• DocumentCode
    3052667
  • Title

    Optimal view selection and event retrieval in multi-camera office environment

  • Author

    Park, Han-Saem ; Lim, Soojung ; Min, Jun-Ki ; Cho, Sung-Bae

  • Author_Institution
    Dept. of Comput. Sci., Yonsei Univ., Seoul
  • fYear
    2008
  • fDate
    20-22 Aug. 2008
  • Firstpage
    106
  • Lastpage
    110
  • Abstract
    Recently, diverse sensor technologies have been advanced dramatically, so that people can use those sensors in many areas. Camera to capture the video data is one of the most useful sensors among them, and the use of camera with other sensors or the use of several cameras has been done to obtain more information. This paper deals with the multi-camera system, which uses the several cameras as sensors. Previous multi-camera systems have been used to track a moving object in a wide area. In this paper, we have set cameras to focus on the same place in an office so that system can provide diverse views on a single event. We have modeled office events, and modeled events can be recognized from annotated features. Finally, we have conducted the event recognition, view selection and event retrieval experiments based on a scenario in an office to show the usefulness of the proposed system.
  • Keywords
    image motion analysis; object recognition; video retrieval; event recognition; event retrieval; moving object tracking; multicamera office environment; multicamera systems; optimal view selection; video data; Acoustic sensors; Bayesian methods; Cameras; Image analysis; Information analysis; Information retrieval; Intelligent sensors; Multimedia systems; Sensor fusion; Sensor systems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multisensor Fusion and Integration for Intelligent Systems, 2008. MFI 2008. IEEE International Conference on
  • Conference_Location
    Seoul
  • Print_ISBN
    978-1-4244-2143-5
  • Electronic_ISBN
    978-1-4244-2144-2
  • Type

    conf

  • DOI
    10.1109/MFI.2008.4648117
  • Filename
    4648117