The identification of buried cables, pipes, conduits, and other cylindrical utilities is a very important task in civil engineering. In the last years, several methods have been proposed in the literature for tackling this problem. Most commonly employed approaches are based on the use of Ground Penetrating Radars, i.e., they extract the needed information about the unknown scenario starting from the electromagnetic field collected by a set of antennas. In the present paper, a statistical method, based on the use of smart antenna techniques, is used for the localization of a single buried object. In particular, two efficient algorithms for the estimation of the directions of arrival of the electromagnetic waves scattered by the targets, namely the MUltiple SIgnal Classification and the Support Vector Regression, are considered and their performances are compared. © 2013 Elsevier B.V.
Detection of subsurface metallic utilities by means of a SAP technique: Comparing MUSIC- and SVM-based approaches / Meschino, Simone; Pajewski, Lara; Pastorino, Matteo; Randazzo, Andrea; Schettini, Giuseppe. - In: JOURNAL OF APPLIED GEOPHYSICS. - ISSN 0926-9851. - STAMPA. - 97:(2013), pp. 60-68. [10.1016/j.jappgeo.2013.01.011]
Detection of subsurface metallic utilities by means of a SAP technique: Comparing MUSIC- and SVM-based approaches
PAJEWSKI, Lara;
2013
Abstract
The identification of buried cables, pipes, conduits, and other cylindrical utilities is a very important task in civil engineering. In the last years, several methods have been proposed in the literature for tackling this problem. Most commonly employed approaches are based on the use of Ground Penetrating Radars, i.e., they extract the needed information about the unknown scenario starting from the electromagnetic field collected by a set of antennas. In the present paper, a statistical method, based on the use of smart antenna techniques, is used for the localization of a single buried object. In particular, two efficient algorithms for the estimation of the directions of arrival of the electromagnetic waves scattered by the targets, namely the MUltiple SIgnal Classification and the Support Vector Regression, are considered and their performances are compared. © 2013 Elsevier B.V.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.