Image Registration for UAV Platform Based on KLT Features

DOI

10.2991/itms-15.2015.441How to use a DOI?

Keywords

KLT; UAV; Image Registration; Feature point

Abstract

Image registration technology is extremely significant in the virtual scene, automatic navigation, computer science, remote sensing image processing and many other aspects. It takes lots of difficulties for video tracking owing to the UAV platform is always unstable. In this paper, we utilized improved KLT algorithm to realize feature extraction, and used distance constraint to speed up matching, then applied the RANSAC to achieve precise matching, finally obtained the affine transform parameters. The experiment results demonstrate that this method can solve the problem of UAV camera shaking effectively.

Copyright

© 2015, 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  - J. Liu
AU  - Z. C. Hao
AU  - W. Gao
PY  - 2015/11
DA  - 2015/11
TI  - Image Registration for UAV Platform Based on KLT Features
BT  - Proceedings of the 2015 International Conference on Industrial Technology and Management Science
PB  - Atlantis Press
SP  - 1806
EP  - 1809
SN  - 2352-538X
UR  - https://doi.org/10.2991/itms-15.2015.441
DO  - 10.2991/itms-15.2015.441
ID  - Liu2015/11
ER  -