A pattern recognition system for extracting buried object characteristics in GPR images

Author

Pasolli, Edoardo ; Melgani, Farid ; Donelli, Massimo

Author_Institution

Dept. of Inf. Eng. & Comput. Sci., Univ. of Trento, Trento, Italy

Volume

4

fYear

2009

fDate

12-17 July 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.

Keywords

Gaussian processes; buried object detection; genetic algorithms; geophysical image processing; geophysical techniques; ground penetrating radar; image segmentation; radar imaging; regression analysis; support vector machines; GPR images; Gaussian process regression; buried object characteristics extraction; genetic algorithm; ground penetrating radar; hyperbolic pattern localization; image processing; image segmentation; linear pattern localization; object classification; object detection; object dimension estimation; object material recognition; pattern recognition system; support vector machine classifier; Buried object detection; Genetic algorithms; Ground penetrating radar; Image analysis; Image segmentation; Object detection; Pattern analysis; Pattern recognition; Support vector machine classification; Support vector machines; Buried objects; Gaussian process regression; feature extraction; ground penetrating radar; image analysis; pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium,2009 IEEE International,IGARSS 2009

Conference_Location

Cape Town

Print_ISBN

978-1-4244-3394-0

Electronic_ISBN

978-1-4244-3395-7

Type

conf

DOI

10.1109/IGARSS.2009.5417405

Filename

5417405