Title :
Detection of gradual transitions in video sequences using B-spline interpolation
Author :
Nam, JeHo ; Tewfik, Ahmed H.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Minnesota, Minneapolis, MN, USA
Abstract :
We present a novel technique for detecting the presence of a gradual transition in video sequences and automatically identifying its type. Our scheme focuses on analyzing the characteristics of the underlying special edit effects and estimates actual transitions by polynomial data interpolation. In particular, a B-spline interpolation curve fitting technique is used. We make use of "goodness" of fitting to determine the presence of gradual transitions. Our approach is able to recover the original transition behavior of an edit effect even if it is distorted by various post-processing stages. Our gradual transition detectors have been extensively tested on various genres of real video sequences to evaluate the performance of the proposed algorithms.
Keywords :
curve fitting; image sequences; polynomial approximation; splines (mathematics); video signal processing; wavelet transforms; B-spline interpolation; curve fitting technique; gradual scene changes; gradual transition detection; polynomial data interpolation; radon transform; shot boundary detection; temporal video segmentation; video sequences; wavelet representation; Continuous wavelet transforms; Curve fitting; Detectors; Gunshot detection systems; Interpolation; Layout; Polynomials; Spline; Testing; Video sequences; Dissolve; Radon transform; fade; gradual scene changes; shot boundary detection; splines; temporal video segmentation; wavelet representation; wipe;
Journal_Title :
Multimedia, IEEE Transactions on
DOI :
10.1109/TMM.2005.843362