Accurate object pose estimation using depth only

Mingyu Li, Koichi Hashimoto

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Object recognition and pose estimation is an important task in computer vision. A pose estimation algorithm using only depth information is proposed in this paper. Foreground and background points are distinguished based on their relative positions with boundaries. Model templates are selected using synthetic scenes to make up for the point pair feature algorithm. An accurate and fast pose verification method is introduced to select result poses from thousands of poses. Our algorithm is evaluated against a large number of scenes and proved to be more accurate than algorithms using both color information and depth information.

Original languageEnglish
Article number1045
JournalSensors (Switzerland)
Volume18
Issue number4
DOIs
Publication statusPublished - 2018 Apr

Keywords

  • Point cloud
  • Point pair feature
  • Pose estimation

ASJC Scopus subject areas

  • Analytical Chemistry
  • Biochemistry
  • Atomic and Molecular Physics, and Optics
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Accurate object pose estimation using depth only'. Together they form a unique fingerprint.

  • Cite this