Video Completion for Generating Omnidirectional Video without Invisible Areas
-
- Kawai Norihiko
- Graduate School of Information Science, Nara Institute of Science and Technology Research Fellow of the Japan Society for the Promotion of Science
-
- Machikita Kotaro
- Graduate School of Information Science, Nara Institute of Science and Technology
-
- Sato Tomokazu
- Graduate School of Information Science, Nara Institute of Science and Technology
-
- Yokoya Naokazu
- Graduate School of Information Science, Nara Institute of Science and Technology
Search this article
Abstract
Omnidirectional multi-camera systems cannot capture entire fields of view because of their inability to view areas directly below them. Such invisible areas in omnidirectional video decrease the resulting realistic sensation experienced when using a telepresence system. In this study, we generate omnidirectional video without invisible areas using an image completion technique. The proposed method compensates for the change in appearance of textures caused by camera motion and searches for appropriate exemplars considering three-dimensional geometric information. In our experiments, the effectiveness of our proposed method has been demonstrated by successfully filling in missing regions in real video sequences captured using an omnidirectional multi-camera system.
Journal
-
- IPSJ Transactions on Computer Vision and Applications
-
IPSJ Transactions on Computer Vision and Applications 2 200-213, 2010
Information Processing Society of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390001205293546880
-
- NII Article ID
- 130000419285
- 120005867194
-
- NII Book ID
- AA12394973
-
- ISSN
- 18827772
- 18826695
- 03875806
-
- HANDLE
- 10061/11036
-
- NDL BIB ID
- 024316167
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- IRDB
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed