A rectification algorithm for un-calibrated multi-view images based on SIFT features

Author

Zhang Yang ; Ping, An ; He, Wang ; haoyang, Zhang

Author_Institution

Sch. of Commun. & Inf. Eng., Shanghai Univ., Shanghai, China

fYear

2010

fDate

23-25 Nov. 2010

Firstpage

143

Lastpage

147

Abstract

In this paper, we present an efficient rectification algorithm for un-calibrated multi-view images based on SIFT (Scale-invariant feature transform) feature matching. Un-calibrated rectification is necessary for some specific occasions and we extend generic stereo pair rectification to multi-view camera array with projection shift method. We bring in SIFT algorithm to extract and match features (key points) automatically. Block-division features extraction method is proposed and RANSAC is used to improve precision of rectifying transformation. From the experiments, we find that our method is effective to rectify parallel cameras array. Rectified images have uniform horizontal disparities and the vertical mismatches between adjacent views are eliminated.

Keywords

feature extraction; image matching; stereo image processing; transforms; RANSAC; block-division feature extraction method; multiview camera array; projection shift method; scale-invariant feature transform feature matching; stereo pair rectification; uncalibrated multiview images; uncalibrated rectification; Algorithm design and analysis; Arrays; Cameras; Feature extraction; Pixel; Three dimensional displays; Visualization;

fLanguage

English

Publisher

ieee

Conference_Titel

Audio Language and Image Processing (ICALIP), 2010 International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-5856-1

Type

conf

DOI

10.1109/ICALIP.2010.5684990

Filename

5684990