and uncooled micro-bolometer , 2019, Construction and Building Materials.

[20]  Y. Le Sant,et al.  An overview of infrared thermography techniques used in large wind tunnels , 2002 .

[21]  Huanhuan Chen,et al.  An Automatic GPR B-Scan Image Interpreting Model , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[22]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[23]  D. Kolymbas,et al.  Groundwater ingress to tunnels - The exact analytical solution , 2007 .

[24]  Shyam Lal,et al.  Dense Refinement Residual Network for Road Extraction From Aerial Imagery Data , 2019, IEEE Access.

[25]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Zheng Tong,et al.  Advances of deep learning applications in ground-penetrating radar: A survey , 2020 .

[27]  Petr Holub,et al.  Détection des cavités à l'aide de mesures électriques et du géoradar dans une galerie d'amenée d'eau , 1994 .

[28]  Peng Jiang,et al.  Deep Learning Inversion of Electrical Resistivity Data , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Anthony G. Cohn,et al.  GPRInvNet: Deep Learning-Based Ground-Penetrating Radar Data Inversion for Tunnel Linings , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Chi-Chih Chen,et al.  Ground penetrating radar for tunnel detection , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[31]  Yujing Jiang,et al.  Estimation of effect of voids on frequency response of mountain tunnel lining based on microtremor method , 2014 .

[32]  Malcolm K. Lim,et al.  RAPID AND ECONOMICAL EVALUATION OF CONCRETE TUNNEL LININGS WITH IMPULSE RESPONSE AND IMPULSE RADAR NONDESTRUCTIVE METHODS , 2005 .

[33]  Aixi Zhu,et al.  Efficient Crack Detection Method for Tunnel Lining Surface Cracks Based on Infrared Images , 2017, J. Comput. Civ. Eng..

[34]  Mansor Nakhkash,et al.  Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition , 2000 .

[35]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Oral Büyüköztürk,et al.  Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks , 2017, Comput. Aided Civ. Infrastructure Eng..

[37]  A. Marino,et al.  2010 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM , 2010, IGARSS 2010.

[38]  Stephen D. Gedney,et al.  Convolution PML (CPML): An efficient FDTD implementation of the CFS–PML for arbitrary media , 2000 .

[39]  Amir M. Alani,et al.  GPR Applications in Structural Detailing of a Major Tunnel Using Different Frequency Antenna Systems , 2018 .

[40]  Anthony G. Cohn,et al.  Real-Time Hyperbola Recognition and Fitting in GPR Data , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Fengshou Zhang,et al.  Application of ground penetrating radar in grouting evaluation for shield tunnel construction , 2010 .

[42]  Anders Krogh,et al.  A Simple Weight Decay Can Improve Generalization , 1991, NIPS.

[43]  J. A. Richards.  Inspection, maintenance and repair of tunnels: International lessons and practice , 1998 .

[44]  A. P. Annan,et al.  Ground-penetrating radar for high-resolution mapping of soil and rock stratigraphy , 1989 .

[45]  Oral Büyüköztürk,et al.  Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage Types , 2018, Comput. Aided Civ. Infrastructure Eng..

[46]  Joseph L. Rose,et al.  The behaviour of ultrasonic pulses in concrete , 1990 .

[47]  Yan Xu,et al.  Deep learning of feature representation with multiple instance learning for medical image analysis , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[48]  Nur Yazdani,et al.  Reinforced concrete mapping using full-waveform inversion of GPR data , 2019 .

[49]  Genshiro Kitagawa,et al.  A physical-model study of the statistics of seismic waveform fluctuations in random heterogeneous media , 2002 .