Research on SIFT Algorithm Base on Complex Environment

DOI

10.2991/isrme-15.2015.138How to use a DOI?

Keywords

traffic; stitching; Curvelet; SIFT

Abstract

A new algorithm of feature matching was presented by this paper. In the new algorithm, Curvelet first used to denoise, then RANSAC optimized SIFT algorithm used to stitch images. Experiments show that the new algorithm is better to remove error matching points. It improved the accuracy of local invariant feature matching. New algorithm has a good anti-noise and lighting capabilities. It has strong adaptability to scale changes, the algorithm is robust, and has better effect on matching and stitching.

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  - Dan Li
AU  - Xiangying Dang
PY  - 2015/04
DA  - 2015/04
TI  - Research on SIFT Algorithm Base on Complex Environment
BT  - Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering
PB  - Atlantis Press
SP  - 694
EP  - 698
SN  - 1951-6851
UR  - https://doi.org/10.2991/isrme-15.2015.138
DO  - 10.2991/isrme-15.2015.138
ID  - Li2015/04
ER  -