|国家预印本平台
首页|Underground Mapping and Localization Based on Ground-Penetrating Radar

Underground Mapping and Localization Based on Ground-Penetrating Radar

Underground Mapping and Localization Based on Ground-Penetrating Radar

来源:Arxiv_logoArxiv
英文摘要

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.

Guoyu Lu、Jinchang Zhang

工程设计、工程测绘地球物理学计算技术、计算机技术

Guoyu Lu,Jinchang Zhang.Underground Mapping and Localization Based on Ground-Penetrating Radar[EB/OL].(2024-09-24)[2025-08-14].https://arxiv.org/abs/2409.16446.点此复制

评论