Extraction of 3D scene structure for semantic annotation and retrieval of unedited video.
Ingo FeldmannWolfgang WaizeneggerOliver SchreerPublished in: MMSP (2008)
Keyphrases
- d scene
- semantic annotation
- automatic annotation
- planar patches
- single image
- semantically annotated
- depth map
- optical flow
- semantic web
- video sequences
- video data
- camera viewpoint
- learning algorithm
- information retrieval
- general purpose
- image retrieval
- semi automatic
- high level
- decision trees
- video content
- view synthesis
- machine learning
- databases