<<
| Journal | Signal Processing: Image Communication |
| Editor | EURASIP |
| Publisher | Elsevier |
| Date | 05.01.2007 |
| Author(s) | Evren Imre, Sebastian Knorr, Burak Ozkalayci, Ugur Topay, A. Aydin Alatan and Thomas Sikora |
| Title | Towards 3-D Scene Reconstruction from Broadcast Video |
| Abstract | Three-dimensional (3-D) scene reconstruction from broadcast video is a challenging problem with many potential applications, such as 3-D TV, free-view TV, augmented reality or three-dimensionalization of two-dimensional (2-D) media archives. In this paper, a flexible and effective system capable of efficiently reconstructing 3-D scenes from broadcast video is proposed, with the assumption that there is relative motion between camera and scene/objects. The system requires no a priori information and input, other than the video sequence itself, and capable of estimating the internal and external camera parameters and performing a 3-D motion-based segmentation, as well as computing a dense depth field. The system also serves as a showcase to present some novel approaches for moving object segmentation, sparse and dense reconstruction problems. According to the simulations for both synthetic and real data, the system achieves a promising performance for typical TV content, indicating that it is a significant step towards the 3-D reconstruction of scenes from broadcast video. |
| Key words | Structure from motion; Feature tracking; Feature segmentation; Dense 3-D reconstruction; 3-D TV |
| Note | E. Imre, B. Özkalayci, U. Topay, A. A. Alatan: Middle East Technical University, Turkey |
| URL | http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V08-4MRNT3C-1&_user=1773525&_coverDate=01%2F05%2F2007&_rdoc=13&_fmt=summary&_orig=browse&_srch=doc-info(%23toc%235640%239999%23999999999%2399999%23FLA%23display%23Articles)&_cdi=5640&_sort=d&_docanchor=&view=c&_ct=24&_acct=C000054491&_version=1&_urlVersion=0&_userid=1773525&md5=75ad72b359f51cb59b0ad44a0251f975 |
BibTeX