Image Stitching by Non-homogeneous warping
Date Issued
2011
Date
2011
Author(s)
Chen, Chiu-Ju
Abstract
This thesis proposes an automatic approach to multi-perspective image stitching. Differently from previous stitching methods using global transformation such as homography, we frame non-homogeneous warping into Lucas-Kanade approach and optimize for multi-perspective images. Our algorithm consists of two stages: alignment stage and aggregation stage. The former uses non-rigid alignment after applying feature-based registration, the latter iteratively solves for multi-perspective results. Experiments on the numbers of images taken from different view-points showed that our algorithm improves the image stitching without using layering or blending techniques.
Subjects
Non-homogeneous warping
non-rigid alignment
multi-perspective image stitching
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-100-R98944009-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):b5894ce36859287cc335090bd453afe3