A Mosaic Method on Images Small of Unmanned Aerial Vehicle

DOI

10.2991/wartia-16.2016.102How to use a DOI?

Keywords

Unmanned aerial images, position and posture information, image registration, transformation matrices, matrix singular value decomposition.

Abstract

Traditional mosaic methods of unmanned aerial vehicle (UAV) need ground control points, which are difficult to implement in the emergency situation. A new image mosaic method on small unmanned aerial vehicle is proposed. The method uses the Harris algorithm to extract the feature points and refines them by the Best-Bin-First (BBF) algorithm and the random sample consensus (RANSAC) algorithm. The transformation matrices from one image to another are computed by the feature points. The position and posture information of UAV is obtained by the transformation matrices according to the matrix singular value decomposition. The UAV images can be merged by the information. Experimental results demonstrate that the method has advantages in mosaic speed and mosaic quality, and is applied potentially in many areas.

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  - Xiang Gao
PY  - 2016/05
DA  - 2016/05
TI  - A Mosaic Method on Images Small of Unmanned Aerial Vehicle
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 508
EP  - 511
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.102
DO  - 10.2991/wartia-16.2016.102
ID  - Gao2016/05
ER  -