Abstract
Ground penetrating radar (GPR) is used for nondestructive examination of utility present underground such as cables, pipes, and landmines. Cables and pipes make hyperbolic shape signatures in GPR radargrams. Automatic detection of hyperbolic signature narrow down the region of interest and therefore results in reduced data set for localization of the buried pipe. In this paper, a machine learning approach is used to detect hyperbolic signatures using a support vector machine (SVM) with the histogram of oriented gradient features (HOG). For this purpose, Voila Jones algorithm is used in Matlab to train a classifier with HOG features instead of haar features. The HOG features have not been used with SVM in the literature for hyperbolic signature detection in the ground penetrating radar (GPR) radargrams. In this paper, it is shown that HOG feature based classifier achieve a high detection rate of 0.758 with a low false positive rate of 0.394. The detection algorithm is tested on both real GPR data and synthetic GPR data. Synthetic GPR data is created on an open source software gprMax.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.