• Login
    View Item 
    •   Eurographics DL Home
    • Eurographics Local Chapter Events
    • EG UK Theory and Practice of Computer Graphics
    • EG UK Theory and Practice of Computer Graphics 2012
    • View Item
    •   Eurographics DL Home
    • Eurographics Local Chapter Events
    • EG UK Theory and Practice of Computer Graphics
    • EG UK Theory and Practice of Computer Graphics 2012
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Fast Scalable k-NN Computation for Very Large Point Clouds

    Thumbnail
    View/Open
    085-092.pdf (794.0Kb)
    Date
    2012
    Author
    Spina, Sandro
    Debattista, Kurt
    Bugeja, Keith
    Chalmers, Alan
    Pay-Per-View via TIB Hannover:

    Try if this item/paper is available.

    Metadata
    Show full item record
    Abstract
    The process of reconstructing virtual representations of large real-world sites is traditionally carried out through the use of laser scanning technology. Recent advances in these technologies led to improvements in precision and accuracy and higher sampling rates. State of the art laser scanners are capable of acquiring around a million points per second, generating enormous point cloud data sets. These data sets are usually cleaned through the application of numerous post-processing algorithms, like normal determination, clustering and noise removal. A common factor in these algorithms is the recurring need for the computation of point neighborhoods, usually by applying algorithms to compute the k-nearest neighbours of each point. The majority of these algorithms work under the assumption that the data sets operated on can fit in main memory, while others take into account the size of the data sets and are thus designed to keep data on disk. We present a hybrid approach which exploits the spatial locality of point clusters in the point cloud and loads them in system memory on demand by taking advantage of paged virtual memory in modern operating systems. In this way, we maximize processor utilization while keeping I/O overheads to a minimum. We evaluate our approach on point cloud sizes ranging from 50K to 333M points on machines with 1GB, 2GB, 4GB and 8GB of system memory.
    BibTeX
    @inproceedings {10.2312:LocalChapterEvents:TPCG:TPCG12:085-092,
    booktitle = {Theory and Practice of Computer Graphics},
    editor = {Hamish Carr and Silvester Czanner},
    title = {{Fast Scalable k-NN Computation for Very Large Point Clouds}},
    author = {Spina, Sandro and Debattista, Kurt and Bugeja, Keith and Chalmers, Alan},
    year = {2012},
    publisher = {The Eurographics Association},
    ISBN = {978-3-905673-93-7},
    DOI = {10.2312/LocalChapterEvents/TPCG/TPCG12/085-092}
    }
    URI
    http://dx.doi.org/10.2312/LocalChapterEvents/TPCG/TPCG12/085-092
    Collections
    • EG UK Theory and Practice of Computer Graphics 2012

    Eurographics Association copyright © 2013 - 2023 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA
     

     

    Browse

    All of Eurographics DLCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

    BibTeX | TOC

    Create BibTeX Create Table of Contents

    Eurographics Association copyright © 2013 - 2023 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA