• DocumentCode
    2432323
  • Title

    Fast Frame-Based Scene Change Detection in the Compressed Domain for MPEG-4 Video

  • Author

    Brandt, Jens ; Trotzky, Jens ; Wolf, Lars

  • Author_Institution
    Tech. Univ. Braunschweig, Braunschweig
  • fYear
    2008
  • fDate
    16-19 Sept. 2008
  • Firstpage
    514
  • Lastpage
    520
  • Abstract
    Detection of scene changes is an elementary step in automatic video processing like indexing, segmentation or transcoding. Video indexing and segmentation allow fast browsing without decoding the complete video. In the case of transcoding, the information about scene changes such as cuts and fades as well as about special movements like rotations or zooms in video frames is helpful to determine suitable transcoding parameters. In the compressed domain only information about DCT values as well as motion information can be used to determine such scene changes and movements. Therefore we defined different measures which use the encoded DCT values and motion vectors of each compressed frame. Based on these measures as well as on motion vector histograms we present a fast approach to detect different kinds of scene changes and special movements in MPEG-4 videos in the compressed domain.
  • Keywords
    discrete cosine transforms; video coding; DCT; MPEG-4 video; automatic video processing; discrete cosine transforms; fast frame-based scene change detection; motion vectors; video indexing; video segmentation; video transcoding; Decoding; Discrete cosine transforms; Histograms; Indexing; Layout; MPEG 4 Standard; Motion detection; Motion measurement; Transcoding; Video compression; compressed domain video processing; video scene change detection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Next Generation Mobile Applications, Services and Technologies, 2008. NGMAST '08. The Second International Conference on
  • Conference_Location
    Cardiff
  • Print_ISBN
    978-0-7695-3333-9
  • Type

    conf

  • DOI
    10.1109/NGMAST.2008.39
  • Filename
    4756480