Image analysis and interpretation for semantics categorization in baseball video
Authors:
- Huang-Chia ShihHSHuang-Chia Shih
- Chung-Lin HuangCHChung-Lin Huang
- 13 May 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 379-383
Abstract
[[abstract]]The semantic information in videos is useful for content-based video retrieval and summarization. Traditional image/video understanding is formulated in terms of low-level features describing the structure and intensity of the input image/video. The way to generate the high-level knowledge such as common sense and human perceptual knowledge is one of the most difficult problems This paper attempts to bridge this gap through the integration of image analysis algorithms and multi-level semantic network (SN) to interpret the semantic meaning of the baseball video[[fileno]]2030109030077[[department]]電機工程學Keywords
This publication has 7 references indexed in Scilit:
- Bayesian modeling of video editing and structure: semantic features for video summarization and browsing2002
- Spatio-temporal video search using the object based video representation2002
- On the application of Bayes networks to semantic understanding of consumer photographs2002
- Color and texture descriptorsIEEE Transactions on Circuits and Systems for Video Technology, 2001
- A model-based hand gesture recognition systemMachine Vision and Applications, 2001
- The expectation-maximization algorithmIEEE Signal Processing Magazine, 1996
- An algebra of bayesian belief universes for knowledge‐based systemsNetworks, 1990