Image Mosaic using ORB descriptor and improved blending algorithm

Author

Fang Tian ; Ping Shi

Author_Institution

Sch. of Inf. Eng., Commun. Univ. of China, Beijing, China

fYear

2014

fDate

14-16 Oct. 2014

Firstpage

693

Lastpage

698

Abstract

This paper presents an image mosaic technique using ORB (oriented FAST and rotated BRIEF) descriptor and an improved blending algorithm. Features of images with overlapping regions are first described by ORB descriptors. This binary descriptor outperforms SIFT and SURF in regard of processing speed. RANSAC algorithm is then applied to reject mismatches. Once the best projective deformation matrix is found, brightness equalization is conducted and an improved weighting function is utilized to blend images and reduce visible artifacts. Experimental results show this approach to be efficient in accounting for image mosaic, and the edge artifacts could be significantly reduced and even completely eliminated with the blending process designed in this paper.

Keywords

image matching; image segmentation; ORB descriptor; RANSAC algorithm; binary descriptor; binary robust independent elementary features; blending algorithm; brightness equalization; edge artifact reduction; features from accelerated segment test; image mosaic technique; oriented FAST and rotated BRIEF descriptor; projective deformation matrix; visible artifact reduction; weighting function; Algorithm design and analysis; Brightness; Cameras; Feature extraction; Image color analysis; Image edge detection; Robustness; Image Blending; Image Mosaic; ORB Descriptor; RANSAC;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing (CISP), 2014 7th International Congress on

Conference_Location

Dalian

Type

conf

DOI

10.1109/CISP.2014.7003867

Filename

7003867