Details
| Original language | English |
|---|---|
| Title of host publication | Computer Vision, Imaging and Computer Graphics |
| Subtitle of host publication | Theory and Application - 7th International Joint Conference, VISIGRAPP 2012, Revised Selected Papers |
| Publisher | Springer Verlag |
| Pages | 340-353 |
| Number of pages | 14 |
| ISBN (print) | 9783642382406 |
| Publication status | Published - 2013 |
| Event | 7th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2012 - Rome, Italy Duration: 24 Feb 2012 → 26 Feb 2012 |
Publication series
| Name | Communications in Computer and Information Science |
|---|---|
| Volume | 359 CCIS |
| ISSN (Print) | 1865-0929 |
Abstract
The segmentation of foreground objects in camera images is a fundamental step in many computer vision applications. For visual effect creation, the foreground segmentation is required for the integration of virtual objects between scene elements. On the other hand, camera and scene estimation is needed to integrate the objects perspectively correct into the video. In this paper, discontinued feature tracks are used to detect occlusions. If these features reappear after their occlusion, they are connected to the correct previously discontinued trajectory during sequential camera and scene estimation. The combination of optical flow for features in consecutive frames and SIFT matching for the wide baseline feature connection provides accurate and stable feature tracking. The knowledge of occluded parts of a connected feature track is used to feed an efficient segmentation algorithm which crops the foreground image regions automatically. The presented graph cut based segmentation uses a graph contraction technique to minimize the computational expense. The presented application in the integration of virtual objects into video. For this application, the accurate estimation of camera and scene is crucial. The segmentation is used for the automatic occlusion of the integrated objects with foreground scene content. Demonstrations show very realistic results.
ASJC Scopus subject areas
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Computer Vision, Imaging and Computer Graphics: Theory and Application - 7th International Joint Conference, VISIGRAPP 2012, Revised Selected Papers. Springer Verlag, 2013. p. 340-353 (Communications in Computer and Information Science; Vol. 359 CCIS).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Foreground Segmentation from Occlusions Using Structure and Motion Recovery
AU - Cordes, Kai
AU - Scheuermann, Björn
AU - Rosenhahn, Bodo
AU - Ostermann, Jörn
PY - 2013
Y1 - 2013
N2 - The segmentation of foreground objects in camera images is a fundamental step in many computer vision applications. For visual effect creation, the foreground segmentation is required for the integration of virtual objects between scene elements. On the other hand, camera and scene estimation is needed to integrate the objects perspectively correct into the video. In this paper, discontinued feature tracks are used to detect occlusions. If these features reappear after their occlusion, they are connected to the correct previously discontinued trajectory during sequential camera and scene estimation. The combination of optical flow for features in consecutive frames and SIFT matching for the wide baseline feature connection provides accurate and stable feature tracking. The knowledge of occluded parts of a connected feature track is used to feed an efficient segmentation algorithm which crops the foreground image regions automatically. The presented graph cut based segmentation uses a graph contraction technique to minimize the computational expense. The presented application in the integration of virtual objects into video. For this application, the accurate estimation of camera and scene is crucial. The segmentation is used for the automatic occlusion of the integrated objects with foreground scene content. Demonstrations show very realistic results.
AB - The segmentation of foreground objects in camera images is a fundamental step in many computer vision applications. For visual effect creation, the foreground segmentation is required for the integration of virtual objects between scene elements. On the other hand, camera and scene estimation is needed to integrate the objects perspectively correct into the video. In this paper, discontinued feature tracks are used to detect occlusions. If these features reappear after their occlusion, they are connected to the correct previously discontinued trajectory during sequential camera and scene estimation. The combination of optical flow for features in consecutive frames and SIFT matching for the wide baseline feature connection provides accurate and stable feature tracking. The knowledge of occluded parts of a connected feature track is used to feed an efficient segmentation algorithm which crops the foreground image regions automatically. The presented graph cut based segmentation uses a graph contraction technique to minimize the computational expense. The presented application in the integration of virtual objects into video. For this application, the accurate estimation of camera and scene is crucial. The segmentation is used for the automatic occlusion of the integrated objects with foreground scene content. Demonstrations show very realistic results.
UR - http://www.scopus.com/inward/record.url?scp=84904666774&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-38241-3_23
DO - 10.1007/978-3-642-38241-3_23
M3 - Conference contribution
AN - SCOPUS:84904666774
SN - 9783642382406
T3 - Communications in Computer and Information Science
SP - 340
EP - 353
BT - Computer Vision, Imaging and Computer Graphics
PB - Springer Verlag
T2 - 7th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2012
Y2 - 24 February 2012 through 26 February 2012
ER -