Research of SLAM for Indoor Environment based on Kinect

DOI

10.2991/wartia-16.2016.99How to use a DOI?

Keywords

SLAM, Kinect, ORB, loop closure detection, pose graph optimization.

Abstract

The research of mobile robot’s intelligence currently is a hot topic, and the basic and key technology to achieve the intelligence is Simultaneous Localization and Mapping(SLAM). In order to solve the problem of localization for mobile robots based on vision, A method of SLAM based on Kinect is proposed. Firstly, the successive images are captured by Kinect. Secondly, the frame-to-frame alignments are performed based on ORB(Oriented FAST and Rotated BRIEF) features between frames, and the relative motion transformations are computed via the PnP algorithm. Thirdly, the key-frames are defined by the relative motion estimated between frames, then loop closure detection and global graph optimization are performed to efficiently decrease the accumulative error of poses and achieve a global consistence trajectory. Finally, the OctoMap are applied to represent the environment with less data amount. Experimental results show the feasibility and effectiveness of this method.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Di Liu
AU  - Ri Pan
AU  - Yajun Zhang
PY  - 2016/05
DA  - 2016/05
TI  - Research of SLAM for Indoor Environment based on Kinect
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 492
EP  - 495
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.99
DO  - 10.2991/wartia-16.2016.99
ID  - Liu2016/05
ER  -