• DocumentCode
    72408
  • Title

    Multi-Scale Descriptor for Robust and Fast Camera Motion Estimation

  • Author

    Changhun Sung ; Myung Jin Chung

  • Author_Institution
    Robot. Program, Korea Adv. Inst. of Sci. & Technol., Daejeon, South Korea
  • Volume
    20
  • Issue
    7
  • fYear
    2013
  • fDate
    Jul-13
  • Firstpage
    725
  • Lastpage
    728
  • Abstract
    This letter presents a robust and fast 6D camera motion estimation system that combines a FAST detector with a Multi-scale Descriptor (MSD). For a robust and fast camera motion estimation system, the descriptor is an especially important component, as it is the most time consuming step in motion estimation. Furthermore, the properties of the descriptor significantly affect the precision of the estimated motion. In this letter, we present a descriptor that requires a low computational burden and offers high precision for robust and fast motion estimation. The descriptor provides high precision through the use of multi-scale gradient information and computational efficiency by employing 4 integral images and an intensity gradient. We conclude this letter with an evaluation of the proposed motion estimation in comparison with different types of descriptors in practical situations. The results show that the proposed motion estimation provides good performance over previous methods in terms of processing time and precision of estimated camera motion.
  • Keywords
    cameras; motion estimation; MSD; computational burden; computational efήciency; estimated camera motion; fast 6D camera motion estimation system; integral images; intensity gradient; multiscale descriptor; multiscale gradient information; robust camera motion estimation system; time consuming step; Cameras; Computer vision; Estimation; Feature extraction; Motion estimation; Robustness; Vectors; Descriptor; motion estimation (ME);
  • fLanguage
    English
  • Journal_Title
    Signal Processing Letters, IEEE
  • Publisher
    ieee
  • ISSN
    1070-9908
  • Type

    jour

  • DOI
    10.1109/LSP.2013.2264672
  • Filename
    6518169