PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Successful maintenance and development of underground infrastructures depends on the ability to access underground utilities efficiently. In general, obtaining accurate positions and conditions of subterranean utilities is not trivial due to inaccurate data records and occlusions that are common in densely populated urban areas. Limited access to underground resources poses challenges to underground utilities management. Ground-penetrating radar (GPR) is an effective sensing tools widely used for underground sensing. Combining high accuracy GPR data and augmented reality (AR) poses enables accurate real time visualizations of the buried objects. Although GPR and AR collect and visualize high accuracy data, intensive computation is required. This work presents a novel GPR-AR system that decreases post-processing time significantly while maintaining a neutral format across GPR-AR data collection methods regardless of varying Internet or GPS connection strengths. The methods explored in this work to mitigate failures of previous systems include automated and georeferenced post processing, the classification of underground assets using artificial intelligence, and real time data collection path visualizations. This work also lays a foundation for the potential combinations of a 5G GPR-AR system in which the temporal gap between data collection and visualization can be alleviated.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Joshua Childs, Dan Orfeo, Dylan Burns, Dryver Huston, Tian Xia, "Enhancing ground penetrating radar with augmented reality systems for underground utility management," Proc. SPIE 11426, Virtual, Augmented, and Mixed Reality (XR) Technology for Multi-Domain Operations, 1142608 (23 April 2020); https://doi.org/10.1117/12.2561042