IEEE Sensors Journal · 2020 · 31 citations · 26 references
EngineeringRadiologyBiomedical ImagingDigital ImagingMachine VisionImage ReconstructionImage RegistrationMotion CorrectionSpatial RegistrationDefects InspectionDistortionsImage Reconstruction AlgorithmsNon-destructive InspectionReconstruction AlgorithmsTemporal AlignmentThermographyVelocity Estimation
Line scanning thermography (LST) is a fast non-destructive inspection (NDI) method for large-scale components. However, the current reconstruction algorithms for LST require the match between the frame rate and the scanning velocity. Moreover, these algorithms bring in spatial distortions. This paper proposes a non-orthogonal reconstructed space for LST. In such a space, the excitation motion in the line scanning process is described as a function of time delay, the moving velocity is estimated by the derived position map, and the reconstruction is achieved by image registration. The LST data are registered spatially by allowing the temporal misalignment among the pixels within the same reconstructed frame. The effectiveness of the proposed reconstruction algorithm is validated by both numerical simulations and experiments. The reconstruction results of experimental data indicate that the velocity is finely estimated so that the temporal alignment error is controlled within one pixel. Besides, no spatial distortions occur no matter how the frame rate and scanning velocity change. Furthermore, the Fourier phase image of the reconstructed LST reaches the diameter-to-depth ratio of 1.25 when inspecting a planar specimen with flat-bottom holes.
26
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text
The PASCAL visual object classes challenge 2006 (VOC2006) results
Mark Everingham, Andrew Zisserman, Christopher K. I. Williams et al. · 2006 · 2.1K citations