Fourth International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 2005)
Six methods for endoscopic motion compensation for laryngeal high-speed videoendoscopy (HSV) are compared. Two of them are based on tracking the maximum of the cross-correlation function of two images; two are based on minimization of the L2norm and L2-like distance between two images; and the other two make use of the peak present in the cross-power FFT-based spectrum of two images. All six methods are applied to compensate the motion, at the sub-pixel level, of the endoscopic lens relative to the vocal folds in HSV recordings. The new motion compensation methods based on FFT cross-power spectrum demonstrated remarkable computational speed and acceptable accuracy. While accuracy was best for the L2-minimization techniques, they were slower and had a limited motiontracking range.
Full Paper (reprinted with permission from Firenze University Press)
Bibliographic reference. Cieciwa, Szymon / Deliyski, Dimitar D. / Zielinski, Tomasz P. (2005): "Fast FFT-based motion compensation for laryngeal high-speed videoendoscopy", In MAVEBA-2005, 129-132.