• DocumentCode
    2729383
  • Title

    AVR theory, techniques and application

  • Author

    Liu, Weibin ; Zhang, Chao ; Yuan, Baozong

  • Author_Institution
    Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
  • Volume
    2
  • fYear
    2000
  • fDate
    2000
  • Firstpage
    1163
  • Abstract
    AVR (from actual reality to virtual reality) is a development of VR technique. In AVR, the objects in real world are virtualized directly from their shape information based on computer graphics and computer vision techniques, which provides the virtual environment with a higher level realism and preciseness. The basic theory and core techniques of AVR have been expounded in this paper. In order to achieve the integration of computer vision and computer graphics, superquadric-based model (SQ-based model) as the universal description of virtual objects is chosen and PAMVISION model providing a general framework for vision recognition and reconstruction in AVR modeling is developed. As the core techniques of AVR, two approaches for virtualizing the real objects from either 2D images or 3D data are implemented
  • Keywords
    computer graphics; computer vision; image recognition; image reconstruction; virtual reality; 2D images; 3D data; AVR application; AVR modeling; AVR techniques; AVR theory; PAMVISION model; actual reality to virtual reality; computer graphics; computer vision; shape information; software package; superquadric-based model; virtual environment; virtual objects; vision recognition; vision reconstruction; Application software; Chaos; Computer graphics; Computer vision; Image reconstruction; Information science; Layout; Shape; Virtual environment; Virtual reality;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
  • Conference_Location
    Beijing
  • Print_ISBN
    0-7803-5747-7
  • Type

    conf

  • DOI
    10.1109/ICOSP.2000.891751
  • Filename
    891751