A High-Precision Localization Algorithm by Improved SIFT Key-Points

Author

Yang, Yang ; Song, Yixu ; Zhai, Fangwen ; Fan, Zhaozhou ; Meng, Yue ; Wang, Jiaxin

Author_Institution

Dept. of Comput. Sci., Tsinghua Univ., Beijing, China

fYear

2009

fDate

17-19 Oct. 2009

Firstpage

1

Lastpage

6

Abstract

High-precision localization is getting more and more dependent on computer vision techniques. In this paper a novel high-precision localization algorithm based on improved SIFT (Scale Invariant Feature Transform) key-points is presented. First considering the drawback of original SIFT algorithm and the special application background, the proposed algorithm improves the SIFT key-point description and discards the most time-consuming step of SIFT algorithm. Then the new matching strategy and localization strategy are investigated to ensure the stability and precision of localization. Compared with conventional localization algorithm by SIFT key-point, this algorithm increases computation efficiency for about 20% and makes the precision more stable, which reaches 0.1 pixel.

Keywords

computer vision; scaling phenomena; SIFT key-points; computer vision; high-precision localization algorithm; scale invariant feature transform; Application software; Bonding; Computer science; Computer vision; Feature extraction; Fourier transforms; Information science; Laboratories; Least squares methods; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing, 2009. CISP '09. 2nd International Congress on

Conference_Location

Tianjin

Print_ISBN

978-1-4244-4129-7

Electronic_ISBN

978-1-4244-4131-0

Type

conf

DOI

10.1109/CISP.2009.5303161

Filename

5303161