Title :
A New Approach to Gradual Video Transition Detection
Author :
Koumousis, K.I. ; Fotopoulos, V. ; Skodras, A.N.
Author_Institution :
Digital Syst. & Media Comput. Lab., Hellenic Open Univ., Patras, Greece
Abstract :
In this paper the problem of shot boundary detection for gradual transitions within video sequences is treated using statistical tests in conjunction with the Iterative Self Organizing Data Analysis (ISODATA) classification algorithm for consecutive video frames. The confusion matrix from the classification results is formed in order to calculate the kappa coefficient and from this to identify the transition. Experimental and comparative results with recently proposed methods are promising.
Keywords :
data analysis; image classification; image sequences; matrix algebra; object detection; statistical testing; video signal processing; ISODATA classification; confusion matrix; gradual video transition detection; iterative self organizing data analysis; kappa coefficient; shot boundary detection; statistical tests; video frames; video sequences; Clustering algorithms; Feature extraction; Histograms; Image color analysis; Streaming media; Support vector machines; Video sequences; Shot Boundary Detection; dissolves; fades;
Conference_Titel :
Informatics (PCI), 2012 16th Panhellenic Conference on
Conference_Location :
Piraeus
Print_ISBN :
978-1-4673-2720-6
DOI :
10.1109/PCi.2012.85
