Integration method of local evidence for part-affordance estimation of everyday objects

Shuichi Akizuki, Masaki Iizuka, Kentaro Kozai, Manabu Hashimoto

Research output: Contribution to journalArticle

Abstract

Shapes of everyday objects are designed to achieve the predefined purpose of use. In this research, we call various kind of inherent functions as "part-affordance", and we have developed the method to perceive it from point cloud captured by a depth sensor. Difficulty of the estimation of it is that same local surfaces do not always have same affordance. In order to deal with this issue, we propose a method which integrates the evidence generated by local feature while considering the continuity of surface structure. Our experiments using a publicly available datasets confirmed that the proposed method have increased the recognition rate from 57% to 73% in comparison with the previous method. Moreover, we demonstrated that the robot arm can perform the task according to estimated part-affordances.

Original languageEnglish
Pages (from-to)658-663
Number of pages6
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume84
Issue number7
DOIs
Publication statusPublished - 2018 Jan 1

    Fingerprint

Keywords

  • 3D object recognition
  • Affordance
  • Local evidence
  • Point cloud processing

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this