Abstract
This paper describes a method to construct seamless image mosaics of a panoramic scene containing two predominate planes: a distant back plane and a ground plane that sweeps out from the camera's location. While this type of panorama can be stitched when the camera is carefully rotated about its optical center, such ideal scene capture is hard to perform correctly. Existing techniques use a single homography per image to perform alignment followed by seam cutting or image blending to hide inevitable alignments artifacts. In this paper, we demonstrate how to use two homographies per image to produce a more seamless image. Specifically, our approach blends the homographies in the alignment procedure to perform a nonlinear warping. Once the images are geometrically stitched, they are further processed to blend seams and reduce curvilinear visual artifacts due to the nonlinear warping. As demonstrated in our paper, our procedure is able to produce results for this type of scene where current state-of-the-art techniques fail.
| Original language | English |
|---|---|
| Title of host publication | 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 |
| Publisher | IEEE Computer Society |
| Pages | 49-56 |
| Number of pages | 8 |
| ISBN (Print) | 9781457703942 |
| DOIs | |
| Publication status | Published - 2011 Jan 1 |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| ISSN (Print) | 1063-6919 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
Cite this
}
Constructing image panoramas using dual-homography warping. / Gao, Junhong; Kim, Seon Joo; Brown, Michael S.
2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. IEEE Computer Society, 2011. p. 49-56 5995433 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Constructing image panoramas using dual-homography warping
AU - Gao, Junhong
AU - Kim, Seon Joo
AU - Brown, Michael S.
PY - 2011/1/1
Y1 - 2011/1/1
N2 - This paper describes a method to construct seamless image mosaics of a panoramic scene containing two predominate planes: a distant back plane and a ground plane that sweeps out from the camera's location. While this type of panorama can be stitched when the camera is carefully rotated about its optical center, such ideal scene capture is hard to perform correctly. Existing techniques use a single homography per image to perform alignment followed by seam cutting or image blending to hide inevitable alignments artifacts. In this paper, we demonstrate how to use two homographies per image to produce a more seamless image. Specifically, our approach blends the homographies in the alignment procedure to perform a nonlinear warping. Once the images are geometrically stitched, they are further processed to blend seams and reduce curvilinear visual artifacts due to the nonlinear warping. As demonstrated in our paper, our procedure is able to produce results for this type of scene where current state-of-the-art techniques fail.
AB - This paper describes a method to construct seamless image mosaics of a panoramic scene containing two predominate planes: a distant back plane and a ground plane that sweeps out from the camera's location. While this type of panorama can be stitched when the camera is carefully rotated about its optical center, such ideal scene capture is hard to perform correctly. Existing techniques use a single homography per image to perform alignment followed by seam cutting or image blending to hide inevitable alignments artifacts. In this paper, we demonstrate how to use two homographies per image to produce a more seamless image. Specifically, our approach blends the homographies in the alignment procedure to perform a nonlinear warping. Once the images are geometrically stitched, they are further processed to blend seams and reduce curvilinear visual artifacts due to the nonlinear warping. As demonstrated in our paper, our procedure is able to produce results for this type of scene where current state-of-the-art techniques fail.
UR - http://www.scopus.com/inward/record.url?scp=80052913194&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052913194&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2011.5995433
DO - 10.1109/CVPR.2011.5995433
M3 - Conference contribution
AN - SCOPUS:80052913194
SN - 9781457703942
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 49
EP - 56
BT - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
PB - IEEE Computer Society
ER -