• DocumentCode
    3593595
  • Title

    Parametric description of object motion using EMUs

  • Author

    Ekin, Ahmet ; Mehrotra, Rajiv ; Tekalp, A. Murat

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Rochester Univ., NY, USA
  • Volume
    2
  • fYear
    2000
  • Firstpage
    570
  • Abstract
    Large scale deployment of digital multimedia applications requires effective and efficient image and video representations for indexing. We present a hierarchical representation of video objects based on their motion. The proposed representation enables both low and semantic level description of object motion. At the low level, we consider a parametric description of the dominant motion of video objects, and define elementary motion units (EMU) where the dominant motion of the object is coherent and does not undergo considerable change. A group of EMUs forms an action unit which carries semantic information. Interactions between objects are also considered by calculating the relative motion between objects in an object-based framework. Experimental results for retrieval of EMUs based on similarity of dominant object motion are demonstrated.
  • Keywords
    database indexing; image representation; image retrieval; motion estimation; multimedia communication; multimedia databases; parameter estimation; video signal processing; EMU; action unit; digital multimedia applications; dominant coherent motion; elementary motion units; hierarchical representation; image representation; low level description; motion indexing; motion retrieval; object based indexing; object motion; parametric description; querying mechanisms; relative motion; semantic information; semantic level description; video objects; video representation; Analytical models; Application software; Cameras; Cognitive science; Humans; Image converters; Indexing; Large-scale systems; Layout; Tracking;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 2000. Proceedings. 2000 International Conference on
  • ISSN
    1522-4880
  • Print_ISBN
    0-7803-6297-7
  • Type

    conf

  • DOI
    10.1109/ICIP.2000.899492
  • Filename
    899492