• DocumentCode
    2417417
  • Title

    Capsule endoscope localization based on computer vision technique

  • Author

    Liu, Li ; Hu, Chao ; Cai, Wentao ; Meng, Max Q H

  • Author_Institution
    Shenzhen Inst. of Adv. Integration Technol. (SIAIT), Chinese Acad. of Sci., Hong Kong, China
  • fYear
    2009
  • fDate
    3-6 Sept. 2009
  • Firstpage
    3711
  • Lastpage
    3714
  • Abstract
    To build a new type of wireless capsule endoscope with interactive gastrointestinal tract examination, a localization and orientation system is needed for tracking 3D location and 3D orientation of the capsule movement. The magnetic localization and orientation method produces only 5 DOF, but misses the information of rotation angle along capsule´s main axis. In this paper, we presented a complementary orientation approach for the capsule endoscope, and the 3D rotation can be determined by applying computer vision technique on the captured endoscopic images. The experimental results show that the complementary orientation method has good accuracy and high feasibility.
  • Keywords
    biomedical optical imaging; computer vision; endoscopes; interactive systems; magnetic sensors; medical image processing; tracking; 3D location tracking; 3D orientation tracking; 3D rotation; capsule movement; complementary orientation method; computer vision technique; interactive gastrointestinal tract examination; magnetic localization system; magnetic orientation system; magnetic sensor array; wireless capsule endoscope localization; Capsule Endoscope; Feature Tracking; Localization and Orientation; Rotation Decomposition; Algorithms; Capsule Endoscopes; Computer Communication Networks; Computer Graphics; Computers; Endoscopy; Gastrointestinal Tract; Humans; Imaging, Three-Dimensional; Magnetics; Models, Statistical; Motion; Reproducibility of Results; Software;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE
  • Conference_Location
    Minneapolis, MN
  • ISSN
    1557-170X
  • Print_ISBN
    978-1-4244-3296-7
  • Electronic_ISBN
    1557-170X
  • Type

    conf

  • DOI
    10.1109/IEMBS.2009.5334803
  • Filename
    5334803