In this work, we present a pattern recognition system for the automatic analysis of ground penetrating radar (GPR) images. This system comprises pre-processing, segmentation, object detection, object material recognition, and object dimension estimation stages. Object detection is done using an unsupervised strategy based on genetic algorithms (GA) which allows to localize linear/hyperbolic patterns in GPR images. Object material recognition is approached as a classification issue, which is solved by means of a support vector machine (SVM) classifier. Dimension estimation is formulated within a Gaussian process (GP) regression approach. Results on synthetic images, representing random exploration scenarios, are reported and discussed. ©2009 IEEE.
A pattern recognition system for extracting buried object characteristics in GPR images / Pasolli, E.; Melgani, F.; Donelli, M.. - 4:(2009), pp. IV430-IV433. (Intervento presentato al convegno 2009 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2009 tenutosi a Cape Town, zaf nel 2009) [10.1109/IGARSS.2009.5417405].
A pattern recognition system for extracting buried object characteristics in GPR images
Pasolli E.;
2009
Abstract
In this work, we present a pattern recognition system for the automatic analysis of ground penetrating radar (GPR) images. This system comprises pre-processing, segmentation, object detection, object material recognition, and object dimension estimation stages. Object detection is done using an unsupervised strategy based on genetic algorithms (GA) which allows to localize linear/hyperbolic patterns in GPR images. Object material recognition is approached as a classification issue, which is solved by means of a support vector machine (SVM) classifier. Dimension estimation is formulated within a Gaussian process (GP) regression approach. Results on synthetic images, representing random exploration scenarios, are reported and discussed. ©2009 IEEE.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
