Feature extraction for 3D object detection from integral imaging

Doron Aloni, Yitzhak Yitzhaky

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Objects in a 3D space can be located and segmented using information obtained by computational integral imaging. This paper implements an approach for objects isolation based on detecting the sharp edges of the focused regions in the reconstructed confocal images. Several edge feature detection methods are employed and examined. Results show that while the ability to detect the correct object depth locations does not depend on the edge detection method, the resulting quality of the detected object features may be significantly affected by the method used.

    Original languageEnglish
    Title of host publicationImage Reconstruction from Incomplete Data VIII
    EditorsPhilip J. Bones, Michael A. Fiddy, Michael A. Fiddy, Rick P. Millane, Philip J. Bones, Rick P. Millane
    PublisherSPIE
    ISBN (Electronic)9781628417661, 9781628417661
    DOIs
    StatePublished - 1 Jan 2015
    EventImage Reconstruction from Incomplete Data VIII - San Diego, United States
    Duration: 11 Aug 201512 Aug 2015

    Publication series

    NameProceedings of SPIE - The International Society for Optical Engineering
    Volume9600
    ISSN (Print)0277-786X
    ISSN (Electronic)1996-756X

    Conference

    ConferenceImage Reconstruction from Incomplete Data VIII
    Country/TerritoryUnited States
    CitySan Diego
    Period11/08/1512/08/15

    Keywords

    • 3D object detection
    • computational reconstructed integral imaging
    • depth extraction
    • edge detection
    • integral imaging

    ASJC Scopus subject areas

    • Electronic, Optical and Magnetic Materials
    • Condensed Matter Physics
    • Computer Science Applications
    • Applied Mathematics
    • Electrical and Electronic Engineering

    Fingerprint

    Dive into the research topics of 'Feature extraction for 3D object detection from integral imaging'. Together they form a unique fingerprint.

    Cite this