3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging

Yasunori Sakuramoto, Yuichi Kanematsu, Hiroki Ohno, Shuichi Akizuki, Manabu Hashimoto, Kiyotaka Watanabe, Makito Seki

Research output: Contribution to journalArticle

Abstract

This paper introduces an object detection method using features described information about a concavo-convex shape of an object that are obtained by using a small camera that controls the illumination direction. An image of the binarized gradient feature containing information about the shape of the object is generated by the Coded Multi Flash Imaging. The proposed method can reliably detect a texture-less object by using this feature image in the matching process. In addition, processing time for matching is significantly reduced by using a small number of pixels. Experiments using 200 actual images confirmed that the proposed method achieves a 98.5% recognition success rate and a 607 msec processing time.

Original languageEnglish
Pages (from-to)944-950
Number of pages7
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume81
Issue number10
DOIs
Publication statusPublished - 2015 Oct 1
Externally publishedYes

Keywords

  • Binarized gradient features
  • Binary code
  • Image matching
  • Object detection
  • Texture-less

ASJC Scopus subject areas

  • Mechanical Engineering

Fingerprint Dive into the research topics of '3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging'. Together they form a unique fingerprint.

  • Cite this