Skip to main navigation Skip to search Skip to main content

A fast 3D map building method for indoor robots based on point-line features extraction

  • Harbin Institute of Technology
  • Duoble Coin Group Jiangsu Tyre CO. LTD

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

Abstract

This paper reports a real-time 3D environmental reconstruction algorithm under semi-structure environment using low-cost Kinect2 sensor. By minimizing the sum of reprojection errors, the changing matrix is solved by Gauss-Newton iteration method. After that, the closed loop detection is performed by using the extracted point-line features, and the closed loop error is reduced by the closed loop optimization, so that a large scale global uniform 3D environment model is obtained. It is converted into the octree structure based on probability. Through off-line and real time on-line data acquire from robot to test the reliability of the algorithm, the accuracy of the calculation time cost and output point cloud model is compared, which verified the reliability and robustness of the reconstruction method.

Original languageEnglish
Title of host publication2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages576-581
Number of pages6
ISBN (Electronic)9781538632604
DOIs
StatePublished - 2 Jul 2017
Event2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017 - Hefei and Tai'an, China
Duration: 27 Aug 201731 Aug 2017

Publication series

Name2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017
Volume2018-January

Conference

Conference2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017
Country/TerritoryChina
CityHefei and Tai'an
Period27/08/1731/08/17

Keywords

  • Kinect2
  • Octree
  • Point-line Features
  • Robot

Fingerprint

Dive into the research topics of 'A fast 3D map building method for indoor robots based on point-line features extraction'. Together they form a unique fingerprint.

Cite this