• DocumentCode
    2357743
  • Title

    A Visual-Perception Layer Applied to Reactive Navigation

  • Author

    Neto, A. Miranda ; Victorino, A. Corrêa ; Ferreira, J.V.

  • Author_Institution
    Heudiasyc Lab., UTC, France
  • fYear
    2012
  • fDate
    16-19 Oct. 2012
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    Environment perception is a major research issue which is very important in the field of robotic system. In order to identify the horizon line and the drivable region, we have proposed a visual-perception system based on an automatic image discarding method as a simple solution to improve the system performance. In this paper, all these previous methods are organized in a visual-perception layer which also includes a method for estimating the risk-of-collision based on Pearson´s Correlation Coefficient and an evolution of the Threshold and Horizon Finder (TH Finder). These methods were successfully evaluated from real data.
  • Keywords
    collision avoidance; mobile robots; robot vision; statistical analysis; visual perception; Pearson´s correlation coefficient; TH finder; automatic image discarding method; drivable region identification; environment perception; horizon line identification; reactive navigation; risk-of-collision estimation; robotic system; system performance improvement; threshold-and-horizon finder; visual-perception layer; visual-perception system; Equations; Image segmentation; Navigation; Roads; Robots; Sensors; Vehicles; Autonomous Vehicles; Computer Vision; Mobile Robots; Perception;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Robotics Symposium and Latin American Robotics Symposium (SBR-LARS), 2012 Brazilian
  • Conference_Location
    Fortaleza
  • Print_ISBN
    978-1-4673-4650-4
  • Type

    conf

  • DOI
    10.1109/SBR-LARS.2012.8
  • Filename
    6363256