Title :
Robust Panning Analysis for Slideshow Detection in Video Databases
Author :
Zdziarski, Zbigniew ; Dahyot, Rozenn
Author_Institution :
Sch. of Comput. Sci. & Stat., Trinity Coll. Dublin, Dublin, Ireland
Abstract :
We present an algorithm for slideshow detection in video databases such as YouTube or Blip.TV. Our solution is based around feature tracking to extract movement between sequentially captured frames. This movement is then analysed through the use of the Hough transform and compared against behaviour commonly exhibited by slideshows: still and panning static images. We show experimentally the effectiveness of this novel idea and approach.
Keywords :
Hough transforms; feature extraction; image motion analysis; image sequences; video databases; video signal processing; Blip.TV; Hough transform; YouTube; feature tracking; movement extraction; panning static image; robust panning analysis; slideshow detection; still image; video databases; Computer science; Hidden Markov models; Image analysis; Image databases; Image processing; Machine vision; Robustness; Spatial databases; Video sharing; Videoconference; Hough Transform; feature tracking; slideshow detection; video databases;
Conference_Titel :
Machine Vision and Image Processing Conference, 2009. IMVIP '09. 13th International
Conference_Location :
Dublin
Print_ISBN :
978-1-4244-4875-3
Electronic_ISBN :
978-0-7695-3796-2
DOI :
10.1109/IMVIP.2009.23
