A Mosaic Method for Aerial Image Sequence by R/C Model

Author

Liu, Jin ; Chen, Zhiyong ; Guo, Ruifang

Author_Institution

Sch. of Geodesy & Geomatics, Wuhan Univ., Wuhan, China

Volume

6

fYear

2008

fDate

12-14 Dec. 2008

Firstpage

58

Lastpage

61

Abstract

An economic and simple scheme to obtain wide field range of aerial images is proposed, the scheme includes only an aerial model taking a camera. For the obtained video an automatic image mosaic technique is used. Firstly a lot of feature point pairs are extracted by SIFT (scale invariant feature transform) features between two adjacent frames, and Ransac (random sampling consensus) is used to pick out bad matching, then homography matrices are calculated, including adjacent frames and non-adjacent frames (cascade of homography matrix), finally a large mosaic image is formed using the homography matrices. The experiment proves that our method can make very wide filed vision of aerial images with high quality.

Keywords

feature extraction; image matching; image segmentation; image sequences; random processes; sampling methods; transforms; R/C model; aerial image sequence; aerial model; automatic image mosaic technique; feature extraction; homography matrix; image matching; random sampling consensus; scale invariant feature transform; Cameras; Computer science; Gaussian processes; Geodesy; Image sampling; Image sequences; Layout; Remote sensing; Software engineering; Video sequences; Homography matrix; Image Mosaic; Sift feature;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Software Engineering, 2008 International Conference on

Conference_Location

Wuhan, Hubei

Print_ISBN

978-0-7695-3336-0

Type

conf

DOI

10.1109/CSSE.2008.1472

Filename

4723196