A PATTERN RECOGNITION SYSTEM FOR EXTRACTING BURIED OBJECT CHARACTERISTICS IN GPR IMAGES

被引:3
作者
Pasolli, Edoardo [1 ]
Melgani, Farid [1 ]
Donelli, Massimo [1 ]
机构
[1] Univ Trento, Dept Informat Engn & Comp Sci, I-38050 Trento, Italy
来源
2009 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-5 | 2009年
关键词
Buried objects; feature extraction; Gaussian process regression; ground penetrating radar; image analysis; pattern recognition; RADAR;
D O I
10.1109/IGARSS.2009.5417405
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
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.
引用
收藏
页码:2810 / 2813
页数:4
相关论文
共 9 条
  • [1] The detection of buried pipes from time-of-flight radar data
    Borgioli, Giovanni
    Capineri, Lorenzo
    Falorni, PierLuigi
    Matucci, Serena
    Windsor, Colin G.
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2008, 46 (08): : 2254 - 2266
  • [2] An electromagnetic approach based on neural networks for the GPR investigation of buried cylinders
    Caorsi, S
    Cevini, G
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2005, 2 (01) : 3 - 7
  • [3] DOLGIY A, 2006, P 12 EUR M ENV ENG G
  • [4] Subsurface sensing of buried objects under a randomly rough surface using scattered electromagnetic field data
    Firoozabadi, Reza
    Miller, Eric L.
    Rappaport, Carey M.
    Morgenthaler, Ann W.
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (01): : 104 - 117
  • [5] Modelling ground penetrating radar by GprMax
    Giannopoulos, A
    [J]. CONSTRUCTION AND BUILDING MATERIALS, 2005, 19 (10) : 755 - 762
  • [6] Automatic Analysis of GPR Images: A Pattern-Recognition Approach
    Pasolli, Edoardo
    Melgani, Farid
    Donelli, Massimo
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2009, 47 (07): : 2206 - 2217
  • [7] PASOLLI L, 2008, P IGARSS 2008 BOST U, V2, P851
  • [8] Rasmussen CE, 2005, ADAPT COMPUT MACH LE, P1
  • [9] Radius estimation for cylindrical objects detected by ground penetrating radar
    Shihab S.
    Al-Nuaimy W.
    [J]. Subsurface Sensing Technologies and Applications, 2005, 6 (2): : 151 - 166