An algorithm for seamless image stitching and its application

Authors:
Jing Xing;Zhenjiang Miao;Jing Chen
Affiliations:
Institute of Information Science, Beijing JiaoTong University, Beijing, P.R. China;Institute of Information Science, Beijing JiaoTong University, Beijing, P.R. China;Institute of Information Science, Beijing JiaoTong University, Beijing, P.R. China
Venue:
ICEC'07 Proceedings of the 6th international conference on Entertainment Computing
Year:
2007

Citing 3
Cited 0

Multiple view geometry in computer visiond

Multiple view geometry in computer visiond
Image quilting for texture synthesis and transfer

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Panoramic image stitching used to create virtual environments for many applications is crucial for IBR. In this paper, we introduce a four-step algorithm based on SIFT features which makes some improvements on large exposure difference, large scene motion or other misregistrations when stitching panoramic images. We introduce a new method that is to add the adjacent images according to a weight function to eliminate the seam in the transition region. As a result, we apply the panoramic image to a computer game to enhance the reality of the game environment. Through lots of analyses and experiments we find that our method is simple and effective. Because this method is not sensitive to ordering, orientation, scaling and illumination, its stitching precision is much higher than many other methods.