Feature-Based Registration for 3D Eddy Current Pulsed Thermography

Abstract

Measurement and quantification of defects are the key challenges for eddy current pulsed thermography (ECPT), localization and detection of surface, sub-surface defects, and the quantification of the defects under complex geometry in particular. To address this issue, this paper proposed a 3D eddy current pulsed thermography system by integration the ECPT system with an RGB-D (3D point cloud with RGB texture information) camera. The thermal image is mapped with the RGB-D image via matched features from the thermal and visible image. In order to establish reliable key-point matches for multi-spectrum image registration, a new shape constrained scale-invariant feature transform (SCSIFT) descriptor is proposed, which adds global shape information to SIFT descriptor. The experimental study has validated that the developed feature matching algorithm for the mapping of the thermal image with RGB-D image. The newly developed 3D ECPT system provides quantified data, including 3D heat distribution and the 3D spatial relationship between defect position, the excitation coil, and the whole specimen, which shows its potential of quantitative evaluation of the defect characteristics.