Robust elevator door recognition using LRF and camera

Seung Wan Ma, Xuenan Cui, Hyung Ho Lee, Hyung Rae Kim, Jae Hong Lee, Hakil Kim

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

The recognition of elevator door is needed for mobile service robots to moving between floors in the building. This paper proposed the sensor fusion approach using LRF (Laser Range Finder) and camera to solve the problem. Using the laser scans by the LRF, we extract line segments and detect candidates as the elevator door. Using the image by the camera, the door candidates are verified and selected as real door of the elevator. The outliers are filtered through the verification process. Then, the door state detection is performed by depth analysis within the door. The proposed method uses extrinsic calibration to fuse the LRF and the camera. It gives better results of elevator door recognition compared to the method using LRF only.

Original languageEnglish
Pages (from-to)601-607
Number of pages7
JournalJournal of Institute of Control, Robotics and Systems
Volume18
Issue number6
DOIs
StatePublished - 2012

Keywords

  • Door detection
  • Door recognition
  • Extrinsic calibration
  • Sensor fusion
  • Straight line extraction

Fingerprint

Dive into the research topics of 'Robust elevator door recognition using LRF and camera'. Together they form a unique fingerprint.

Cite this