TY - JOUR A1 - Cotic, Patricia A1 - Jaglicic, Z. A1 - Niederleithinger, Ernst A1 - Stoppel, Markus A1 - Bosiljkov, V. T1 - Image fusion for improved detection of near-surface defects in NDT-CE using unsupervised clustering methods JF - Journal of nondestructive evaluation N2 - The capabilities of non-destructive testing (NDT) methods for defect detection in civil engineering are characterized by their different penetration depth, resolution and sensitivity to material properties. Therefore, in many cases multi-sensor NDT has to be performed, producing large data sets that require an efficient data evaluation framework. In this work an image fusion methodology is proposed based on unsupervised clustering methods. Their performance is evaluated on ground penetrating radar and infrared thermography data from laboratory concrete specimens with different simulated near-surface defects. It is shown that clustering could effectively partition the data for further feature level-based data fusion by improving the detectability of defects simulating delamination, voids and localized water. A comparison with supervised symbol level fusion shows that clustering-based fusion outperforms this, especially in situations with very limited knowledge about the material properties and depths of the defects. Additionally, clustering is successfully applied in a case study where a multi-sensor NDT data set was automatically collected by a self-navigating mobile robot system. KW - Non-destructive testing KW - Concrete KW - Defect detection KW - Data fusion KW - Cluster analysis KW - Image fusion KW - Thermography KW - Radar KW - Ultrasonics KW - Defects PY - 2014 DO - https://doi.org/10.1007/s10921-014-0232-1 SN - 0195-9298 SN - 1573-4862 VL - 33 IS - 3 SP - 384 EP - 397 PB - Plenum Press CY - New York, NY AN - OPUS4-33831 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Cotic, P. A1 - Jaglicic, Z. A1 - Bosiljkov, V. A1 - Niederleithinger, Ernst T1 - GPR an IR thermography for near-surface defect detection in building structures T2 - 12th International conference of the Slovenian society for non-destructive testing - Application of contemporary non-destructive testing in engineering N2 - Ground penetrating radar (GPR) and infrared (IR) thermography techniques have been used in many civil engineering applications for the structural visualization and defect detection. However, validation tests of the methods performance for the defection of defects in the nearsurface region with respect to the defects different material and depth below the surface are lacking. To overcome this, we performed GPR and IR thermography tests where the different material properties, shape and depth of defects were studied on concrete and the evaluation of seismic related damage propagation was assessed on stone masonry walls. The results showed that IR thermography, though being greatly affected by the presence of water in the specimen, outperformed GPR in the detection of defects very close to the surface. However, already at the depth of 3 cm and further up till almost 7.5 cm, the performance of GPR resembles the one of IR thermography for the detection of polystyrene (air) voids. On the plastered masonry walls, IR thermography could detect an air gap resulting from plaster delamination as small as 2 mm. Moreover, structural cracking resulting from the induced lateral load could be detected at an early stage. T2 - 12th International conference of the Slovenian society for non-destructive testing - Application of contemporary non-destructive testing in engineering CY - Ljubljana, Slovenia DA - 04.09.2013 KW - Radar KW - Thermography KW - Defects KW - Non-destructive testing validation KW - Concrete KW - Masonry KW - Near-surface defects KW - Ground PY - 2013 UR - http://www.ndt.net/article/ndt-slovenia2013/papers/225.pdf SP - 1 EP - 8 AN - OPUS4-33793 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -