Title :
Scene change detection algorithm on specific movie
Author :
Chung, Myoung-Beom ; Ko, Il-Ju ; Jang, Dae-Sik
Author_Institution :
Dept. of Media, Soongsil Univ., Seoul
Abstract :
Scene detection is pretreatment to index video information in video search system, and it is very important technology for overall performance. Existing scene detection used single characteristic of pixel value difference, histogram difference, etc or mixed single characteristics. However, accuracy of those is poor for specific video such as infrared camera, night shooting. This paper is proposed the method that is mixed color histogram and KLT algorithm for scene detection at the specific movie. We did an experiment which used color histogram only and KLT algorithm with color histogram. In result, proposed method is improved about 11.4% at the specific movie.
Keywords :
image colour analysis; object detection; video signal processing; image processing; infrared camera; mixed color histogram; scene change detection algorithm; video indexing; video search system; Cameras; Change detection algorithms; Detection algorithms; Histograms; Indexing; Infrared detectors; Karhunen-Loeve transforms; Layout; Motion pictures; User-generated content; Image processing; Scene Change Detection; Video Indexing;
Conference_Titel :
Advanced Communication Technology, 2009. ICACT 2009. 11th International Conference on
Conference_Location :
Phoenix Park
Print_ISBN :
978-89-5519-138-7
Electronic_ISBN :
1738-9445