Underground Mapping and Localization Based on Ground-Penetrating Radar
This addresses the problem of underground mapping and localization for applications such as infrastructure inspection and agriculture, representing an incremental advance by applying existing deep learning techniques to GPR data.
The paper tackles the challenge of 3D reconstruction of underground objects like plant roots and pipelines using Ground-Penetrating Radar (GPR), introducing a deep learning method that detects keypoints from B-scan images and performs point cloud segmentation and completion to generate accurate maps, with experimental results showing effectiveness.
3D object reconstruction based on deep neural networks has gained increasing attention in recent years. However, 3D reconstruction of underground objects to generate point cloud maps remains a challenge. Ground Penetrating Radar (GPR) is one of the most powerful and extensively used tools for detecting and locating underground objects such as plant root systems and pipelines, with its cost-effectiveness and continuously evolving technology. This paper introduces a parabolic signal detection network based on deep convolutional neural networks, utilizing B-scan images from GPR sensors. The detected keypoints can aid in accurately fitting parabolic curves used to interpret the original GPR B-scan images as cross-sections of the object model. Additionally, a multi-task point cloud network was designed to perform both point cloud segmentation and completion simultaneously, filling in sparse point cloud maps. For unknown locations, GPR A-scan data can be used to match corresponding A-scan data in the constructed map, pinpointing the position to verify the accuracy of the map construction by the model. Experimental results demonstrate the effectiveness of our method.