Feature Based Vision Destination Recognition for Mobile Robot

DOI

10.2991/mcae-16.2016.15How to use a DOI?

Keywords

camera calibration; destination matching; visual heading

Abstract

This paper presents a feature based vision destination recognition approach. A simplified static calibration of camera is implemented and then based on the homography matrix calculated by coplanar matched Speeded-Up Robust Features (SURF) points the destination which is not even a direct feature point is tracked. By using the reference image and the invariance of area ratio of two triangles in affine transformation, the accumulated error is eliminated and the homography is corrected. The result of the laboratory dynamic experiment proves the stability and accuracy of the 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  - Xianguang Cui
AU  - Hai Zhang
AU  - Yue Wang
PY  - 2016/07
DA  - 2016/07
TI  - Feature Based Vision Destination Recognition for Mobile Robot
BT  - Proceedings of the 2016 International Conference on Mechatronics, Control and Automation Engineering
PB  - Atlantis Press
SP  - 58
EP  - 62
SN  - 2352-5401
UR  - https://doi.org/10.2991/mcae-16.2016.15
DO  - 10.2991/mcae-16.2016.15
ID  - Cui2016/07
ER  -