Implementation of 3D Shape Matching for EV Charging Connector

Pai Chuaychoo, Benjamas Panomruttanarug, Mario Hirz

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

A shape feature is commonly chosen for matching an object with a template model in a vision-based design. A 3D shape matching technique is presented in this work to localize an EV charging connector. To perform the matching, a 3D model of the connector is firstly created and then used as a template to compare with images captured from different camera locations. This process is carried out by placing the camera around the fixed location with a fixed pose of the connector. To evaluate an effectiveness of matching, a white and black background are used to study a robustness to illumination changes. The results display some errors from using the white and black backgrounds in the Cartesian coordinate.

Original languageEnglish
Title of host publication2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021
PublisherInstitute of Electrical and Electronics Engineers
Pages498-501
Number of pages4
ISBN (Electronic)9784907764739
Publication statusPublished - 8 Sep 2021
Event60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021 - Tokyo, Japan
Duration: 8 Sep 202110 Sep 2021

Publication series

Name2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021

Conference

Conference60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021
Country/TerritoryJapan
CityTokyo
Period8/09/2110/09/21

Keywords

  • 3D CAD matching
  • 3D object recognition
  • shape-based matching

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization
  • Instrumentation

Fields of Expertise

  • Mobility & Production

Fingerprint

Dive into the research topics of 'Implementation of 3D Shape Matching for EV Charging Connector'. Together they form a unique fingerprint.

Cite this