Interactive Object Recognition System for a Helper Robot Using Photometric Invariance

Access this Article

Search this Article

Author(s)

    • KURNIA Rahmadi
    • Department of Information and Computer Sciences, Saitama University
    • NAKAMURA Akio
    • Department of Machinery System Engineering, Tokyo Denki University
    • KUNO Yoshinori
    • Department of Information and Computer Sciences, Saitama University

Abstract

We are developing a helper robot that carries out tasks ordered by the user through speech. The robot needs a vision system to recognize the objects appearing in the orders. It is, however, difficult to realize vision systems that can work in various conditions. Thus, we have proposed to use the human user's assistance through speech. When the vision system cannot achieve a task, the robot makes a speech to the user so that the natural response by the user can give helpful information for its vision system. Our previous system assumes that it can segment images without failure. However, if there are occluded objects and/or objects composed of multi-color parts, segmentation failures cannot be avoided. This paper presents an extended system that tries to recover from segmentation failures using photometric invariance. If the system is not sure about segmentation results, the system asks the user by appropriate expressions depending on the invariant values. Experimental results show the usefulness of the system.

Journal

  • IEICE Trans. Inf. & Syst., D

    IEICE Trans. Inf. & Syst., D 88(11), 2500-2508, 2005-11-01

    The Institute of Electronics, Information and Communication Engineers

References:  19

Cited by:  5

Codes

  • NII Article ID (NAID)
    110003501994
  • NII NACSIS-CAT ID (NCID)
    AA10826272
  • Text Lang
    ENG
  • Article Type
    Journal Article
  • ISSN
    09168532
  • Data Source
    CJP  CJPref  NII-ELS 
Page Top