Title :
A Self-adapting Dual-threshold Method for Video Shot Transition Detection
Author :
Wang, Jianyu ; Luo, Wen
Author_Institution :
Nanjing Univ. of Sci. & Technol., Nanjing
Abstract :
Video shots are basic physical units of videos and dividing videos into shots is the base of video structurization. In this paper, the dual-compare method is used for reference, and a video shot transition detection method is presented, which is based on self-adapting dual-threshold comparison. In this method, the chi2 histogram is used to compute frame difference, and the self-adapting threshold can be achieved. The problem of flash detection is also solved by the method of projected window. This method is applied in the video shot detection of ball game videos and experiments indicate the method can detect in higher efficiency.
Keywords :
image segmentation; video signal processing; ball game videos; chi2 histogram; dual-compare method; self-adapting dual-threshold method; video shot transition detection; video structurization; Automation; Cameras; Games; Gunshot detection systems; Histograms; Image coding; Image edge detection; Image sequences; Video compression; Video sequences;
Conference_Titel :
Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-1685-1
Electronic_ISBN :
978-1-4244-1686-8
DOI :
10.1109/ICNSC.2008.4525307