Skip to main navigation Skip to search Skip to main content

Information entropy based viewpoint planning for digitization of 3D objects

Z. G. Liu, Y. F. Li

    Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

    Abstract

    In this paper, we present an information entropy based viewpoint planning approach for digitalization of 3D freeform objects. The object is firstly sliced into a number of cross section curves, with each cross-section to be reconstructed by a closed B-spline curve. Then, we propose an improved Bayesian information criterion (BIC) for selecting the control point number of B-spline models. Based on the selected model, we use entropy as the measurement of uncertainty of B-spline model to predict the information gain for each cross section curve. After obtaining the predicted information gain of all the B-spline models, we can map the information gain of these B-spline model into the view space. The viewpoint that contains maximal information gain for the object is then selected as the next best view. Finally, we show our experimental results for the digitization and reconstruction of freedom objects with our view planning method.
    Original languageEnglish
    Title of host publicationProceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA
    PublisherIEEE
    Pages1509-1514
    Volume3
    ISBN (Print)780378660
    DOIs
    Publication statusPublished - 2003
    Event2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2003 - Kobe, Japan
    Duration: 16 Jul 200320 Jul 2003

    Publication series

    Name
    Volume3

    Conference

    Conference2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2003
    PlaceJapan
    CityKobe
    Period16/07/0320/07/03

    Fingerprint

    Dive into the research topics of 'Information entropy based viewpoint planning for digitization of 3D objects'. Together they form a unique fingerprint.

    Cite this