GPR-based Model Reconstruction System for Underground Utilities Using GPRNet

Ground Penetrating Radar (GPR) is one of the most important non-destructive evaluation (NDE) instruments to detect and locate underground objects (i.e. rebars, utility pipes). Many of the previous researches focus on GPR image-based feature detection only, and none can process sparse GPR measurements to successfully reconstruct a very fine and detailed 3D model of underground objects for better visualization. To address this problem, this paper presents a novel robotic system to collect GPR data, localize the underground utilities, and reconstruct the underground objects' dense point cloud model. This system is composed of three modules: 1) visual-inertial-based GPR data collection module which tags the GPR measurements with positioning information provided by an omnidirectional robot; 2) a deep neural network (DNN) migration module to interpret the raw GPR B-scan image into a cross-section of object model; 3) a DNN-based 3D reconstruction module, i.e., GPRNet, to generate underground utility model with the fine 3D point cloud. The experiments show that our method can generate a dense and complete point cloud model of pipe-shaped utilities based on a sparse input, i.e., GPR raw data, with various levels of incompleteness and noise. The experiment results on synthetic data as well as field test data verified the effectiveness of our method.

[1]  Mauricio Pereira,et al.  3D tomography for multistatic GPR subsurface sensing , 2018, Defense + Security.

[2]  Mohamed S. El-Mahallawy,et al.  Material Classification of Underground Utilities From GPR Images Using DCT-Based SVM Approach , 2013, IEEE Geoscience and Remote Sensing Letters.

[3]  Suyash P. Awate,et al.  Computer Vision, Graphics, and Image Processing , 2016, Lecture Notes in Computer Science.

[4]  Leiv-J. Gelius,et al.  Improving Kirchhoff migration with repeated local plane-wave imaging? A SAR-inspired signal-processing approach in prestack depth imaging , 2005 .

[5]  Bidyut Baran Chaudhuri,et al.  A survey of Hough Transform , 2015, Pattern Recognit..

[6]  Haiyan Wang,et al.  GPR-based Subsurface Object Detection and Reconstruction Using Random Motion and DepthNet , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Vipula Singh,et al.  Kirchhoff and F-K migration to focus ground penetrating radar images , 2016, International Journal of Geo-Engineering.

[8]  William A. Schneider,et al.  INTEGRAL FORMULATION FOR MIGRATION IN TWO AND THREE DIMENSIONS , 1978 .

[9]  Leonidas J. Guibas,et al.  Frustum PointNets for 3D Object Detection from RGB-D Data , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Farid Melgani,et al.  GPR B scan image analysis with deep learning methods , 2020 .

[11]  Martial Hebert,et al.  PCN: Point Completion Network , 2018, 2018 International Conference on 3D Vision (3DV).

[12]  Sevket Demirci,et al.  A STUDY ON MILLIMETER-WAVE IMAGING OF CONCEALED OBJECTS: APPLICATION USING BACK- PROJECTION ALGORITHM , 2012 .

[13]  Jie Gao,et al.  Autonomous pavement distress detection using ground penetrating radar and region-based deep learning , 2020 .

[14]  Biao Jiang,et al.  Wall-climbing robot for visual and GPR inspection , 2018, 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[15]  Yun-Kyu An,et al.  Deep learning-based automated underground cavity detection using three-dimensional ground penetrating radar , 2020, Structural Health Monitoring.

[16]  Silvio Savarese,et al.  TopNet: Structural Point Cloud Decoder , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  L. Pichon,et al.  Ground penetrating radar data imaging via Kirchhoff migration method , 2017, International Conference on Advances in Cybersecurity.

[18]  Xinyi Le,et al.  PF-Net: Point Fractal Network for 3D Point Cloud Completion , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[21]  Jon F. Claerbout,et al.  DOWNWARD CONTINUATION OF MOVEOUT‐CORRECTED SEISMOGRAMS , 1972 .

[22]  Dong Tian,et al.  FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[24]  Jenö Gazdag,et al.  Wave equation migration with the phase-shift method , 1978 .

[25]  Leonidas J. Guibas,et al.  Learning Representations and Generative Models for 3D Point Clouds , 2017, ICML.

[26]  Namgyu Kim,et al.  Three-dimensional convolutional neural network–based underground object classification using three-dimensional ground penetrating radar data , 2020 .

[27]  Hai Liu,et al.  Detection and localization of rebar in concrete by deep learning using ground penetrating radar , 2020 .

[28]  Sevket Demirci,et al.  Ground penetrating radar imaging of water leaks from buried pipes based on back-projection method , 2012 .