8 April 2016 Underground object characterization based on neural networks for ground penetrating radar data
Author Affiliations +
Abstract
In this paper, an object characterization method based on neural networks is developed for GPR subsurface imaging. Currently, most existing studies demonstrate detecting and imaging objects of cylindrical shapes. While in this paper, no restriction is imposed on the object shape. Three neural network algorithms are exploited to characterize different types of object signatures, including object shape, object material, object size, object depth and subsurface medium’s dielectric constant. Feature extraction is performed to characterize the instantaneous amplitude and time delay of the reflection signal from the object. The characterization method is evaluated utilizing the data synthesized with the finite-difference timedomain (FDTD) simulator.
Conference Presentation
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yu Zhang, Yu Zhang, Dryver Huston, Dryver Huston, Tian Xia, Tian Xia, "Underground object characterization based on neural networks for ground penetrating radar data", Proc. SPIE 9804, Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016, 980403 (8 April 2016); doi: 10.1117/12.2219345; https://doi.org/10.1117/12.2219345
PROCEEDINGS
9 PAGES + PRESENTATION

SHARE
Back to Top