Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2016 IEEE International Conference on Image Processing |
| Untertitel | ICIP 2016 - Proceedings |
| Herausgeber (Verlag) | IEEE Computer Society |
| Seiten | 2961-2965 |
| Seitenumfang | 5 |
| ISBN (elektronisch) | 9781467399616 |
| Publikationsstatus | Veröffentlicht - Aug. 2016 |
| Veranstaltung | 23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, USA / Vereinigte Staaten Dauer: 25 Sept. 2016 → 28 Sept. 2016 |
Publikationsreihe
| Name | Proceedings - International Conference on Image Processing, ICIP |
|---|---|
| Band | 2016-August |
| ISSN (Print) | 1522-4880 |
Abstract
For the generation of overview panoramic images from aerial surveillance videos, registered video frames are stitched together. Assuming a planar landscape, feature points can be detected and used to estimate a homography. However, if the features are affected by radial distortion, their mapping depends on their position within the frame and the resulting homography becomes inaccurate. As a result, the length of aerial panorama images is typically restricted to several hundred frames. To overcome this issue, we derive a model for the joint estimation of several homographies and one constant radial distortion. Due to the computational complexity of the solution, we propose a fast, iterative algorithm. Based on geometrical constraints, we regularize the projection of a jointly estimated picture group. We present panorama images from uncalibrated aerial videos with more than 1500 frames.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Software
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
- Informatik (insg.)
- Signalverarbeitung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2016 IEEE International Conference on Image Processing: ICIP 2016 - Proceedings. IEEE Computer Society, 2016. S. 2961-2965 7532902 (Proceedings - International Conference on Image Processing, ICIP; Band 2016-August).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - In-loop radial distortion compensation for long-term mosaicing of aerial videos
AU - Meuel, Holger
AU - Ferenz, Stephan
AU - Munderloh, Marco
AU - Ackermann, Hanno
AU - Ostermann, Jörn
PY - 2016/8
Y1 - 2016/8
N2 - For the generation of overview panoramic images from aerial surveillance videos, registered video frames are stitched together. Assuming a planar landscape, feature points can be detected and used to estimate a homography. However, if the features are affected by radial distortion, their mapping depends on their position within the frame and the resulting homography becomes inaccurate. As a result, the length of aerial panorama images is typically restricted to several hundred frames. To overcome this issue, we derive a model for the joint estimation of several homographies and one constant radial distortion. Due to the computational complexity of the solution, we propose a fast, iterative algorithm. Based on geometrical constraints, we regularize the projection of a jointly estimated picture group. We present panorama images from uncalibrated aerial videos with more than 1500 frames.
AB - For the generation of overview panoramic images from aerial surveillance videos, registered video frames are stitched together. Assuming a planar landscape, feature points can be detected and used to estimate a homography. However, if the features are affected by radial distortion, their mapping depends on their position within the frame and the resulting homography becomes inaccurate. As a result, the length of aerial panorama images is typically restricted to several hundred frames. To overcome this issue, we derive a model for the joint estimation of several homographies and one constant radial distortion. Due to the computational complexity of the solution, we propose a fast, iterative algorithm. Based on geometrical constraints, we regularize the projection of a jointly estimated picture group. We present panorama images from uncalibrated aerial videos with more than 1500 frames.
KW - Long-term mosaicing
KW - On-Board Image Distortion
KW - Panorama Image
KW - Stitching
UR - http://www.scopus.com/inward/record.url?scp=85006765800&partnerID=8YFLogxK
U2 - 10.1109/icip.2016.7532902
DO - 10.1109/icip.2016.7532902
M3 - Conference contribution
AN - SCOPUS:85006765800
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2961
EP - 2965
BT - 2016 IEEE International Conference on Image Processing
PB - IEEE Computer Society
T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016
Y2 - 25 September 2016 through 28 September 2016
ER -