• DocumentCode
    632717
  • Title

    3D Ground-Truth Systems for Object/Human Recognition and Tracking

  • Author

    Godil, Afzal ; Bostelman, Roger ; Saidi, Kamel ; Shackleford, Will ; Cheok, Geraldine ; Shneier, Michael ; Tsai Hong

  • Author_Institution
    Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
  • fYear
    2013
  • fDate
    23-28 June 2013
  • Firstpage
    719
  • Lastpage
    726
  • Abstract
    We have been researching three dimensional (3D) ground-truth systems for performance evaluation of vision and perception systems in the fields of smart manufacturing and robot safety. In this paper we first present an overview of different systems that have been used to provide ground-truth (GT) measurements and then we discuss the advantages of physically-sensed ground-truth systems for our applications. Then we discuss in detail the three ground- truth systems that we have used in our experiments: ultra wide-band, indoor GPS, and a camera-based motion capture system. Finally, we discuss three different perception-evaluation experiments where we have used these GT systems.
  • Keywords
    computer vision; image motion analysis; object recognition; object tracking; visual perception; 3D ground-truth systems; GT measurements; GT systems; camera-based motion capture system; human recognition; indoor GPS; object recognition; object tracking; perception systems; perception-evaluation experiments; performance evaluation; physically-sensed ground-truth systems; robot safety; smart manufacturing; ultra wideband; vision system; Accuracy; Robot kinematics; Robot sensing systems; Three-dimensional displays; Tracking; Vehicles; Ground-Truth Systems; human detection and tracking; object detection and tracking; performance evaluation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on
  • Conference_Location
    Portland, OR
  • Type

    conf

  • DOI
    10.1109/CVPRW.2013.109
  • Filename
    6595953